A system and method for generating a target pose model

Abstract

Embodiments of the present application provide a method and system for generating a target pose model. The method includes obtaining image data of a target object. The method includes generating an object model of the target object based on the image data. The method also includes obtaining a reference pose model related to the target object. The method further includes generating the target pose model of the target object based on the object model and the reference pose model.

Description

[0001] Case Analysis

[0002] This application is a divisional application of Chinese application No. 202110848460.X, filed on July 27, 2021, entitled "An Imaging System and Method," which claims priority to international application No. PCT / CN2020 / 104970, filed on July 27, 2020, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application generally relates to medical imaging, and more specifically to systems and methods for automated scan preparation in medical imaging. Background Technology

[0004] In recent years, medical imaging technology has been widely used in clinical examinations and medical diagnosis. For example, with the development of X-ray imaging technology, digital radiography (DR) systems have become increasingly important in procedures such as breast tomography and chest examinations. Summary of the Invention

[0005] According to one aspect of this application, a method for generating a target pose model of a target object may include one or more operations. The one or more operations may be implemented on a computing device having one or more processors and one or more storage devices. The one or more processors may acquire image data of the target object. The one or more processors may generate an object model of the target object based on the image data. The one or more processors may also acquire a reference pose model associated with the target object. The one or more processors may also generate a target pose model of the target object based on the object model and the reference pose model.

[0006] Some of the additional features of this application will be described in the following description. Some of these additional features will be apparent to those skilled in the art from the study of the following description and the accompanying drawings, or from an understanding of the production or operation of the embodiments. The features of this application can be implemented and achieved through the practice or use of various methods, means, and combinations of the specific embodiments described below. Attached Figure Description

[0007] This application will be further described through exemplary embodiments. These exemplary embodiments will be described in detail with reference to the accompanying drawings. The drawings are not drawn to scale. These embodiments are non-limiting exemplary embodiments, in which the same numbers in the figures denote similar structures, wherein:

[0008] Figure 1 These are schematic diagrams of exemplary imaging systems according to some embodiments of this application;

[0009] Figure 2 These are schematic diagrams of exemplary hardware and / or software components of a computing device according to some embodiments of this application;

[0010] Figure 3 These are schematic diagrams of exemplary hardware and / or software components of a mobile device according to some embodiments of this application;

[0011] Figure 4A These are schematic diagrams of exemplary medical imaging devices according to some embodiments of this application;

[0012] Figure 4B This is a schematic diagram of an exemplary support device for a medical imaging apparatus according to some embodiments of this application;

[0013] Figure 5A This is a flowchart illustrating the traditional process of scanning a target object;

[0014] Figure 5B This is a flowchart illustrating an exemplary process for scanning a target object according to some embodiments of this application;

[0015] Figure 6 This is a flowchart illustrating an exemplary scan preparation process according to some embodiments of this application;

[0016] Figure 7 This is a block diagram of an exemplary processing apparatus according to some embodiments of this application;

[0017] Figure 8 This is a flowchart illustrating an exemplary process for identifying a target object to be scanned, according to some embodiments of this application;

[0018] Figure 9 This is a flowchart illustrating an exemplary process for generating a target pose model of a target object according to some embodiments of this application;

[0019] Figure 10 This is a flowchart illustrating an exemplary scan preparation process according to some embodiments of this application;

[0020] Figure 11A This is a schematic diagram of an exemplary patient model of a patient according to some embodiments of this application;

[0021] Figure 11B This is a schematic diagram of an exemplary patient model of a patient according to some embodiments of this application;

[0022] Figure 12 This is a flowchart illustrating an exemplary process for controlling the optical field of a medical imaging device according to some embodiments of this application;

[0023] Figure 13 This is a flowchart illustrating an exemplary process for determining a target object according to some embodiments of this application;

[0024] Figure 14 These are schematic diagrams of exemplary images of hands in different orientations, as shown in some embodiments of this application;

[0025] Figure 15 This is a flowchart illustrating an exemplary process for dose estimation according to some embodiments of this application;

[0026] Figure 16A This is a flowchart illustrating an exemplary process for selecting a target ionization chamber from a plurality of ionization chambers, according to some embodiments of this application;

[0027] Figure 16B This is a flowchart illustrating an exemplary process for selecting at least one target ionization chamber for a target object's ROI based on target image data of the target object, according to some embodiments of this application;

[0028] Figure 16C This is a flowchart illustrating an exemplary process for selecting at least one target ionization chamber for a target object's ROI based on target image data of the target object, according to some embodiments of this application;

[0029] Figure 17 This is a flowchart illustrating an exemplary process for object location according to some embodiments of this application;

[0030] Figure 18 These are schematic diagrams of exemplary composite images shown according to some embodiments of this application;

[0031] Figure 19 This is a flowchart illustrating an exemplary process for image display according to some embodiments of this application;

[0032] Figure 20 These are schematic diagrams of exemplary display images relating to a target object, as shown in some embodiments of this application; and

[0033] Figure 21 This is a flowchart illustrating an exemplary process for imaging a target object according to some embodiments of this application. Detailed Implementation

[0034] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. However, those skilled in the art should understand that this application can be implemented without these details. In other instances, to avoid unnecessarily obscuring various aspects of this application, well-known methods, processes, systems, components, and / or circuits have been described at a higher level. It will be apparent to those skilled in the art that various changes can be made to the disclosed embodiments, and the general principles defined in this application can be applied to other embodiments and application scenarios without departing from the principles and scope of this application. Therefore, this application is not limited to the embodiments shown, but conforms to the broadest scope consistent with the scope of the claims.

[0035] The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. As used herein, the singular forms “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and “including” as used herein only indicate the presence of the stated feature, integral, step, operation, component, and / or part, but do not exclude the presence or addition of at least one other feature, integral, step, operation, component, part, and / or combination thereof.

[0036] It will be understood that the terms “system,” “engine,” “unit,” “module,” and / or “block” used herein are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels in ascending order. However, these terms may be replaced with other expressions if they serve the same purpose.

[0037] Generally, the terms “module,” “unit,” or “block” as used herein refer to a collection of logical or software instructions embodied in hardware or firmware. The modules, units, or blocks described herein may be implemented as software and / or hardware and may be stored in any type of non-transitory computer-readable medium or other storage device. In some embodiments, software modules / units / blocks may be compiled and linked into an executable program. It will be appreciated that software modules may be invoked from other modules / units / blocks or from themselves, and / or may be invoked in response to detected events or interrupts. Software modules / units / blocks configured to execute on a computing device (e.g., such as…) Figure 2The processor 210 shown can be located on a computer-readable medium, such as an optical disc, digital video disc, flash drive, hard disk, or any other tangible media, or as a digital download (and can be initially stored in a compressed or installable format that requires installation, decompression, or decryption before execution). Such software code can be stored, partially or wholly, on the storage device of the executing computing device and applied to the operation of the computing device. Software instructions can be embedded in firmware, such as EPROM. It will also be appreciated that hardware modules / units / blocks can be included in connected logical components, such as gates and flip-flops, and / or can be included in programmable units, such as programmable gate arrays or processors. The modules / units / blocks or computing device functions described herein can be implemented as software modules / units / blocks, or can be represented in hardware or firmware. Typically, the modules / units / blocks described herein can be combined with other modules / units / blocks, or, although they are physically organized or stored, can be divided into submodules / subunits / subblocks. This description can apply to a system, an engine, or a part thereof.

[0038] It will be understood that when a unit, engine, module, or block is referred to as being "on," "connected," or "coupled to" another unit, engine, module, or block, it may be directly on, connected to, coupled to, or communicate with the other unit, engine, module, or block, or there may be intermediate units, engines, modules, or blocks, unless the context clearly indicates otherwise. In this application, the term "and / or" may include any one or more of the related listed items or a combination thereof. The term "image" in this application is used collectively to refer to image data (e.g., scanned data, projected data) and / or images of various forms, including two-dimensional (2D) images, three-dimensional (3D) images, four-dimensional (4D) images, etc. The terms "pixel" and "voxel" in this application are used interchangeably and refer to an element of an image. In this application, the terms "region," "location," and "area" may refer to the location of an anatomical structure shown in an image, or to the actual location of an anatomical structure existing within or on a target object. Therefore, an image may indicate the actual location of certain anatomical structures existing within or on a target object. For the sake of brevity, the term "object image" may be referred to as "object". Segmentation of an object image may be referred to as object segmentation.

[0039] These and other features, characteristics, and functions and methods of operation of related structural elements, as well as the economic efficiency of component assembly and manufacture, will become more apparent when considering the following description with reference to the accompanying drawings, which form part of this specification. However, it should be understood that the drawings are for illustrative and descriptive purposes only and are not intended to limit the scope of this application. It should be understood that the drawings are not drawn to scale.

[0040] Traditional medical imaging procedures often require significant human intervention. For example, users (e.g., doctors, operators, technicians, etc.) may need to manually perform scan preparation to scan a target object. This involves, for instance, adjusting the position of at least two components of the medical imaging apparatus, setting one or more scan parameters, guiding the target object to maintain a specific pose, and detecting the target object's position. Such medical imaging processes can be inefficient and / or susceptible to human error or subjectivity. Therefore, it is desirable to develop systems and methods for automated scan preparation in medical imaging, thereby improving imaging efficiency and / or accuracy. The terms "automated" and "automated" are used interchangeably, referring to methods and systems for analyzing information and generating results with little or no direct human intervention.

[0041] This application provides systems and methods for automated scan preparation in medical imaging. According to some embodiments of this application, at least two scan preparation operations can be performed automatically or semi-automatically. These at least two scan preparation operations may include: identifying a target object to be scanned by a medical imaging apparatus from one or more candidate objects; generating a target pose model of the target object; adjusting the position of one or more components of the medical imaging apparatus (e.g., scanning stage, detector, X-ray tube, support device); setting one or more scan parameters (e.g., light field size, estimated dose associated with the target object); guiding the target object to maintain a specific pose; detecting the position of the target object; determining the orientation of the target object; selecting at least one target ionization chamber, etc., or any combination thereof. Compared to conventional scan preparation involving significant human intervention, the systems and methods of this application can be implemented with reduced or minimized or no user intervention. For example, the systems and methods are more efficient and accurate by reducing user workload, cross-user variations, and the time required for scan preparation.

[0042] Figure 1 This is a schematic diagram of an exemplary imaging system 100 according to some embodiments of this application. As shown, the imaging system 100 may include a medical imaging device 110, a processing device 120, a storage device 130, one or more terminals 140, a network 150, and an image capture device 160. In some embodiments, the medical imaging device 110, processing device 120, storage device 130, terminal 140, and / or image capture device 160 may be interconnected and / or communicate via wireless connection, wired connection, or a combination thereof. The connections between the components of the imaging system 100 may be variable. By way of example only, the medical imaging device 110 may be connected to the processing device 120 via the network 150 or directly. As another example, the storage device 130 may be connected to the processing device 120 via the network 150 or directly.

[0043] Medical imaging apparatus 110 can generate or provide image data related to a target object by scanning the target object. For illustrative purposes, image data of a target object acquired using medical imaging apparatus 110 is referred to as medical image data, while image data of a target object acquired using image capture device 160 is referred to as image data. In some embodiments, the target object may include biological and / or non-biological objects. For example, the target object may include specific parts of the body, such as the head, chest, abdomen, etc., or combinations thereof. As another example, the target object may be a human-made component of living or non-living organic and / or inorganic matter. In some embodiments, imaging system 100 may include modules and / or components for performing imaging and / or related analyses. In some embodiments, medical image data related to the target object may include projection data of the target object, one or more images, etc. Projection data may include raw data generated by medical imaging apparatus 110 by scanning the target object and / or data generated by forward projection onto an image of the target object.

[0044] In some embodiments, the medical imaging device 110 may be a non-invasive biomedical imaging device for disease diagnosis or research purposes. The medical imaging device 110 may include a single-modal scanner and / or a multimodal scanner. A single-modal scanner may include, for example, an ultrasound scanner, an X-ray scanner, a computed tomography (CT) scanner, a magnetic resonance imaging (MRI) scanner, an ultrasound examination device, a positron emission tomography (PET) scanner, an optical coherence tomography (OCT) scanner, an ultrasound (US) scanner, an intravascular ultrasound (IVUS) scanner, a near-infrared spectroscopy (NIRS) scanner, a far-infrared (FIR) scanner, or any combination thereof. A multimodal scanner may include, for example, an X-ray imaging-magnetic resonance imaging (X-MRI) scanner, a positron emission tomography-X-ray imaging (PET-X-ray) scanner, a single-photon emission computed tomography-magnetic resonance imaging (SPECT-MRI) scanner, a positron emission tomography-computed tomography (PET-CT) scanner, a digital subtraction angiography-magnetic resonance imaging (DSA-MRI) scanner, etc. The scanners described above are for illustrative purposes only and are not intended to limit the scope of this application. As used herein, the term "imaging modality" or "modality" broadly refers to imaging methods or techniques for collecting, generating, processing, and / or analyzing imaging information of a target object.

[0045] For illustrative purposes, this application primarily describes systems and methods related to X-ray imaging systems. It should be noted that the X-ray imaging systems described below are provided as examples only and are not intended to limit the scope of this application. The systems and methods disclosed herein can be any other imaging system.

[0046] In some embodiments, the medical imaging apparatus 110 may include a gantry 111, a detector 112, a detection area 113, a scanning stage 114, and a radiation source 115. The gantry 111 may support the detector 112 and the radiation source 115. A target object may be placed on the scanning stage 114 and then moved to the detection area 113 for scanning. The radiation source 115 may emit radioactive rays toward the target object. The radioactive rays may include particle rays, photon rays, etc., or combinations thereof. In some embodiments, the radioactive rays may include at least two radiating particles (e.g., neutrons, protons, electrons, muons, heavy ions), at least two radiating photons (e.g., X-rays, gamma rays, ultraviolet rays, lasers), etc., or combinations thereof. The detector 112 may detect radiation and / or radiation events (e.g., gamma photons) emitted from the detection area 113. In some embodiments, the detector 112 may include at least two detector units. Detector units may include scintillation detectors (e.g., cesium iodide detectors) or gas detectors. Detector units may be single-row detectors or multi-row detectors.

[0047] In some embodiments, the medical imaging apparatus 110 may be or include X-ray imaging equipment, such as a computed tomography (CT) scanner, a digital radiography (DR) scanner (e.g., moving digital radiography), a digital subtraction angiography (DSA) scanner, a dynamic spatial reconstruction (DSR) scanner, an X-ray microscopy scanner, a multimodal scanner, etc. For example, the X-ray imaging equipment may include a support, an X-ray source, and a detector. The support may be configured to support the X-ray source and / or the detector. The X-ray source may be configured to emit X-rays toward the target object to be scanned. The detector may be configured to detect X-rays that pass through the target object. In some embodiments, the X-ray imaging equipment may be, for example, a C-shaped X-ray imaging equipment, an upright X-ray imaging equipment, a suspended X-ray imaging equipment, etc.

[0048] Processing device 120 can process data and / or information acquired from medical imaging device 110, storage device 130, terminal 140, and / or image capture device 160. For example, processing device 120 can perform automatic scan preparation for scanning a target object. Automatic scan preparation may include, for example, identifying the target object to be scanned, generating a target pose model of the target object, moving the moving components of medical imaging device 110 to their target positions, determining one or more scan parameters (e.g., light field), or any combination thereof. Further description of automatic scan preparation can be found elsewhere in this application. See, for example... Figure 5B and Figure 6 Related descriptions.

[0049] In some embodiments, processing device 120 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processing device 120 may be local or remote to imaging system 100. For example, processing device 120 may access information and / or data from medical imaging device 110, storage device 130, terminal 140, and / or image capture device 160 via network 150. Alternatively, processing device 120 may be directly connected to medical imaging device 110, terminal 140, storage device 130, and / or image capture device 160 to access information and / or data. In some embodiments, processing device 120 may be implemented on a cloud platform. For example, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multi-cloud, etc., or combinations thereof. In some embodiments, processing device 120 may be configured with one or more servers such as... Figure 2 The computing device 200 that describes the components is implemented.

[0050] In some embodiments, the processing device 120 may include one or more processors (e.g., a single-chip processor or a multi-chip processor). By way of example only, the processing device 120 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, or any combination thereof.

[0051] Storage device 130 can store data, instructions, and / or any other information. In some embodiments, storage device 130 can store data acquired from processing device 120, terminal 140, medical imaging device 110, and / or image capture device 160. In some embodiments, storage device 130 can store data and / or instructions that can be executed by processing device 120 or used to execute the exemplary methods described in this application. In some embodiments, storage device 130 may include mass storage devices, removable storage devices, volatile read-write memory, read-only memory (ROM), etc., or any combination thereof. Exemplary mass storage devices may include disks, optical disks, solid-state drives, etc. Exemplary removable storage devices may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tapes, etc. Exemplary volatile read-write memory may include random access memory (RAM). Exemplary RAM may include dynamic random access memory (DRAM), double data rate synchronous dynamic access memory (DDR SDRAM), static random access memory (SRAM), thyristor random access memory (T-RAM), and zero-capacitance random access memory (Z-RAM), etc. Exemplary ROMs may include mask-mode read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), optical disc read-only memory (CD-ROM), and digital universal optical disc read-only memory, etc. In some embodiments, storage device 130 may be implemented on a cloud platform as described elsewhere in this application.

[0052] In some embodiments, storage device 130 may be connected to network 150 to communicate with one or more other components of imaging system 100 (e.g., processing device 120, terminal 140). One or more components of imaging system 100 may access data or instructions stored in storage device 130 via network 150. In some embodiments, storage device 130 may be part of processing device 120.

[0053] Terminal 140 enables interaction between a user and imaging system 100. For example, terminal 140 can display a composite image in which a target object and a target pose model of the target object are superimposed. In some embodiments, terminal 140 may include mobile device 141, tablet computer 142, laptop computer 143, etc., or any combination thereof. For example, mobile device 141 may include mobile phone, personal digital assistant (PDA), gaming device, navigation device, point-of-sale (POS) device, laptop computer, tablet computer, desktop computer, etc., or any combination thereof. In some embodiments, terminal 140 may include input device, output device, etc. In some embodiments, terminal 140 may be part of processing device 120.

[0054] Network 150 may include any suitable network that can facilitate the exchange of information and / or data between imaging system 100. In some embodiments, components of one or more imaging systems 100 (e.g., medical imaging device 110, processing device 120, storage device 130, terminal 140) may communicate information and / or data with other components of one or more imaging systems 100 via network 150. For example, processing device 120 may acquire medical image data from medical imaging device 110 via network 150. As another example, processing device 120 may acquire user instructions from terminal 140 via network 150.

[0055] Network 150 may be or include public networks (e.g., the Internet), private networks (e.g., local area networks (LANs)), wired networks, wireless networks (e.g., 802.11 networks, Wi-Fi networks), Frame Relay networks, virtual private networks (VPNs), satellite networks, telephone networks, routers, hubs, switches, server computers, and / or any combination thereof. For example, network 150 may include cable networks, wired networks, fiber optic networks, telecommunications networks, intranets, wireless local area networks (WLANs), metropolitan area networks (MANs), public switched telephone networks (PSTNs), Bluetooth networks, ZigBee networks, near field communication (NFC) networks, etc., or any combination thereof. In some embodiments, network 150 may include one or more network access points. For example, network 150 may include wired and / or wireless network access points such as base stations and / or internet switching points, through which one or more components of imaging system 100 can connect to network 150 to exchange data and / or information.

[0056] Before, during, and / or after the medical imaging apparatus 110 performs a scan on a target object, the image capture device 160 may be configured to capture image data of the target object. For example, before scanning, the image capture device 160 may capture first image data of the target object, which may be used to generate a target pose model of the target object and / or determine one or more scanning parameters of the medical imaging apparatus 110. As another example, after the target object is in the scanning position (i.e., the specific position receiving the scan), the image capture device 160 may be configured to capture second image data of the target object, which may be used to check whether the position and pose of the target object need adjustment.

[0057] Image capture device 160 can be and / or includes any suitable device capable of capturing image data of a target object. For example, image capture device 160 may include a camera (e.g., a digital camera, analog camera, etc.), a red-green-blue (RGB) sensor, an RGB depth (RGB-D) sensor, or other devices capable of capturing color image data of the target object. As another example, image capture device 160 can be used to acquire point cloud data of the target object. Point cloud data may include at least two data points, each representing a physical point on the surface of the target object, and can be described using feature values ​​of one or more physical points (e.g., feature values ​​related to the location and / or composition of the physical point). Exemplary image capture device 160 capable of acquiring point cloud data may include a 3D scanner, such as a 3D laser imaging device, or a structured light scanner (e.g., a structured light laser scanner). By way of example only, a structured light scanner can be used to scan a target object to acquire point cloud data. During scanning, the structured light scanner can project structured light (e.g., structured light spots, structured light grids) with a certain pattern onto the target object. Point cloud data can be acquired based on the structured light projected onto the target object. As another example, image capture device 160 can be used to acquire depth image data of a target object. Depth image data can refer to image data that includes depth information for each physical point on the surface of the target object, such as the distance from each physical point to a specific point (e.g., the optical center of image capture device 160). Depth image data can be captured by a range sensing device, such as a structured light scanner, a time-of-flight (TOF) device, a stereo triangulation camera, a laser triangulation device, an interferometric device, a coded aperture device, a stereo matching device, or any combination thereof.

[0058] In some embodiments, such as Figure 1 As shown, the image capture device 160 may be a device independent of the medical imaging device 110. For example, the image capture device 160 may be a camera mounted on the ceiling of an examination room, with the medical imaging device 160 located inside or outside the examination room. Alternatively, the image capture device 160 may be integrated into or mounted on the medical imaging device 110 (e.g., rack 111). In some embodiments, image data acquired by the image capture device 160 may be transmitted to a processing device 120 for further analysis. Additionally or alternatively, the image data acquired by the image capture device 160 may be sent to a terminal device (e.g., terminal 140) for display and / or to a storage device (e.g., storage device 130) for storage.

[0059] In some embodiments, before, during, and / or after a scan of the target object by the medical imaging device 110, the image capturing device 160 may continuously or intermittently (e.g., periodically) capture image data of the target object. In some embodiments, the acquisition of image data by the image capturing device 160, the transmission of the captured image data to the processing device 120, and the analysis of the image data may be performed substantially in real time, so that the image data can provide information indicating the basic real-time state of the target object.

[0060] It should be noted that the above description of the imaging system 100 is intended to be illustrative and not to limit the scope of this application. Many alternatives, modifications, and variations will be apparent to those skilled in the art. The features, structures, methods, and other features of the exemplary embodiments described herein can be combined in various ways to obtain additional and / or alternative exemplary embodiments. For example, the imaging system 100 may include one or more additional components. Additionally or alternatively, one or more components of the imaging system 100, such as the image capturing device 160 or medical imaging device 110 described above, may be omitted. As another example, two or more components of the imaging system 100 may be integrated into a single component. By way of example only, the processing device 120 (or a portion thereof) may be integrated into the medical imaging device 110 or the image capturing device 160.

[0061] Figure 2 This is a schematic diagram of exemplary hardware and / or software components of a computing device 200 according to some embodiments of this application. As described herein, the computing device 200 can be used to implement any component of the imaging system 100. For example, the processing device 120 and / or the terminal 140 can be implemented on the computing device 200, respectively, through their hardware, software programs, firmware, or combinations thereof. Although only one such computing device is shown, for convenience, the computer functions associated with the imaging system 100 described herein can be implemented in a distributed manner on multiple similar platforms to distribute the processing load. Figure 2 As shown, computing device 200 may include processor 210, storage device 220, input / output (I / O) 230 and communication port 240.

[0062] Processor 210 can execute computer instructions (e.g., program code) and perform the functions of processing device 120 according to the techniques described herein. The computer instructions may include, for example, routines, programs, objects, components, data structures, procedures, modules, and functions that perform the specific functions described herein. For example, processor 210 can process image data acquired from medical imaging device 110, terminal 140, storage device 130, image capture device 160, and / or any other component of imaging system 100. In some embodiments, processor 210 may include one or more hardware processors, such as microcontrollers, microprocessors, reduced instruction set computers (RISC), application-specific integrated circuits (ASICs), application-specific instruction set processors (ASIPs), central processing units (CPUs), image processing units (GPUs), physical processing units (PPUs), microcontroller units, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), advanced RISC machines (ARMs), programmable logic devices (PLDs), and any circuits and processors capable of performing one or more functions, or any combination thereof.

[0063] For illustrative purposes only, only one processor is described in computing device 200. However, it should be noted that computing device 200 in this application may also include multiple processors, and therefore the operations and / or method steps performed by one processor described in this application may also be performed jointly or individually by multiple processors. For example, if the processor of computing device 200 in this application performs operations A and B, it should be understood that operations A and B may also be performed jointly or individually by two or more different processors in computing device 200 (e.g., the first processor performs operation A, the second processor performs operation B, or the first processor and the second processor jointly perform operations A and B).

[0064] Storage device 220 may store data / information acquired from medical imaging apparatus 110, terminal 140, storage device 130, image capture device 160, and / or any other component of imaging system 100. In some embodiments, storage device 220 may include mass storage device, removable storage device, volatile read-write memory, read-only memory (ROM), etc., or any combination thereof. In some embodiments, storage device 220 may store one or more programs and / or instructions to perform the exemplary methods described in this application. For example, storage device 220 may store a program for processing device 120 to perform automated scan preparation for scanning a target object.

[0065] I / O 230 can input and / or output signals, data, information, etc. In some embodiments, I / O 230 can enable user interaction with processing device 120. In some embodiments, I / O 230 may include input devices and output devices. Input devices may include letters and other keys input via a keyboard, touchscreen (e.g., with haptic input or haptic feedback), voice input, eye-tracking input, brain monitoring system, or any other similar input mechanism. Input information received through the input device may be transmitted, for example, via a bus, to another component (e.g., processing device 120) for further processing. Other types of input devices may include cursor control devices, such as a mouse, trackball, or cursor arrow keys. Output devices may include displays (e.g., liquid crystal display (LCD), light-emitting diode (LED) based displays, flat panel displays, curved screens, television equipment, cathode ray tube (CRT), touchscreens), speakers, printers, etc., or combinations thereof.

[0066] Communication port 240 can be connected to a network (e.g., network 150) to facilitate data communication. Communication port 240 can establish a connection between processing device 120 and medical imaging device 110, terminal 140, image capture device 160, and / or storage device 130. This connection can be a wired connection, a wireless connection, any other communication connection that enables data transmission and / or reception, and / or a combination of these connections. Wired connections can include, for example, cables, optical fibers, telephone lines, etc., or any combination thereof. Wireless connections can include, for example, Bluetooth connections, Wi-Fi connections, WiMax connections, WLAN connections, VPN connections, mobile network connections (e.g., 3G, 4G, 5G), etc., or combinations thereof. In some embodiments, communication port 240 can be and / or includes standardized communication ports, such as RS232, RS485, etc. In some embodiments, communication port 240 can be a specially designed communication port. For example, communication port 240 can be designed according to the Medical Digital Imaging and Communication (DICOM) protocol.

[0067] Figure 3 This is a schematic diagram of exemplary hardware and / or software components of a mobile device 300 according to some embodiments of this application. In some embodiments, components of one or more imaging systems 100 (e.g., terminal 140 and / or processing device 120) may be implemented on the mobile device 300.

[0068] like Figure 3As shown, the mobile device 300 may include a communication platform 310, a display 320, a graphics processing unit (GPU) 330, a central processing unit (CPU) 340, I / O 350, memory 360, and storage 390. In some embodiments, any other suitable components, including but not limited to a system bus or controller (not shown), may also be included in the mobile device 300. In some embodiments, a mobile operating system 370 (e.g., iOS) TM Android TM Windows Phone TM One or more applications 380 may be downloaded from storage 390 to memory 360 and executed by CPU 340. Application 380 may include a browser or any other suitable mobile application for receiving and rendering information relating to imaging system 100. User interaction with the information stream can be achieved via I / O 350 and provided to processing device 120 and / or other components of imaging system 100 via network 150.

[0069] To implement the various modules, units, and functions described in this application, a computer hardware platform may be used as the hardware platform for one or more of the components described herein. A computer with a user interface component may be used to implement a personal computer (PC) or any other type of workstation or terminal device. If the computer is properly programmed, it may also be used as a server.

[0070] Figure 4A This is a schematic diagram of an exemplary medical imaging device 400 according to some embodiments of this application. Figure 4B This is a schematic diagram of an exemplary support device 460 for a medical imaging apparatus 400 according to some embodiments of this application. The medical imaging apparatus 400 may be combined with... Figure 1 An exemplary embodiment of the described medical imaging apparatus 110. (As follows) Figure 4A As shown, the medical imaging device 400 can be a suspended digital radiography device. The medical imaging device 400 may include a scanning stage 410, an X-ray source 420, a suspension device 421, a control device 430, a flat panel detector 440, and a column 450.

[0071] In some embodiments, the scanning stage 410 may include a support component 411 and a drive component 412. The support component 411 may be configured to support the target object to be scanned. The drive component 412 may be configured to drive the support component to move, such as translate and / or rotate. The positive direction of the X-axis of the coordinate system 470 represents the direction from the left edge to the right edge of the scanning stage 410 (or support component 411). The positive direction of the Y-axis of the coordinate system 470 represents the direction from the lower edge to the upper edge of the scanning stage 410 (or support component 411).

[0072] The suspension device 421 can be configured to suspend the X-ray source 420 and control the movement of the X-ray source 420. For example, the suspension device 421 can control the movement of the X-ray source 420 to adjust the distance between the X-ray source 420 and the flat panel detector 440. In some embodiments, the X-ray source 420 may include an X-ray tube and a beam constrictor. Figure 4A (Not shown in the image). The X-ray tube can be configured to emit X-rays towards a target object for scanning. A beam limiting device can be configured to control the area of ​​X-ray irradiation on the target object. Additionally or alternatively, the beam limiting device can be configured to adjust the intensity and / or quantity of X-rays irradiating the target object. In some embodiments, a handle can be mounted on the X-ray source 420. A user can hold the handle to move the X-ray source 420 to a desired position.

[0073] The flat panel detector 440 may be detachably mounted on and supported by the column 450. In some embodiments, the flat panel detector 440 may be movable relative to the column 450, for example, translating along the column 450 and / or rotating about the column 450. The control device 430 may be configured to control one or more components of the medical imaging apparatus 400. For example, the control device 430 may control the X-ray source 420 and the flat panel detector 440 to move to their respective target positions.

[0074] In some embodiments, it can be used as follows Figure 4B The support device 460 shown replaces the scanning stage 410 of the medical imaging device 400. When the medical imaging device 400 scans a target object, the support device 460 can be used to support the target object in an upright position. For example, the target object can stand, sit, or kneel on the support device 460 for scanning. In some embodiments, the support device 460 can be used in a mosaic scan of the target object. A mosaic scan refers to a scan that sequentially scans at least two regions of the target object to obtain a mosaic image of those regions. For example, a whole-body image of the target object can be obtained by sequentially performing at least two scans of each part of the target object in a mosaic scan.

[0075] In some embodiments, the support device 460 may include a support assembly 451, a first drive assembly 452, a second drive assembly 453, a fixing assembly 454, and a back plate 455. The support assembly 451 may be configured to support a target object. In some embodiments, the support assembly 451 may be a flat plate made of any suitable material with high strength and / or stability to provide stable support to the target object. The first drive assembly 452 may be configured to drive the support device in a first direction (e.g., in...). Figure 4AThe first drive assembly 452 can move on the XY plane of the coordinate system 470 shown. In some embodiments, the first drive assembly 452 can be a roller, a wheel (e.g., a caster wheel), etc. For example, the support device 460 can move on the ground via wheels.

[0076] The second drive assembly 453 can be configured to drive the support assembly 451 to move along a second direction. The second direction can be perpendicular to the first direction. For example, the first direction can be parallel to the XY plane of coordinate system 470, and the second direction can be parallel to the Z-axis direction of coordinate system 470. In some embodiments, the second drive assembly 453 can be a lifting device. For example, the second drive assembly 453 can be a scissor arm, a lever-type lifting device (e.g., a hydraulic lever lifting device), etc. The fixing assembly 454 can be configured to fix the support assembly 460 in a certain position. For example, the fixing assembly 454 can be a column, bolt, etc.

[0077] During scanning of a target object, a backplate 455 may be located between the target object and one or more other components of the medical imaging apparatus 400. The backplate 455 may be configured to separate the target object from one or more components of the medical imaging apparatus 400 (e.g., the flat panel detector 440) to avoid collisions between the target object and one or more components of the medical imaging apparatus 400 (e.g., the flat panel detector 440). In some embodiments, the backplate 455 may be made of any light-transmitting material and have a relatively low X-ray absorptivity (e.g., below a threshold). In this case, the backplate 455 may cause minimal interference to the flat panel detector 440 receiving X-rays, e.g., whether the X-ray beam emitted by the X-ray tube passes through the target object. For example, the backplate 455 may be made of materials such as polymethyl methacrylate (PMMA), polyethylene (PE), polyvinyl chloride (PVC), polystyrene (PS), high-impact polystyrene (HIPS), polypropylene (PP), acrylonitrile butadiene-styrene (ABS) resin, or any combination thereof. In some embodiments, the back plate 455 may be secured to the support assembly 451 using adhesives, threaded connections, locks, bolts, or any combination thereof. Further description of the support device 460 can be found elsewhere in this application (e.g., Figure 21 (and related descriptions).

[0078] In some embodiments, the support device 460 may further include one or more handles 456. The target object may grasp one or more handles 456 as he and / or she dismounts from the support device 460. The target object may also grasp one or more handles 456 as the support device 460 moves the target object from one scanning position to another. In some embodiments, one or more handles 456 may be movable. For example, handles 456 may be movable along... Figure 4AThe coordinate system 470 shown moves along the Z-axis. In some embodiments, the position of the handle 456 can be automatically adjusted according to, for example, the height of the target object, so that the target object can easily grip the handle. Further description of the support device can be found elsewhere in this application. See, for example... Figure 21 And its related descriptions.

[0079] It should be noted that, Figure 4A and Figure 4B The examples shown are for illustrative purposes only and are not intended to limit the scope of this application. Those skilled in the art can make various improvements and changes in form and detail to the application of the above methods and systems without departing from the principles of this application. In some embodiments, the column 450 can be constructed in any suitable manner, such as a C-shaped support, U-shaped support, G-shaped support, etc. In some embodiments, the medical imaging device 400 may include one or more additional components not described and / or one or more components not included in the description. Figure 4A and Figure 4B The components shown are as described. For example, the medical imaging device 400 may further include a camera. As another example, two or more components of the medical imaging device 400 may also be integrated into a single component. By way of example only, the first drive component 452 and the second drive component 453 may be integrated into a single drive component.

[0080] Figure 5A This is a flowchart illustrating the conventional process 500A for scanning target objects. Figure 5B This is a flowchart of an exemplary process 500B for scanning a target object, as shown in some embodiments of this application. In some embodiments, process 500B can be... Figure 1 This is implemented in the imaging system 100 shown. For example, process 500B can be stored as instructions in a storage device (e.g., storage device 130, storage device 220, storage device 390) and processed by a processing device 120 (e.g., such as...). Figure 2 The processor 210 of the computing device 200 shown, such as Figure 3 The CPU 340 of the mobile device 300 shown is as follows: Figure 7 (One or more modules shown) are executed. The operation of the procedures shown below is for illustrative purposes only. In some embodiments, process 800 may be accomplished using one or more additional operations not described, and / or without the one or more operations discussed. Additionally, as Figure 5B The order of operations of process 500B shown and described below is not intended to be restrictive.

[0081] like Figure 5A As shown, the conventional scanning process for a target object may include operations 501 to 506.

[0082] In 501, the user can select the imaging protocol and request the target object to enter the examination room.

[0083] For example, the target subject may be a patient being imaged (or treated) by a medical imaging device (e.g., medical imaging device 110) in an examination room. In some embodiments, a user (e.g., a doctor, operator, technician, etc.) may call the target subject's examination number and / or name to request the target subject to enter the examination room. In some embodiments, the user may select an imaging protocol based on the equipment parameters of the medical imaging device, the user's preferences, and / or information related to the target subject (e.g., the target subject's body size, gender, and the area to be imaged).

[0084] In 502, users can adjust the position of components of the medical imaging device.

[0085] Medical imaging devices (e.g., medical imaging device 110) may be X-ray imaging equipment (e.g., suspended X-ray imaging equipment, C-arm X-ray imaging equipment), digital radiography (DR) equipment (e.g., mobile digital X-ray imaging equipment), CT equipment, PET equipment, MRI equipment, etc., as described in other parts of this application. By way of example only, for an X-ray imaging device, one or more components may include a scanning stage (e.g., scanning stage 114), detectors (e.g., detector 112, flat panel detector 440), X-ray sources (e.g., radiation source 115, X-ray source 420), support devices (e.g., support device 460), etc. In some embodiments, a user can input the position parameters of the components according to an imaging protocol via a terminal device. Alternatively or additionally, a user can manually move the components of the medical imaging device to the appropriate position.

[0086] In 503, the target object can be positioned according to the user's instructions.

[0087] In some embodiments, the target object may need to maintain a standard pose (also known as a reference pose) while being scanned. The user can instruct the target object to stand or lie in a specific position and maintain that pose. In some embodiments, after the target object is positioned at the scanning location (i.e., the specific location receiving the scan), the user can check the target object's pose and / or position if necessary, and / or instruct the target object to adjust his / her pose and / or position.

[0088] In 504, users can fine-tune the components of the medical imaging device.

[0089] In some embodiments, after the target object is located in the scanning position, the user can further inspect and / or adjust the position of one or more components of the medical imaging device. For example, the user can determine whether the position of the detector needs to be adjusted based on the scanning position and the pose of the target object.

[0090] In 505, users can set the values ​​of scan parameters.

[0091] Scanning parameters may include X-ray tube voltage and / or current, scan mode, stage movement speed, gantry rotation speed, field of view (FOV), scan time, size of the optical field, or any combination thereof. In some embodiments, the user may set the values ​​of the scanning parameters based on the imaging protocol, information related to the target object, or any combination thereof.

[0092] In 506, the medical imaging device can be instructed to scan the target object.

[0093] In some embodiments, medical image data can be acquired when a medical imaging device scans a target object. Users can perform one or more image processing operations on the medical image data. For example, users can perform image segmentation, image classification, image scaling, image rotation, etc., on the medical image data.

[0094] like Figure 5B As shown, an exemplary process 500B for scanning a target object according to some embodiments of this application may include one or more operations 507 to 512.

[0095] In 507, the user can select the imaging protocol and require the target object to enter the examination chamber.

[0096] Operation 507 can be combined Figure 5A The described operation 501 is performed in a similar manner, and its description will not be repeated here. In some embodiments, the processing device 120 may select an imaging protocol based on, for example, the area to be scanned of the target object and / or other information about the target object. Additionally or alternatively, the processing device 120 may cause the terminal device to output a notification requiring the target object to enter the examination room.

[0097] In some embodiments, one or more candidate objects may enter the inspection chamber. The processing device 120 may automatically or semi-automatically identify the target object from one or more candidate objects. For example, when or after one or more candidate objects enter the inspection chamber, the processing device 120 may acquire image data of one or more candidate objects. The image data may be captured by an image capture device installed inside or outside the inspection chamber. The processing device 120 may automatically identify the target object from one or more candidate objects based on the image data of one or more candidate objects and reference information associated with the target object. Further description of the identification of the target object can be found elsewhere in this application (e.g., Figure 8 (and its description).

[0098] In 508, the positions of the components of the medical imaging device can be adjusted automatically or semi-automatically.

[0099] In some embodiments, the processing device 120 can determine the positions of components of a medical imaging apparatus based on image data of a target object. For example, the processing device 120 can acquire image data of a target object from an image capture device installed in an examination room. The processing device 120 can then generate an object model (or target pose model) representing the target object based on the image data. The processing device 120 can also determine the target positions of components of the medical imaging apparatus (e.g., detectors, scanning stages, support devices) based on the object model (or target pose model). Elsewhere in this application (e.g., Figure 10 , Figure 11A , Figure 11B and Figure 21 Further descriptions of how to determine the target location of medical imaging device components can be found in the [and its description].

[0100] In 509, target objects can be positioned according to user instructions or automatically generated instructions.

[0101] In some embodiments, after the target object is located at the scanning position, the processing device 120 can acquire target image data of the target object maintaining a pose. The processing device 120 can determine whether the pose of the target object needs to be adjusted based on the target image data and the target pose model. If it is determined that the pose of the target object needs to be adjusted, the processing device 120 can further generate instructions. These instructions can instruct the target object to move one or more of its body parts to maintain the target pose. Further descriptions of positioning the target object can be found elsewhere in this application (e.g., Figure 17 (and its explanation).

[0102] In some embodiments, if the target object remains in a standing position to receive a scan, the detector of the medical imaging device can be adjusted first (e.g., as shown in the image). Figure 4BThe position of the flat panel detector 440 shown. Then, the target object can be instructed to stand at a specific scanning position to receive the scan (e.g., as shown). Figure 4B As shown, the target object stands on support assembly 451 to receive a scan, and after the target object is positioned in a specific scanning location, the radiation source of the medical imaging device can be adjusted. If the target object is lying on the scanning table of the medical imaging device to receive a scan, the target object can be instructed to lie on the scanning table first, and then the radiation source and detector can be adjusted to their target positions. This avoids collisions between the target object, detector, and radiation source.

[0103] In the 510, the values ​​of the scan parameters can be determined automatically or semi-automatically.

[0104] In some embodiments, the processing device 120 may determine the values ​​of scanning parameters based on feature information (e.g., width, thickness, height) related to the region of interest (ROI) of a target object. The ROI of a target object refers to the scanned area of ​​the target object to be imaged (or diagnosed or treated) or a portion of the scanned area to be imaged (e.g., a specific organ or tissue within the scanned area). For example, the processing device 120 may determine feature information related to the ROI of the target object based on image data of the target object or an object model (or target pose model) of the target object. The processing device 120 may further determine the voltage value of the radiation source, the current value of the radiation source, and / or the exposure time of the scan based on the thickness of the ROI. Additionally or alternatively, the processing device 120 may determine the target size of the optical field based on the width and height of the ROI of the target object. Further descriptions of determining the values ​​of scanning parameters can be found elsewhere in this application (e.g., Figure 12 and Figure 15 (and its description).

[0105] In 511, scan preparation can be checked automatically or semi-automatically.

[0106] In some embodiments, the positions of components determined in operation 508, the position and / or pose of the target object, and / or the values ​​of scanning parameters determined in operation 510 can be further checked and / or adjusted. For example, the position of the active component can be manually checked and / or adjusted by the user of imaging system 100. As yet another example, after the target object is in the scanning position, an image capturing device can be used to capture target image data of the target object. The target position of the active component (e.g., a detector) can be automatically checked and / or adjusted by one or more components of imaging system 100 (e.g., processing device 120) based on the target image data. Further description of scan preparation checks based on target image data can be found elsewhere in this application. See, for example... Figures 16A to 17 and Figure 19 And related explanations.

[0107] In 512, a medical imaging device can be instructed to scan a target object.

[0108] In some embodiments, medical image data of the target object can be acquired when the target object is scanned by a medical imaging device. The processing device 120 can perform one or more additional operations to process the medical image data. For example, the processing device 120 can determine the orientation of the target object based on the medical image data and display the medical image data according to the orientation of the target object. Further description regarding the determination of the orientation of the target object can be found elsewhere in this application (e.g., Figure 13 and Figure 14 (and its explanation).

[0109] It should be noted that the above description of process 500B is provided for illustrative purposes only and is not intended to limit the scope of this application. In some embodiments, one or more additional operations may be added, and / or one or more of the operations described above may be omitted. As an example only, operation 511 may be omitted. Additionally or alternatively, the order of operations in process 500B may be modified as needed. For example, two or more operations may be performed simultaneously. As another example, operations 508-510 may be performed in any order.

[0110] Figure 6 This is a flowchart illustrating an exemplary process for scan preparation according to some embodiments of this application. Process 600 may be combined with... Figure 5B An exemplary embodiment of the process 500B is described.

[0111] In 601, the processing device 120 (e.g., analysis module 720) can identify the target object to be scanned by the medical imaging device. Further description of target object identification can be found elsewhere in this application (e.g., Figure 8 (and its description).

[0112] In 602, the processing device 120 (e.g., acquisition module 710) can acquire image data of the target object.

[0113] Image data may include 2D images, 3D images, 4D images (e.g., time-series 3D images), and / or any associated image data of the target object (e.g., scan data, projection data). Image data may include color image data, point cloud data, depth image data, mesh data, medical image data, etc., of the target object, or any combination thereof.

[0114] In some embodiments, the image data acquired in 602 may include one or more sets of image data, such as at least two images of the target object taken by an image capturing device (e.g., image capturing device 160) at at least two time points, or at least two images of the target object taken by different image capturing devices. For example, the image data may include a first set of image data captured by a specific image capturing device before the target object is in the scanning position. Additionally or alternatively, the image data may include a second set of image data (also referred to as target image data) captured by the specific image capturing device (or another image capturing device) after the target object is in the scanning position.

[0115] Then, the processing device 120 can perform automatic scan preparation. Automatic scan preparation may include one or more preparation operations, such as... Figure 6 One or more of operations 603 to 608 are shown. In some embodiments, automatic scan preparation may include at least two preparation operations. Different preparation operations may be performed based on the same set of image data or different sets of image data of the target object captured by one or more image capture devices. For example, the target pose model of the target object as described in operation 603, the target position of the moving component of the medical imaging device as described in operation 604, and the values ​​of the scan parameters as described in operation 605 may be determined based on the same set of image data or different sets of image data captured before the target object is in the scan position. As another example, the target ionization chamber described in operation 607 may be selected based on a set of image data of the target object captured after the target object is in the scan position.

[0116] For ease of description, unless the context clearly indicates otherwise, detailed descriptions of different preparation operations (e.g., Figures 8 to 21 The term "image data of the target object" refers to the same set of image data or different sets of image data of the target object.

[0117] In 603, the processing device 120 (e.g., analysis module 720) can generate a target pose model of the target object.

[0118] As used herein, the target pose model of a target object refers to a model representing the target object maintaining a target pose (or reference pose). The target pose can be a standard pose that the target object needs to maintain during a scan of the target object. Further descriptions of generating the target pose model of a target object can be found elsewhere in this application (e.g., Figure 9 (and its description).

[0119] In 604, the processing device 120 (e.g., control module 730) can move the active components of the medical imaging apparatus to their respective target locations.

[0120] For example, processing device 120 can determine the target position of a movable component (e.g., a scanning stage) based on image data acquired in 602 by determining the dimensions (e.g., height, width, thickness) of the target object, especially when the target object is substantially positioned. Additionally or alternatively, processing device 120 can determine the target position of a movable component (e.g., a detector, a support device) by generating an object model (or a target pose model) based on image data of the target object. Further description of determining the target position of movable components of a medical imaging apparatus can be found elsewhere in this application (e.g., Figure 10 , Figure 11A , Figure 11B , Figure 21 (and its explanation).

[0121] In 605, the processing device 120 (e.g., analysis module 720) can determine the value of the scanning parameters (e.g., light field).

[0122] Operation 605 can be performed in a similar manner to operation 510, and its description will not be repeated here.

[0123] In 606, the processing device 120 (e.g., analysis module 720) can determine the value of the estimated dose.

[0124] In some embodiments, the processing device 120 can acquire a relationship between a reference dose and one or more specific scanning parameters (e.g., radiation source voltage, radiation source current, exposure time, etc.). The processing device 120 can determine an estimated dose value associated with a target object based on the acquired relationship and the parameter values ​​of the specific scanning parameters. Further descriptions of determining estimated values ​​can be found elsewhere in this application (e.g., Figure 15 (and its description).

[0125] In 607, the processing device 120 (e.g., analysis module 720) can select at least one target ionization chamber.

[0126] In some embodiments, the processing device 120 may include at least two ionization chambers. At least one target ionization chamber may be activated during scanning of a target object, while other ionization chambers (if any) may be deactivated during scanning. Further description of selecting at least one target ionization chamber can be found elsewhere in this application (e.g., Figures 16A to 16C (and its description).

[0127] In 608, the processing device 120 (e.g., analysis module 720) can determine the location of the target object.

[0128] In some embodiments, the processing device 120 can determine the orientation of a target region corresponding to the ROI of a target object in the image data acquired in 601. The processing device 120 can further determine the orientation of the target object based on the orientation of the target region. In some embodiments, the processing device 120 can determine the position of the target region corresponding to the ROI of the target object in the image data, and determine the orientation of the target object based on the position of the target region. Further description of determining the orientation of the target object can be found elsewhere in this application (e.g., Figure 12 (and its description).

[0129] In some embodiments, after determining the orientation of a target object, the processing device 120 can process image data based on the orientation of the target object and display the processed image data on the user's terminal device. For example, if the orientation of the target object differs from a reference orientation (e.g., head-up orientation), the image data can be rotated to generate processed image data, wherein the representation of the target object in the processed image data may have a reference orientation. In some embodiments, the processing device 120 can process another set of image data (e.g., medical images acquired by the medical imaging device 110) based on the orientation of the target object. In some embodiments, operation 608 can be performed after scanning the target object to determine the orientation of the target object based on medical image data acquired during the scan.

[0130] In 609, the processing device 120 (e.g., analysis module 720) can perform a preparation check. This can be combined with... Figure 5B Operation 511 is performed in a similar manner to operation 609, and its description will not be repeated here.

[0131] In some embodiments, such as Figure 6 As shown, collision detection can be performed during the implementation of process 600 (or a portion thereof). For example, processing device 120 can acquire real-time image data of the inspection chamber and track the movement of components (e.g., people, image capture devices) in the inspection chamber based on the real-time image data. Processing device 120 can further estimate the probability of a collision between two or more components in the inspection chamber. If a collision is detected between different components, processing device 120 can cause a terminal device to output a notification about the collision. Additionally or alternatively, a visual interactive interface can be used to enable user interaction between the user and the imaging system and / or between the target object and the imaging system. The visual interactive interface can, for example, be combined with... Figure 1 The described terminal device 140 or in combination Figure 3The described process is implemented on mobile device 300. A visual interface can be presented within the implementation of process 600, displaying data acquired and / or generated by processing device 120 (e.g., analysis results, intermediate results). For example, a visual interface can be used to display data combined with… Figure 19 The description includes one or more displayed images. Additionally or alternatively, the visual interactive interface may receive user input from the user and / or the target object.

[0132] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the description in this application. However, such changes and modifications do not depart from the scope of this application. In some embodiments, one or more operations of 500B and process 600 may be added or omitted. For example, one or more operations 601, 608, and 609 may be omitted. In some embodiments, two or more operations may be performed simultaneously. For example, operations 601 and 602 may be performed simultaneously. As another example, operations 602 and 603 may be performed simultaneously. As yet another example, operation 605 may be performed before operation 604. In some embodiments, the automatic preparation operation of process 500B or process 600 may be performed semi-automatically by the processing device 120 based on user intervention, or manually by the user.

[0133] Figure 7 This is a block diagram of an exemplary processing device 120 according to some embodiments of this application. For example... Figure 7 As shown, the processing device 120 may include an acquisition module 710, an analysis module 720, and a control module 730.

[0134] The acquisition module 710 can be configured to acquire information related to the imaging system. For example, the acquisition module 710 can acquire image data of the target object before, during, and / or after it is scanned by a medical imaging device, wherein the image data can be captured by an image capture device (e.g., a camera installed in the examination chamber where the target object is located). As another example, the acquisition module 710 can acquire reference information including, for example, reference identity information, reference feature information, and reference image data of the target object. As yet another example, the acquisition module 710 can acquire a reference pose model of the target object. As yet another example, the acquisition module can acquire at least one scan parameter value associated with at least one scan parameter performed on the target object.

[0135] The analysis module 720 can be configured to perform one or more scan preparation operations for target object scanning by analyzing information acquired by the acquisition module 710. More information on information analysis and scan preparation operations can be found elsewhere in this application, see, for example... Figure 6 and Figure 8-21 And its related descriptions.

[0136] The control module 730 can be configured to control one or more components of the imaging system 100. For example, the control module 730 can move the moving components of the medical imaging apparatus to their respective target positions. Further description of determining the target positions of the moving components of the medical imaging apparatus can be found elsewhere in this application (e.g., Figure 10 , 11A 11B, 21 and their descriptions).

[0137] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the teachings of this application. However, these changes and modifications do not depart from the scope of this application. For example, the processing device 120 may further include a storage module ( Figure 7 (Not shown in the image). The storage module can be configured to store data generated during any process performed by any component of the processing device 120. As another example, each of the components of the processing device 120 may include a storage device. Additionally or alternatively, the components of the processing device 120 may share a common storage device.

[0138] Figure 8 This is a flowchart illustrating an exemplary process for identifying a target object to be scanned, according to some embodiments of this application. In some embodiments, process 800 may be... Figure 1 This is implemented in the imaging system 100 shown. For example, process 800 can be stored as instructions in a storage device (e.g., storage device 130, storage device 220, storage device 390) and processed by a processing device 120 (e.g., such as...). Figure 2 The processor 210 of the computing device 200 shown, such as Figure 3 The CPU 340 of the mobile device 300 shown is as follows: Figure 7 (One or more modules shown) are executed. The operation of the process shown below is for illustrative purposes only. In some embodiments, process 800 may be accomplished using one or more additional operations not described and / or without the one or more operations discussed. Additionally, as Figure 8 The order of operations of process 800 shown and described below is not intended to be limiting.

[0139] In 810, the processing device 120 (e.g., acquisition module 710) can acquire image data of one or more candidate objects. When or after a candidate object enters the inspection room, the first image capturing device can capture image data.

[0140] In some embodiments, one or more candidate subjects may include the target subject to be examined. For example, the target subject may be a patient to be imaged in an examination room by a medical imaging device (e.g., medical imaging device 110). In some embodiments, one or more candidate subjects may also include one or more persons who are not the target subject. For example, candidate subjects may include the target subject's companions (e.g., relatives, friends), doctors, nurses, technicians, etc.

[0141] As used herein, image data of a target object (e.g., a candidate object, a target object) refers to image data corresponding to the entire object or image data corresponding to a part of the target object (e.g., a body part including a patient's face). In some embodiments, image data of a target object may be two-dimensional (2D) images, three-dimensional (3D) images, four-dimensional (4D) images (e.g., a series of images changing over time), and / or any relevant image data (e.g., scan data, projection data). In some embodiments, image data of a candidate object may include color image data, point cloud data, depth image data, mesh data, etc., or any combination thereof.

[0142] Image data of the candidate object can be captured by a first image capturing device (e.g., image capturing device 160) installed in the examination room or at the entrance of the examination room. The first image capturing device can include any type of device capable of acquiring image data, as described elsewhere in this application (e.g., Figure 1 (and related descriptions), such as 3D cameras, RGB sensors, RGB-D sensors, 3D scanners, 3D laser imaging devices, structured light scanners, etc. In some embodiments, when one or more candidate objects enter the inspection chamber, the first image capturing device can automatically capture image data of one or more candidate objects.

[0143] In some embodiments, the processing device 120 may acquire image data from the first image capturing device. Alternatively, the image data may be acquired by the first image capturing device and stored in a storage device (e.g., storage device 130, storage device 220, storage 390, or an external source). The processing device 120 may acquire image data from the storage device.

[0144] In 820, the processing device 120 (e.g., acquisition module 710) can acquire reference information associated with the target object to be inspected.

[0145] Reference information associated with the target object may include reference image data of the target object, reference identity information of the target object, one or more reference features of the target object, or any other information that can be used to distinguish the target object from other people, or any combination thereof. Reference image data of the target object may include image data, which may include the target object's face. For example, reference image data may include an image of the target object after its identity has been verified. Reference identity information may include the target object's identity card (ID) number, name, gender, age, date of birth, occupation, contact information (e.g., mobile phone number), driver's license, etc., or any combination thereof. One or more reference features may include the target object's body shape (e.g., contours, height, width, thickness, ratio between two body dimensions), clothing (e.g., color, style), etc., or any combination thereof.

[0146] In some embodiments, reference information for the target object may be acquired on-site, for example, by one or more image capture devices inside or outside the inspection room. Alternatively or additionally, the reference information for the target object may be pre-generated and stored in a storage device (e.g., storage device 130, storage device 220, memory 390, or an external source). The processing device 120 may retrieve the reference information from the storage device.

[0147] Taking reference image data of the target object as an example, it can be captured by a second image capture device installed inside or outside the examination room. The first and second image capture devices can be of the same or different types. In some embodiments, the second image capture device can be the same as the first image capture device. By way of example only, before or after the object enters the examination room, a scanner (e.g., part of the second image capture device) can scan the quick response (QR) code on its medical card or examination request form to identify the object. If the object is determined to be the target object, the second image capture device can be instructed to capture reference image data of the target object.

[0148] For example, before, during, or after entering the examination room, the target object can be instructed to perform a specific action (e.g., make a specific gesture and / or sound, stand in a specific area for more than a time threshold). The processing device 120 can be configured to track the state (e.g., gesture, pose, expression, sound) of each candidate object based on, for example, image data captured by a second image capture device. If a candidate object performs a specific action, it can be identified as the target object, and the second image capture device can capture image data of that candidate object as reference image data.

[0149] In some embodiments, reference information about the target object can be obtained based on a copy image of the target object's identification document. The identification document can be the target object's ID card, health insurance card, medical card, examination application form, etc. For example, before, during, or after the target object enters the examination room, a copy image of the identification document can be obtained by scanning it with an image capture device (e.g., a first image capture device, a second image capture device, or another image capture device). Alternatively, the copy image of the identification document can be pre-generated and stored in a storage device, such as the storage device of the imaging system 100 or another system (e.g., a public security system). The processing device 120 can acquire the copy image from the image capture device or the storage device and determine the reference information of the target object based on the copy image.

[0150] For example, identification may include a photograph of the target object. Processing device 120 can detect the face of the target object in the copied image according to one or more face detection algorithms. Exemplary face detection or recognition algorithms may include knowledge-based techniques, feature-based techniques, template matching techniques, eigenface-based techniques, distribution-based techniques, neural network-based techniques, support vector machine (SVM) techniques, sparse Winnows network (SNoW)-based techniques, naive Bayesian classifiers, hidden Markov models, information theory algorithms, inductive learning techniques, etc. Processing device 120 can segment the face of the target object from the copied image based on one or more image segmentation algorithms. Exemplary image segmentation algorithms may include region-based algorithms (e.g., thresholding segmentation, region growing segmentation), edge detection segmentation algorithms, compression-based algorithms, histogram-based algorithms, dual clustering algorithms, etc. The segmented face of the target object may be referred to as reference image data of the target object.

[0151] For example, the identity verification may include reference identity information of the target object. The processing device 120 can identify the reference identity information in the copied image according to one or more text recognition algorithms. Exemplary text recognition algorithms may include template algorithms, indicator algorithms, structure recognition algorithms, artificial neural networks, etc.

[0152] In some embodiments, reference information for a target object can be determined based on a unique symbol associated with the target object. The unique symbol may include a barcode, a QR code, a serial number comprising letters and / or numbers, or any combination thereof. For example, reference information for the target object can be obtained by scanning a QR code on a wristband or target object tag via an image capture device (e.g., a first image capture device, a second image capture device, or other image capture device). In some embodiments, a user, such as the target object or a doctor, may manually input reference identification information via a terminal device of the imaging system 100 (e.g., terminal device 140).

[0153] In 830, the processing device 120 (e.g., analysis module 720) can identify the target object from one or more candidate objects based on reference information and image data.

[0154] In some embodiments, the processing device 120 can identify a target object from one or more candidate objects based on reference image data of the target object and image data of one or more candidate objects. As an example only, the processing device 120 can obtain reference feature information of the target object from the reference image data. The reference feature information may include the target object or parts of the target object, such as the face of the target object (e.g., eyes, nose, mouth), its shape (e.g., contour, area, height, width, aspect ratio), color, texture, etc., or any combination thereof. For example, the processing device 120 can detect the face of the target object in the reference image data according to one or more face detection algorithms described elsewhere in this application. The processing device 120 can obtain feature information of the target object's face according to one or more feature acquisition algorithms. Exemplary feature acquisition algorithms may include principal component analysis (PCA), linear discriminant analysis (LDA), independent component analysis (ICA), multidimensional scaling (MDS) algorithm, discrete cosine transform (DCT) algorithm, etc., or any combination thereof. The processing device 120 can further obtain feature information of each of one or more candidate objects from the image data. Retrieving feature information for each candidate object from image data can be done in a manner similar to retrieving reference feature information from reference image data.

[0155] Then, the processing device 120 can identify the target object based on the reference feature information of the target object and the feature information of each of one or more candidate objects. For example, for each candidate object, the processing device 120 can determine the similarity between the target object and the candidate object based on the reference feature information of the target object and the feature information of the candidate object. The processing device 120 can also further select the candidate object with the highest similarity to the target object as the target object.

[0156] The similarity between a target object and a candidate object can be determined using various methods. As an example only, processing device 120 can determine a first feature vector (also called a first feature vector corresponding to the target object) representing reference feature information of the target object. Processing device 120 can determine a second feature vector (also called a second feature vector corresponding to the candidate object) representing feature information of the candidate object. Processing device 120 can determine the similarity between the target object and the candidate object by determining the similarity between the first and second feature vectors. The similarity between two feature vectors can be determined based on similarity algorithms, such as Euclidean distance, Manhattan distance, Minkowski distance, cosine similarity, Jacquard similarity, Pearson correlation, etc., or any combination thereof.

[0157] In some embodiments, the processing device 120 can identify the target object from one or more candidate objects based on the target object's reference identity information and the identity information of each of the candidate objects. For example, for each candidate object, the processing device 120 can determine the candidate object's identity information based on image data. In some embodiments, the processing device 120 can segment the face of each candidate object from the image data according to one or more face detection algorithms and / or one or more image segmentation algorithms, such as those described elsewhere in this application.

[0158] For each candidate object, the processing device 120 can determine the candidate object's identity information based on a database of candidate object faces and identity information. Exemplary identity information databases may include public safety databases, medical insurance databases, social insurance databases, etc. The identity information database can store at least two faces of at least two objects (humans) and their respective identity information. For example, the processing device 120 can determine the similarity between a candidate object's face and each face stored in the identity information database, and select the target face with the highest similarity to the identified candidate object's face. In some embodiments, the similarity between a candidate object's face and faces stored in the identity information database can be determined based on the similarity between the feature vector representing the candidate object's face and the feature vector representing the face stored in the identity information database. The processing device 120 can determine the identity information corresponding to the selected target face as the candidate object's identity information. By comparing the identity information of each candidate object with the reference identity information of the target object, the processing device 120 can further identify the target object from at least one candidate object. For example, the processing device 120 can compare the ID number of each candidate object with the reference ID number of the target object. The processing device 120 can identify a candidate object with the same ID number as the reference ID number as the target object.

[0159] In some embodiments, the processing device 120 can identify a target object from one or more candidate objects based on a combination of reference image data and reference identity information of the target object. For example, the processing device 120 can determine a first target object from at least one candidate object based on reference image data of the target object and image data of one or more candidate objects. The processing device 120 can determine a second target object from one or more candidate objects based on reference identity information of the target object and identity information of one or more candidate objects. The processing device 120 can determine whether the first target object and the second target object are the same. If the first target object and the second target object are the same, the processing device 120 can determine the first target object (or the second target object) as the final target object. In this case, the accuracy of target object identification can be improved.

[0160] If the first target object is different from the second target object, the processing device 120 can re-identify the first and second target objects and / or generate an alert regarding the identification result. This alert can be in the form of text, voice, image, video, tactile alarm, etc., or any combination thereof. For example, the processing device 120 can send the alert to the terminal device (e.g., terminal device 140) of the user (e.g., a doctor) of the imaging system 100. The terminal device can output the alert to the user. Optionally, the user can respond to the alert by inputting a command or sounding an alert. As an example only, the user can manually select a final target object from the first and second target objects. For example, the processing device 120 can cause the terminal device to display information about the first and second target objects (e.g., image data, identity information). The user can select the final target object from the first and second target objects based on the information about them.

[0161] In some embodiments, the processing device 120 can identify a target object from one or more candidate objects based on one or more reference features of the target object and image data of one or more candidate objects. For example, the processing device 120 can detect each candidate object in the image data and further obtain one or more features of the candidate object. By comparing one or more features of each candidate object with one or more reference features of the target object, the processing device 120 can identify the target object from one or more candidate objects. As an example only, the processing device 120 can select the candidate object with the most similar body shape to the target object as the target object.

[0162] Based on image data of candidate objects and reference information of the target object, the target object can be automatically identified from the candidate objects. Compared with traditional imaging procedures, in which users (e.g., doctors or nurses) need to identify the target object and check its identity by, for example, looking up the contour information of the target object (e.g., visually examining the contour image of the candidate object relative to the target object), the target object identification method disclosed in this application can eliminate the need for subjective judgment and is more efficient and accurate.

[0163] In some embodiments, after acquiring image data of one or more candidate objects, the processing device 120 can cause the user's terminal device (e.g., terminal device 140) to display the image data. The processing device 120 can obtain input associated with the target object from the user through the terminal device. The processing device 120 can identify the target object from one or more candidate objects based on this input. For example, the terminal device can display image data, and the user can select (e.g., by clicking the corresponding icon) a specific candidate object from the displayed image via an input component of the terminal device (e.g., a mouse, a touchscreen). The processing device 120 can then determine the selected candidate object as the target object.

[0164] In some embodiments, after the target object (or final target object) has been determined, the processing device 120 may perform one or more other operations to prepare for scanning the target object. For example, the processing device 120 may generate a target pose model of the target object. As another example, the processing device 120 may move the moving components of a medical imaging apparatus (e.g., the scanning stage) to their respective target positions. As yet another example, the processing device 120 may determine the values ​​of scanning parameters (e.g., light field) corresponding to the target object. Further descriptions of scan preparation can be found elsewhere in this application, see, for example... Figure 6 And its related descriptions.

[0165] Compared to conventional methods where users need to manually identify target objects and / or check their identity, the automatic target object identification system and method disclosed in this application are more accurate and efficient by reducing user workload, cross-user variations, and the time required for target object identification.

[0166] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the description of this application. However, such changes and modifications will not depart from the scope of this application. In some embodiments, one or more operations may be added or omitted. For example, a process for preprocessing (e.g., denoising) image data in at least one candidate object may be added before operation 830. In some embodiments, two or more operations may be performed simultaneously. For example, operations 810 and 820 may be performed simultaneously. As another example, operation 820 may be performed before operation 810.

[0167] Figure 9 This is a flowchart illustrating an exemplary process for generating a target pose model of a target object according to some embodiments of this application. In some embodiments, process 900 can be performed in... Figure 1 This is implemented in the imaging system 100 shown. For example, process 900 can be stored as instructions in a storage device (e.g., storage device 130, storage device 220, storage device 390) and processed by a processing device 120 (e.g., such as...). Figure 2 The processor 210 of the computing device 200 shown, such as Figure 3 The CPU 340 of the mobile device 300 shown is as follows: Figure 7 (One or more modules shown) are executed. The operation of the process shown below is for illustrative purposes only. In some embodiments, process 900 may be completed using one or more additional operations, and / or without the one or more operations discussed. Additionally, as Figure 9 The order of operations of process 900 shown and described below is not intended to be restrictive.

[0168] In 910, the processing device 120 (e.g., acquisition module 710) can acquire image data of the target object (e.g., a patient) to be examined (or scanned).

[0169] Image data may include 2D images, 3D images, 4D images (e.g., time-series 3D images), and / or any associated image data of the target object (e.g., scan data, projection data). Image data may include color image data, point cloud data, depth image data, mesh data, medical image data, etc., of the target object, or any combination thereof.

[0170] In some embodiments, image data of the target object can be captured by an image capture device (e.g., image capture device 160 installed in the examination chamber). The image capture device can include any type of device capable of acquiring image data, such as a 3D camera, RGB sensor, RGB-D sensor, 3D scanner, 3D laser imaging device, or structured light scanner. In some embodiments, the image capture device can acquire image data of the target object before placing it in the scanning position. For example, image data of the target object can be captured after it enters the examination chamber and its identity is confirmed (e.g., in implementing the combination...). Figure 8 The process described is after 800.

[0171] In some embodiments, the processing device 120 may acquire image data of a target object from an image capturing device. Alternatively, the image data may be acquired by the image capturing device and stored in a storage device (e.g., storage device 130, storage device 220, memory 390, or an external source). The processing device 120 may also acquire image data from the storage device.

[0172] In 920, the processing device 120 (e.g., the analysis module 720) can generate an object model of the target object based on the image data.

[0173] As used in this paper, the object model of the target object is determined based on the image data of the target object (e.g., ...). Figure 11A The object model shown is 1100A or Figure 11B The object model 1100B shown refers to a model representing the target object whose pose is maintained during image data acquisition. The pose of the target object can reflect the position, pose, shape, size, etc. of the target object (or a part thereof).

[0174] In some embodiments, the object model may include a 2D skeleton model, a 3D skeleton model, a 3D mesh model, etc. The 2D skeleton model of the target object may include images showing one or more anatomical joints and / or bones of the target object in 2D space. The 3D skeleton model of the target object may include images showing one or more anatomical joints and / or bones of the target object in 3D space. The 3D mesh model of the target object may include at least two vertices, edges, and faces that define the 3D shape of the target object.

[0175] In some embodiments, the processing device 120 can generate an object model of the target object based on image data of the target object. For illustrative purposes, the exemplary generation process of a 3D mesh model of the target object is described below. The processing device 120 can obtain body surface data of the target object (or a portion thereof) from the image data by performing an image segmentation operation on the image data, for example, according to one or more image segmentation algorithms described elsewhere in this application. The body surface data may include at least two pixels (or voxels) corresponding to at least two physical points on the body surface of the target object. In some embodiments, the body surface data can be represented by a mask, which includes a two-dimensional matrix array, a multi-valued image, or any combination thereof. In some embodiments, the processing device 120 can process the body surface data. For example, the processing device 120 can remove at least two noise points (e.g., at least two pixels of clothing or accessories) from the body surface data. As another example, the processing device 120 can perform filtering operations, smoothing operations, boundary calculation operations, or any combination thereof on the body surface data. The processing device 120 can also generate a 3D mesh model based on the (processed) body surface data. For example, processing device 120 can generate at least two grids by combining (e.g., connecting) at least two points of body surface data.

[0176] In some embodiments, the processing device 120 may generate a 3D mesh model of the target object based on one or more mesh generation techniques, such as triangular / tetrahedral (Tri / Tet) techniques (e.g., Octree algorithm, advanced Front algorithm, Delaunay algorithm, etc.), quadrilateral / hexahedral (Quad / Hex) techniques (e.g., ultrafinite interpolation (TFI) algorithm, elliptic algorithm, etc.), hybrid techniques, parametric model-based techniques, surface meshing techniques, etc., or any combination thereof.

[0177] In some embodiments, one or more feature points can be identified from the object model. For example, a feature point may correspond to a specific physical point of the target object, such as an anatomical joint (e.g., shoulder joint, knee joint, elbow joint, ankle joint, wrist joint) or a representative physical point of a body region of the target object (e.g., head, neck, hand, leg, foot, spine, pelvis, hip).

[0178] In some embodiments, one or more feature points may be manually annotated by a user (e.g., a doctor, imaging expert, technician) on an interface displaying image data (e.g., implemented on terminal device 140). Alternatively, one or more feature points may be automatically generated by a computing device (e.g., processing device 120) based on an image analysis algorithm (e.g., an image segmentation algorithm, a feature point acquisition algorithm). Alternatively, one or more feature points may be automatically generated by the computing device based on an image analysis algorithm combined with information provided by the user. Exemplary information provided by the user may include parameters related to the image analysis algorithm, positional parameters related to the feature points, adjustments to the initial feature points generated by the computing device, rejection or acceptance, etc.

[0179] In some embodiments, the object model can be represented by one or more model parameters, such as one or more contour parameters and / or one or more pose parameters of the object model or the target object represented by the object model. For example, one or more contour parameters can be a quantitative expression describing the contour of the object model (or target object). Exemplary contour parameters may include the shape and / or dimensions (e.g., height, thickness) of the object model or a portion thereof. One or more pose parameters can be a quantitative expression describing the pose of the object model (or target object). Exemplary pose parameters may include the position of feature points of a reference pose model (e.g., the coordinates of a joint in a coordinate system), the relative position between two feature points of the reference pose model (e.g., the joint angle of a joint), etc.

[0180] At 930, the processing device 120 (e.g., acquisition module 710) can acquire a reference pose model associated with the target object.

[0181] As used herein, a reference pose model refers to a model representing a reference object that maintains a reference pose. The reference object can be a real person or a phantom. The reference pose model can include a 2D skeleton model, a 3D skeleton model, a 3D mesh model, etc., of the reference object. In some embodiments, the reference pose model can be represented by one or more model parameters, such as one or more reference contour parameters and / or one or more reference pose parameters of the reference pose model or the reference object it represents. One or more reference contour parameters can be quantitative expressions describing the contour of the reference pose model or the reference object. One or more reference pose parameters can be quantitative expressions describing the pose of the reference pose model or the reference object. Exemplary reference contour parameters can include the shape and / or size (e.g., height, width, thickness) of the reference pose model or a portion thereof. Exemplary reference pose parameters can include the position of reference feature points of the reference pose model (e.g., coordinates of a joint in a coordinate system), the relative position between two reference feature points of the reference pose model (e.g., joint angles), etc.

[0182] In some embodiments, the reference pose model and the object model can be of the same type or different types. For example, the reference pose model and the object model can be 3D mesh models. As another example, the object model can be represented by at least two model parameters (e.g., one or more contour parameters and one or more pose parameters), while the reference pose model can be a 3D mesh model. The reference pose can be the reference pose that the target object needs to maintain during a scan of the target object. Exemplary reference poses may include a head-first supine posture, a feet-first prone posture, a head-first leftlateral recumbent posture, or a feet-first right lateral recumbent posture, etc.

[0183] In some embodiments, the processing device 120 may acquire a reference pose model associated with the target object based on an imaging protocol for the target object. The imaging protocol may include, for example, values ​​or ranges of one or more scanning parameters (e.g., X-ray tube voltage and / or current, X-ray tube angle, scanning mode, stage movement speed, gantry rotation speed, field of view (FOV)), source-image distance (SID), the area of ​​the target object to be imaged, characteristic information of the target object (e.g., gender, body shape), etc., or any combination thereof. The imaging protocol (or a portion thereof) may be manually determined by a user (e.g., a physician) or determined by one or more components of the imaging system 100 (e.g., the processing device 120) depending on the circumstances.

[0184] For example, the imaging protocol can define the area of ​​the target object to be imaged, and the processing device 120 can acquire a reference pose model corresponding to the area of ​​the target object to be imaged. As an example only, if imaging of the chest of the target object is required, a first reference pose model corresponding to a chest examination can be acquired. The first reference pose model can represent a reference object standing on the floor with its hands on its waist. As another example, if imaging of the vertebrae of the target object is required, a second reference pose model corresponding to a vertebral examination can be acquired. The second reference pose model can represent a reference object lying on a scanning table with its legs and arms extended on the scanning table.

[0185] In some embodiments, a pose model library having at least two pose models can be pre-generated and stored in a storage device (e.g., storage device 130, storage device 220, and / or memory 390, external source). In some embodiments, the pose model library can be updated from time to time, e.g., periodically or irregularly, based on data of a reference object, the data of which differs at least partially from the original data used to generate the original pose model library. The data of the reference object may include the imaged part of the reference object, one or more features of the reference object (e.g., gender, body shape), etc. In some embodiments, the at least two pose models may include pose models corresponding to different examination areas of the human body. For example, for each examination area (e.g., chest, vertebrae, elbow), there may be a set of pose models, wherein each pose model in the set may represent a reference object with specific features (e.g., having a specific gender and / or a specific body shape) and maintain a reference pose corresponding to the examination area. As an example only, for the human chest, the corresponding pose model set may include pose models representing at least two reference objects that maintain a standard chest examination pose and have different body shapes (e.g., height and / or weight).

[0186] The pose model (or a portion thereof) may be pre-generated by the computing device (e.g., processing device 120) of the imaging system 100. Alternatively or additionally, the pose model (or a portion thereof) may be generated and provided by a vendor's system that provides and / or maintains the pose model, wherein the vendor's system is different from the imaging system 100. The processing device 120 may generate or retrieve the pose model directly or via a network (e.g., network 150) from the computing device and / or a storage device storing the pose model.

[0187] The processing device 120 can also select a reference pose model from a pose model library based on the area to be imaged and one or more features of the target object (e.g., gender, body shape, etc.). For example, the processing device 120 can acquire a set of pose models corresponding to the area of ​​the target object to be imaged, and select one from the set of pose models as a reference pose model. The selected pose model can represent a reference object with the same or similar features as the target object. As an example only, if the area to be imaged is the chest and the target object is female, the processing device 120 can acquire a set of pose models corresponding to chest examination and select the pose model representing a female reference object as the reference pose model for the target object. By pre-generating pose models, the process of generating reference pose models can be simplified, thereby improving the efficiency of generating target pose models for the target object.

[0188] In some embodiments, a reference pose model of a reference object can be annotated with one or more reference feature points. Similar to feature points in an object model, reference feature points can correspond to specific anatomical points (e.g., joints) of the reference object. Identifying reference feature points from the reference pose model can be performed in a manner similar to that described in combination operation 920 for identifying feature points from an object model, and will not be repeated here.

[0189] In 940, processing device 120 (e.g., analysis module 720) can generate a target pose model of the target object based on the object model and the reference pose model. As used herein, the target pose model of the target object refers to a model representing the target object maintaining the reference pose.

[0190] In some embodiments, the processing device 120 can generate a target pose model of a target object by transforming an object model based on a reference pose model. For example, the processing device 120 can acquire reference pose parameters of one or more reference pose models. One or more reference pose parameters can be pre-generated by a computing device and stored in a storage device such as the storage device of the imaging system 100 (e.g., storage device 130). Alternatively, one or more reference pose parameters can be determined by the processing device 120 by analyzing the reference pose model.

[0191] The processing device 120 can further transform the object model based on one or more reference pose parameters to generate a target pose model of the target object. In some embodiments, the processing device 120 can perform one or more image processing operations (e.g., rotation, translation, deformation) on one or more parts of the object model based on one or more reference pose parameters to generate a target pose model. For example, the processing device 120 can rotate the part of the object model representing the right wrist of the target object so that the joint angle of the right wrist of the target object in the transformed object model is equal to or substantially equal to the right wrist joint angle of the reference pose model. As another example, the processing device 120 can translate the first part representing the left ankle of the target object and / or the second part representing the right ankle of the target object so that the distance between the first part and the second part in the transformed object model is equal to or substantially equal to the distance between the left ankle and the right ankle of the reference pose model.

[0192] In some embodiments, the processing device 120 can generate a target pose model of a target object by transforming a reference pose model based on an object model. For example, the processing device 120 can acquire one or more contour parameters of the object model. One or more contour parameters can be pre-generated by a computing device and stored in a storage device such as the imaging system 100 (e.g., storage device 130). Alternatively, the processing device 120 can determine one or more contour parameters by analyzing the object model.

[0193] The processing device 120 can further transform the reference pose model based on one or more contour parameters of the object model to generate a target pose model of the target object. In some embodiments, the processing device 120 can perform one or more image processing operations (e.g., rotation, translation, deformation) on one or more portions of the reference pose model based on one or more contour parameters to generate the target pose model. For example, the processing device 120 can stretch or shrink the reference pose model so that the height of the transformed reference pose model is equal to or substantially equal to the height of the object model.

[0194] In some embodiments, the processing device 120 may use an object model and / or a target pose model in one or more other scan preparation operations. For example, the processing device 120 may use the object model to move the moving components of a medical imaging apparatus (e.g., a scanning stage) to their respective target positions. In some embodiments, the target pose model may be used to assist in positioning a target object. For example, the target pose model or a synthetic image generated based on the target pose model may be displayed to the target object to guide the target object in adjusting his / her pose. As another example, after positioning the target object in the scanning position, the processing device 120 may use the target pose model to determine whether the target object's pose needs adjustment. Compared to conventional positioning methods that require a user (e.g., a physician) to examine the target object's pose and / or instruct the target object to adjust its pose, the target object positioning techniques disclosed herein can be implemented without user intervention, or with reduced or minimized user intervention, and are time-saving, efficient, and accurate. Further descriptions of the use of object models and / or target pose models can be found elsewhere in this application. See, for example... Figures 16A to 17 And its related descriptions.

[0195] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the description of this application. However, such changes and modifications will not depart from the scope of this application. In some embodiments, one or more operations may be added or omitted. For example, an operation to preprocess the image data of the target object (e.g., denoising) may be added before operation 920. In some embodiments, two or more operations may be performed simultaneously. For example, operations 920 and 930 may be performed simultaneously. As another example, operation 930 may be performed before operation 920.

[0196] Figure 10 This is a flowchart illustrating an exemplary process for scan preparation according to some embodiments of this application. In some embodiments, process 1000 may be performed... Figure 1This is implemented in the imaging system 100 shown. For example, process 1000 may be stored as instructions in a storage device (e.g., storage device 130, storage device 220, memory 390) and processed by a processing device 120 (e.g., such as...). Figure 2 The processor 210 of the computing device 200 shown, such as Figure 3 The CPU 340 of the mobile device 300 shown is as follows: Figure 7 The process 1000 is executed by one or more modules shown. The operation of the process shown below is for illustrative purposes only. In some embodiments, process 1000 may be accomplished using one or more additional operations not described, and / or without one or more operations discussed. Additionally, as Figure 10 The order of operations of process 1000 shown and described below is not intended to be restrictive.

[0197] In 1010, the processing device 120 (e.g., acquisition module 710) can acquire image data of the target object.

[0198] It can be combined with Figure 9 Operation 910 is performed in a similar manner to operation 1010, and its description will not be repeated here.

[0199] In 1020, for one or more active components of a medical imaging apparatus, processing device 120 (e.g., analysis module 720) can determine the target position of each of the one or more active components of the medical imaging apparatus based on image data.

[0200] Medical imaging apparatus can be used to scan a target object. In some embodiments, the medical imaging apparatus (e.g., medical imaging apparatus 110) can be an X-ray imaging device (e.g., a suspended X-ray imaging device, a C-arm X-ray imaging device), a digital radiography (DR) device (e.g., a mobile digital X-ray imaging device), a CT device, a PET device, an MRI device, etc. By way of example only, for an X-ray imaging device, one or more active components of the X-ray imaging device may include a scanning stage (e.g., scanning stage 114), a detector (e.g., detector 112, flat panel detector 440), an X-ray source (e.g., radiation source 115, X-ray source 420), etc. The target position of the active component refers to the estimated position where the active component needs to be located during the scanning of the target object, based on, for example, the pose of the target object and / or the imaging protocol of the target object.

[0201] In some embodiments, the processing device 120 can determine the target position of an active component (e.g., a scanning stage) based on image data by determining the height of a target object. For example, the processing device 120 can identify a representation of the target object in the image data and determine a reference height for the representation of the target object in the image domain. For illustrative purposes only, a first point located at the feet of the target object and a second point located above the head of the target object can be identified in the image data. The pixel distance (or voxel distance) between the first and second points can be determined as the reference height for the representation of the target object in the image domain. The processing device 120 can then determine the height of the target object in the physical world based on the reference height and one or more parameters (e.g., internal parameters, external parameters) of the image capturing device that captured the image data.

[0202] The processing device 120 can also determine the target position (e.g., height) of the active component based on the height of the target object. For example, the processing device 120 can determine the height of the scanning stage to be 1 / 3, 1 / 2, etc., of the height of the target object. The height of the scanning stage can be expressed, for example, as the surface of the scanning stage on which the target object lies. Figure 4A The Z-axis coordinate in the coordinate system 470 is shown. This allows the scanning stage height to be automatically determined and adjusted based on the target object's height, facilitating the object's movement on and off the stage. After the target object is on the scanning stage, the stage can be moved further to a second target position to prepare for imaging (or treatment) of the target object.

[0203] Additionally or alternatively, the processing device 120 may generate an object model based on the image data of the target object (or as... Figure 9 The target pose model described in [the document] is used to determine the target position of the active component. Further description of the generated object model (or target pose model) can be found elsewhere in this application (e.g., [other documents]). Figure 9 (and its description). The processing device 120 can determine a target region in an object model, wherein the target region may correspond to the ROI of the target object. The ROI may contain one or more body parts (e.g., tissues, organs) of the target object that need to be imaged by the medical imaging device. The processing device 120 can also determine the target location of active components based on the target region.

[0204] For illustrative purposes, the example described is determining the target location of a detector (e.g., a flat panel detector) in a medical imaging apparatus based on a target region. In some embodiments, processing device 120 can determine the target location of the detector based on the target region, where the detector at the target location can cover the entire ROI of the target object when the target object is in the scanning position. In this case, the detector can receive an X-ray beam emitted by an X-ray tube that effectively passes through the ROI of the target object. In some embodiments, if the detector cannot cover the entire ROI of the target object (e.g., the area of ​​the ROI is larger than the area of ​​the detector), processing device 120 can determine the center of the ROI as the target location of the detector based on the target region. Alternatively, processing device 120 can determine at least two target locations of the detector based on the target region, at each target location where the detector can cover a specific portion of the ROI. Processing device 120 can move the detector to each of the at least two target locations to acquire an image corresponding to a specific portion of the ROI of the target object. Processing device 120 can further generate an image of the ROI of the target object by combining at least two images corresponding to different portions of the ROI.

[0205] In some embodiments, a target region corresponding to a ROI of a target object can be determined from an object model using various methods. For example, processing device 120 can identify one or more feature points corresponding to the ROI of a target object from the object model. The feature point corresponding to the ROI may include pixels or voxels in the object model that represent the ROI. Different ROIs of the target object may have their corresponding representative physical points or anatomical points. As an example only, one or more representative physical points corresponding to the chest of the target object may include the ninth thoracic vertebra (i.e., spine T9), the eleventh thoracic vertebra (i.e., spine T11), and the third lumbar vertebra (i.e., spine L3). One or more representative physical points corresponding to the right leg of the target object may include the right knee. Taking the chest of the target object as an example ROI, such as Figure 11A As shown, feature point 3 corresponding to spine T9, feature point 4 corresponding to spine T11, and feature point 5 corresponding to spine L3 can be identified from the object model. The processing device 120 can also determine a target region of the object model based on one or more identified feature points. For example, the processing device 120 can determine the region in the object model that surrounds one or more identified feature points as the target region. Further description of determining a target region based on one or more identified feature points can be found elsewhere in this application (e.g., Figure 11A (and its description).

[0206] For example, processing device 120 can divide the object model into at least two regions (e.g., such as...). Figure 11B(As shown in regions 1, 2, ... and 10). The processing device 120 can select a target region corresponding to the ROI of the target object from at least two regions. Further description of determining the target region based on at least two regions can be found elsewhere in this application (e.g., Figure 11B (and its description).

[0207] In some embodiments, the processing device 120 may further determine the target position of the X-ray tube based on the target position of the detector and the imaging protocol of the target object. The X-ray tube can generate a radiation beam (e.g., an X-ray beam) and emit it toward the target object. For example, the processing device 120 may determine the target position of the X-ray tube based on the target position of the detector and the source-image distance (SID) defined in the imaging protocol. The target position of the X-ray tube may include, for example, Figure 4A The coordinates of the X-ray tube in the coordinate system 470 shown are (e.g., X-axis, Y-axis, and / or Z-axis), and / or the angles of the X-ray tube (e.g., the tilt angle of the X-ray tube anode target). As used herein, SID refers to the distance between the focal target of the X-ray tube and the beam of radiation generated and emitted along the X-ray tube to the image receiver (e.g., the X-ray detector). In some embodiments, SID may be manually set by a user of the imaging system 100 (e.g., a physician), or determined by one or more components of the imaging system 100 (e.g., processing device 120) depending on the circumstances. For example, a user may manually input information about SID (e.g., the value of SID) via a terminal device. A medical imaging apparatus (e.g., medical imaging apparatus 110) may receive information about SID and set the value of SID based on the information input by the user. As another example, a user may manually set SID by controlling the movement of one or more components of the medical imaging apparatus (e.g., the radiation source and / or detector).

[0208] Additionally or alternatively, the processing apparatus 120 may determine the target position of the collimator based on the target position of the X-ray tube and one or more parameters related to the optical field (e.g., the target size of the optical field). Further description of the determination of the optical field parameters and the determination of the target position of the collimator can be found elsewhere in this application (e.g., Figure 12 (and its description).

[0209] It should be noted that the above description of determining the target position of an active component based on image data is for illustrative purposes only and is not intended to limit the scope of this application. For example, the height of a target object can be determined based on an object model rather than the original image data, and the target position of the scanning stage can be further determined based on the height of the target object. As another example, the target position of a detector can be determined based on the original image data without generating an object model. As an example only, feature points corresponding to the ROI of the target object can be identified from the original image data, and the target position of the detector can be determined based on the feature points identified from the original image data.

[0210] In 1030, for each of one or more active components of a medical imaging device, processing device 120 (e.g., control module 730) can move the active component to its target position.

[0211] In some embodiments, the processing device 120 may send instructions to the active component or a drive device capable of moving the active component to move the active component to its target position. The instructions may include various parameters related to the movement of the active component. Exemplary parameters related to the movement of the active component may include movement distance, movement direction, movement speed, etc., or any combination thereof.

[0212] Compared to conventional methods where users need to manually determine and / or inspect the location of active components of a medical imaging device, the automated system and method for determining the target location of active components disclosed in this application can improve accuracy and efficiency by reducing user workload, cross-user variations, and the time required for system setup.

[0213] In 1040, when each of one or more active components of the medical imaging apparatus is at its respective target location, the processing device 120 (e.g., control module 730) can cause the medical imaging apparatus to scan the target object.

[0214] In some embodiments, prior to operation 1040, the target position of the active component determined in operation 1030 may be further checked and / or adjusted. For example, the target position of the active component may be manually checked and / or adjusted by a user of the imaging system 100. As yet another example, after the target object is located in the scanning position, target image data of the target object may be captured using an image capturing device. One or more components of the imaging system 100 (e.g., processing device 120) may automatically check and / or adjust the target position of the active component (e.g., detector) based on the target image data. For example, based on the target image data, processing device 120 may select at least one target ionization chamber from at least two ionization chambers in a medical imaging apparatus. Processing device 120 may also determine whether the target position of the detector needs to be adjusted based on the position of the selected at least one target ionization chamber. Further description of the selection of at least one target ionization chamber can be found elsewhere in this application. Refer to, for example Figures 16A to 16C And its related descriptions.

[0215] In some embodiments, medical image data of the target object can be acquired during the scanning process. The processing device 120 can perform one or more additional operations to process the medical image data. For example, the processing device 120 can determine the orientation of the target object based on the medical image data and display the medical image data according to the orientation of the target object. Further description regarding the determination of the orientation of the target object can be found elsewhere in this application. See, for example... Figures 13 to 14 And its related descriptions.

[0216] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the description of this application. However, such changes and modifications will not depart from the scope of this application. In some embodiments, one or more operations may be added or omitted. For example, an operation of preprocessing (e.g., denoising) the image data of the target object may be added before operation 1020.

[0217] Figure 11A This is a schematic diagram of an exemplary patient model 1100A according to some embodiments of this application. Patient model 1100A may be an exemplary patient model described elsewhere in this application (e.g., Figure 9 (and related descriptions).

[0218] like Figure 11AAs shown, at least two feature points can be identified from the patient model. Each feature point can correspond to a physical point of the patient's ROI (e.g., an anatomical joint). For example, feature point 1 can correspond to the patient's head. Feature point 2 can correspond to the patient's neck. Feature point 3 can correspond to the patient's T9 spine. Feature point 4 can correspond to the patient's T11 spine. Feature point 5 can correspond to the patient's L3 spine. Feature point 6 can correspond to the patient's pelvis. Feature point 7 can correspond to the patient's right jaw. Feature point 8 can correspond to the patient's left jaw. Feature point 9 can correspond to the patient's right shoulder. Feature point 10 can correspond to the patient's left shoulder. Feature point 11 can correspond to the patient's right elbow. Feature point 12 can correspond to the patient's left elbow. Feature point 13 can correspond to the patient's right wrist. Feature point 14 can correspond to the patient's left wrist. Feature point 15 can correspond to the patient's right hand. Feature point 16 can correspond to the patient's left hand. Feature point 17 can correspond to the patient's right hip. Feature point 18 can correspond to the patient's left hip. Feature point 19 can correspond to the patient's right knee. Feature point 20 can correspond to the patient's left knee. Feature point 21 can correspond to the patient's right ankle. Feature point 22 can correspond to the patient's left ankle. Feature point 23 can correspond to the patient's right foot. Feature point 24 can correspond to the patient's left foot.

[0219] In some embodiments, a target region corresponding to a specific ROI of a patient in a patient model 1100A can be determined based on one or more feature points corresponding to the ROI. For example, feature points 2, 3, 4, 5, and 6 may all correspond to the patient's spine. Target region 1 corresponding to the patient's spine can be determined by identifying feature points 2, 3, 4, 5, and 6 in the patient model 1100A, wherein target region 1 may surround feature points 2, 3, 4, 5, and 6. As another example, feature points 3, 4, and 5 may all correspond to the patient's chest. Target region 2 corresponding to the patient's chest can be determined by identifying feature points 3, 4, and 5 in the patient model 1100A, wherein target region 2 may surround feature points 3, 4, and 5. As yet another example, feature point 19 may correspond to the patient's right knee. Target region 3 corresponding to the patient's right knee can be determined by identifying feature point 19 in the patient model 1100A, wherein target region 3 may surround feature point 19.

[0220] Figure 11B This is a schematic diagram of an exemplary patient model 1100B of a patient according to some embodiments of this application.

[0221] like Figure 11B As shown, at least two regions (e.g., region 1, region 2, region 3, region 4, ... and region 10) can be segmented from the patient model 1100B. Target regions corresponding to specific ROIs can be identified in the patient model 1100B based on these at least two regions. For example, as... Figure 11B As shown, the areas covered by regions 1, 2, 3, and 4 can be identified as target region 4 corresponding to the patient's chest. Similarly, the area covered by region 10 can be identified as target region 5 corresponding to the patient's right knee.

[0222] In some embodiments, a patient's region of interest (ROI) can be scanned using a medical imaging device (e.g., medical imaging device 110). The target location of an active component (e.g., a detector) of the medical imaging device can be determined based on a target region corresponding to the ROI. Further description of determining the location of an active component based on a target region can be found elsewhere in this application. See, for example, operation 1020 and its related description.

[0223] Figure 12 This is a flowchart illustrating an exemplary process for controlling the optical field of a medical imaging apparatus according to some embodiments of this application. In some embodiments, process 1200 may be performed in... Figure 1 This is implemented in the imaging system 100 shown. For example, process 1200 can be stored as instructions in a storage device (e.g., storage device 130, storage device 220, storage device 390) and processed by a processing device 120 (e.g., such as...). Figure 2 The processor 210 of the computing device 200 shown, such as Figure 3 The CPU 340 of the mobile device 300 shown is as follows: Figure 7 (One or more modules shown) are executed. The operation of the process shown below is for illustrative purposes only. In some embodiments, process 1200 may be accomplished using one or more additional operations not described, and / or without one or more operations discussed. Additionally, as Figure 12 The order of operations of process 1200 shown and described below is not intended to be restrictive.

[0224] In 1210, the processing device 120 (e.g., acquisition module 710) can acquire image data of the target object to be scanned (or examined or treated) by the medical imaging device. The image data can be captured by an image capture device.

[0225] It can be combined with Figure 9 Operation 910 is performed in a similar manner to operation 1210, and its description will not be repeated here.

[0226] In 1220, the processing device 120 (e.g., analysis module 720) can determine one or more parameter values ​​of the light field based on the image data.

[0227] As used herein, a light field refers to the area on a target object irradiated by rays (e.g., an X-ray beam) emitted from a radiation source (e.g., an X-ray source) of a medical imaging apparatus. One or more parameter values ​​of the light field may be associated with one or more parameters of the light field, such as the size, shape, location, etc., or any combination thereof. In some embodiments, a beam-limiting device (e.g., a collimator) may be placed between the radiation source and the target object and configured to control one or more parameters related to the light field. For illustrative purposes, the following description is described with reference to values ​​used to determine the size of the light field (or target size). This is not intended to be limiting, and the systems and methods disclosed in this application can be used to determine one or more other parameters related to the light field.

[0228] In some embodiments, the processing device 120 may determine the target size of the optical field based on feature information related to the ROI of the target object. The feature information related to the ROI of the target object may include the location, height, width, thickness, etc., of the ROI. As used herein, the width of the ROI refers to the length of the ROI along a direction perpendicular to the sagittal plane of the target object (e.g., the length of the center of the ROI, the maximum length of the ROI). The height of the ROI refers to the length of the ROI along a direction perpendicular to the cross-section of the target object (e.g., the length of the center of the ROI, the maximum length of the ROI).

[0229] In some embodiments, processing device 120 can determine feature information related to the ROI of a target object by identifying a target region in image data or an object model (or target pose model) of the target object generated based on the image data. For example, processing device 120 can generate an object model based on image data of the target object and identify the target region from the object model. Further description of identifying the target region from image data or object model (or target pose model) can be found elsewhere in this application (e.g., operation 1020 and its description). Processing device 120 can also determine feature information (e.g., width and height) of the ROI based on the target region and one or more parameters (e.g., intrinsic parameters, extrinsic parameters) of the image capturing device that captured the image data.

[0230] Alternatively or concurrently, the processing device 120 may determine the characteristic information of the ROI of the target object based on anatomical information of a human. Anatomical information may include the location information of one or more ROIs within the human body, the size information of one or more ROIs, the shape information of one or more ROIs, or any combination thereof. In some embodiments, anatomical information may be obtained from at least two samples (e.g., images) displaying ROIs of different individuals. For example, the size information of the ROI may be associated with the average size of the same ROI in at least two samples. Specifically, the at least two samples may be other individuals with similar characteristics to the patient (e.g., similar height or weight). In some embodiments, the anatomical information of the human may be stored in a storage device (e.g., storage device 130, storage device 220, memory 390, or an external source).

[0231] After determining the feature information of the ROI, the processing device 120 can further determine the target size of the light field based on the feature information of the ROI of the target object. When scanning the target object, the light field with the target size can cover the entire ROI of the object model. For example, the width of the light field can be greater than or equal to the width of the ROI, and the height of the light field can be greater than or equal to the height of the ROI.

[0232] In some embodiments, the processing device 120 can determine the target size of the light field (also referred to as the first relationship) based on the relationship between the feature information of the ROI and the light field size. As an example only, the target size can be determined based on the first relationship between the height (and / or width) of the ROI and the light field size. A larger height (and / or a larger width) may correspond to a larger light field size value. The first relationship between the height (and / or width) of the ROI and the size can be represented in the form of a table or curve, which records different heights (and / or widths) of the ROI and their corresponding size values, mathematical functions, etc. In some embodiments, the first relationship between the height (and / or width) of the ROI and the size can be stored in a storage device (e.g., storage device 130, storage device 220, memory 390, or an external source). The processing device 120 can retrieve the first relationship from the storage device and determine the target size of the light field based on the retrieved first relationship and the height (and / or width) of the ROI.

[0233] Alternatively or concurrently, the processing device 120 may use an optical field determination model to determine the target size of the optical field. As used herein, an optical field determination model refers to a model (neural network) or algorithm configured to receive input and output the target size of the optical field of a medical imaging device based on that input. For example, image data acquired in operation 1210 and / or feature information of the ROI determined based on the image data may be input into the optical field determination model, which may output the target size of the optical field.

[0234] In some embodiments, the optical field determination model can be obtained from one or more components of the imaging system 100 or an external source via a network (e.g., network 150). For example, the optical field determination model can be pre-trained by a computing device (e.g., processing device 120 or a processing device of the seller of the optical field determination model) and stored in a storage device (e.g., storage device 130, storage device 220, memory 390, or an external source). Processing device 120 can access the storage device and obtain the optical field determination model. In some embodiments, the optical field determination model can be trained according to a machine learning algorithm, such as artificial neural network algorithms, deep learning algorithms, decision tree algorithms, association rule algorithms, inductive logic programming algorithms, support vector machine algorithms, clustering algorithms, Bayesian network algorithms, reinforcement learning algorithms, representation learning algorithms, similarity and metric learning algorithms, sparse dictionary learning algorithms, genetic algorithms, rule-based machine learning algorithms, etc., or any combination thereof. The machine learning algorithm used to generate the optical field determination model can be a supervised learning algorithm, a semi-supervised learning algorithm, an unsupervised learning algorithm, etc.

[0235] In some embodiments, the light field determination model can be trained based on at least two training samples. Each training sample may include sample image data of a sample object and / or sample feature information of a sample ROI of the sample object (e.g., the height and / or width of the sample ROI of the sample object) and the sample size of the sample light field. As used herein, sample image data of a sample object refers to image data of the sample object used to train the light field determination model. For example, sample image data of a sample object may include 2D images, point cloud data, color image data, depth image data, or medical image data of the sample object. The sample size of the sample light field can be used as a basis fact and can be determined in a manner similar to determining the target size of the light field as described above, or it can be manually set by a user (e.g., a physician) based on experience. Processing device 120 or another computing device can generate the light field determination model by training an initial model using at least two training samples. For example, the initial model can be trained according to a machine learning algorithm (e.g., a supervised machine learning algorithm) as described above.

[0236] In some embodiments, if the target size of the light field cannot cover the entire ROI of the target object (e.g., the size of the ROI is larger than the target size of the light field), the processing device 120 may determine at least two light fields. Each light field may cover a specific portion of the ROI, and the total size of the at least two light fields may be equal to or greater than the size of the ROI, so that the light fields can cover the entire ROI of the target object.

[0237] In 1230, the processing device 120 (e.g., control module 730) can enable the medical imaging device to scan the target object based on one or more parameter values ​​of the light field.

[0238] In some embodiments, processing device 120 may determine one or more parameter values ​​for one or more components in a medical imaging apparatus used to generate and / or control radiation to obtain one or more parameter values ​​for an optical field. By way of example only, processing device 120 may determine the target position of a beam-limiting device (e.g., a collimator) of the medical imaging apparatus based on one or more parameter values ​​of the optical field (e.g., the target size of the optical field). In some embodiments, the collimator may include at least two blades. Processing device 120 may determine the position of each blade of the collimator based on one or more parameter values ​​of the optical field. Processing device 120 may also cause the medical imaging apparatus to adjust the components used to generate and / or control radiation according to their respective parameter values ​​and scan the target object after adjustment.

[0239] In some embodiments, after determining one or more parameter values ​​of the optical field, the processing device 120 may perform one or more additional operations to prepare for scanning the target object. For example, the processing device 120 may determine a value of the estimated dose associated with the target object based at least in part on one or more parameter values ​​of the optical field. Further description of dose estimation can be found elsewhere in this application. See, for example... Figure 15 And related descriptions. For example, after the target object is located at the scanning position, one or more parameter values ​​of the optical field determined in process 1200 can be further checked and / or adjusted.

[0240] Using the automated light field control system and method disclosed in this application, the light field can be controlled in a more accurate and efficient manner, for example, by reducing user workload, cross-user changes, and the time required for light field control.

[0241] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the description in this application. However, such changes and modifications do not depart from the scope of this application. In some embodiments, one or more operations may be added or omitted. For example, an operation to preprocess the image data of the target object (e.g., denoising) may be added before operation 1220.

[0242] Figure 13 This is a flowchart illustrating an exemplary process for determining the location of a target object according to some embodiments of this application. In some embodiments, process 1300 may be performed in... Figure 1This is implemented in the imaging system 100 shown. For example, process 1300 can be stored as instructions in a storage device (e.g., storage device 130, storage device 220, memory 390) and processed by a processing device 120 (e.g., such as...). Figure 2 The processor 210 of the computing device 200 shown, such as Figure 3 The CPU 340 of the mobile device 300 shown is as follows: Figure 7 (One or more modules shown) are executed. The operation of the process shown below is for illustrative purposes only. In some embodiments, process 1300 may be accomplished using one or more additional operations not described, and / or without one or more operations discussed. Additionally, as Figure 13 The order of operations of process 1300 shown and described below is not intended to be restrictive.

[0243] In 1310, the processing device 120 (e.g., acquisition module 710) can acquire a first image of the target object.

[0244] As used herein, the first image of the target object refers to a raw image captured using an image capture device (e.g., image capture device 160) or a medical imaging device (e.g., medical imaging device 110). For example, the first image can be captured by a camera after the target object is in the scanning position. Alternatively, the first image can be generated based on medical image data acquired by an X-ray imaging device during an X-ray scan of the target object.

[0245] In some embodiments, the processing device 120 may acquire the first image from an image capturing device or a medical imaging device. Alternatively, the first image may be acquired by an image capturing device or a medical imaging device and stored in a storage device (e.g., storage device 130, storage device 220, memory 390, or an external source). The processing device 120 may acquire the first image from the storage device.

[0246] In 1320, the processing device 120 (e.g., analysis module 720) can determine the orientation of the target object based on the first image.

[0247] As used herein, the orientation of a target object refers to the direction from the upper part (also known as the head) to the lower part (also known as the feet) or from the lower part to the upper part of the target object. Generally, the upper part of a person or part of a person (e.g., an organ) may be closer to the head, and the lower part may be closer to the feet. The upper and lower parts of a body part can be defined according to human anatomy. For example, for the hand of a target object, the fingers may correspond to the lower part of the hand, while the wrist may correspond to the upper part.

[0248] In some embodiments, the orientation of the target object may include an "upward" orientation, an "downward" orientation, a "leftward" orientation, and a "rightward" orientation, or any combination thereof. For example, the target object may be placed as follows: Figure 4A The scanning stage 410 is shown. The four edges of the scanning stage 410 can be represented as the top edge, bottom edge, left edge, and right edge. For a target object in an "upward" orientation, the upper part of the target object can be closer to the top edge of the scanning stage 410, while the lower part of the target object can be closer to the bottom edge of the scanning stage 410. In other words, the direction from the top to the bottom of the target object can be (essentially) the same as the direction from the top edge to the bottom edge of the scanning stage 410. For a target object in a "downward" orientation, the upper part of the target object can be closer to the bottom edge of the scanning stage 410, while the lower part of the target object can be closer to the top edge of the scanning stage 410. In other words, the direction from the top to the bottom of the target object can be (essentially) the same as the direction from the bottom edge to the top edge of the scanning stage 410. For a target object in a "right-facing" orientation, the upper part of the target object can be closer to the right edge of the scanning stage 410, while the lower part of the target object can be closer to the left edge of the scanning stage 410. In other words, the direction from the top to the bottom of the target object can be (essentially) the same as the direction from the right edge to the left edge of the scanning stage 410. For a target object in a "head-to-left" orientation, the top of the target object can be closer to the left edge of the scanning stage 410, while the bottom of the target object can be closer to the right edge of the scanning stage 410. In other words, the direction from the top to the bottom of the target object can be (essentially) the same as the direction from the left edge to the right edge of the scanning stage 410. The above description of the target object orientation is for illustrative purposes only and is not intended to be limiting. For example, any edge of the scanning stage 410 can be considered the top edge.

[0249] In some embodiments, each side of the first image may correspond to a reference object in the imaging system 100. For example, the upper side of the first image may correspond to the upper edge of the scanning stage, the lower side of the first image may correspond to the lower edge of the scanning stage, the left side of the first image may correspond to the left edge of the scanning stage, and the right side of the first image may correspond to the right edge of the scanning stage. The correspondence between a side of the first image and its corresponding reference object in the imaging system 100 may be manually set by a user of the imaging system 100 or determined by one or more components of the imaging system 100 (e.g., processing device 120).

[0250] In some embodiments, the processing device 120 can determine the orientation of a target region corresponding to a target object in the first image. The ROI of the target object can be the entire target object itself or a part of it. For example, the processing device 120 can identify at least two feature points corresponding to the ROI from the first image. The feature points corresponding to the ROI can include pixels or voxels in the first image corresponding to representative physical points of the ROI. Different ROIs of the target object can have their corresponding representative physical points. By way of example only, one or more representative physical points corresponding to the hand of the target object can include fingers (e.g., thumb, index finger, middle finger, ring finger, and little finger) and wrist. Fingers and wrist can correspond to the upper and lower parts of the hand, respectively. The at least two feature points can be manually identified by a user (e.g., a doctor) and / or determined by a computing device (e.g., the processing device 120) according to an image analysis algorithm (e.g., an image segmentation algorithm, a feature point acquisition algorithm).

[0251] Then, the processing device 120 can determine the orientation of the target region based on at least two feature points. For example, the processing device 120 can determine the orientation of the target region based on the relative positions between at least two feature points. The processing device 120 can further determine the orientation of the target object based on the orientation of the target region. For example, the orientation of the target region can be specified as the orientation of the target object.

[0252] Taking the determination of the hand's orientation in a first image as an example, the processing device 120 can identify a first feature point corresponding to the middle finger (as an example of the lower part of the hand) and a second feature point corresponding to the wrist (as an example of the upper part of the hand) in the first image. The processing device 120 can determine the orientation of the target area corresponding to the hand in the first image as the direction from the first feature point to the second feature point. The processing device 120 can also determine the hand's orientation based on the orientation of the target area in the first image and the correspondence between one side of the first image and its respective reference object in the imaging system 100 (also referred to as the second relationship). As an example only, if the orientation of the target area corresponding to the hand (i.e., the direction from the wrist to the middle finger) is from the upper side to the lower side of the first image, where the upper side of the first image corresponds to the upper edge of the scanning table and the lower side of the first image corresponds to the lower edge of the scanning table, then the processing device 120 can determine the hand's orientation as "head up".

[0253] In some embodiments, the processing device 120 can determine the location of a target region corresponding to the ROI of a target object in a first image, and determine the orientation of the target object based on the location of the target region. For example, the target object may be a patient, and the ROI may be the patient's head. The processing device 120 can identify the target region corresponding to the head of the target object from the first image according to an image analysis algorithm (e.g., an image segmentation algorithm). The processing device 120 can determine the location of the center of the identified target region as the location of the target region. Based on the location of the target region, the processing device 120 can further determine which side of the first image is closest to the target region in the first image. As an example only, if the target region is closest to the upper side of the first image, and the upper side of the first image corresponds to the upper edge of the scanning table, then the processing device 120 can determine that the patient's orientation is "head up".

[0254] In 1330, the processing device 120 (e.g., control module 730) can cause the terminal device (e.g., terminal device 140) to display a second image of the target object based on the orientation of the target object and the first image. The representation of the target object in the second image has a reference orientation.

[0255] As used herein, the reference orientation of a target object refers to the desired or expected direction displayed in the second image from top to bottom or from bottom to top of the target object. For example, to ensure that the second image conforms to image display conventions or the viewing habits of a user (e.g., a doctor), the reference orientation may be a "head-up" orientation. In some embodiments, the reference orientation may be manually set by the user (e.g., a doctor) or determined by one or more components of the imaging system 100 (e.g., processing device 120). For example, the reference orientation may be determined by the processing device 120 by analyzing the user's image browsing history.

[0256] In some embodiments, the processing device 120 can generate a second image of the target object based on the orientation of the target object and a first image, and send the second image to a terminal device for display. For example, the processing device 120 can determine display parameters based on the first image and the orientation of the target object. The display parameters may include the rotation angle and / or rotation direction of the first image. For example, if the target object has a "head down" orientation and the reference orientation is a "head up" orientation, the processing device 120 can determine that the first image needs to be rotated 180 degrees clockwise. The processing device 120 can generate the second image by rotating the first image 180 degrees clockwise. For illustrative purposes, the processing device 120 can rotate the first image 180 degrees clockwise and send the rotated first image (also referred to as the second image or the adjusted first image) to the terminal device for display.

[0257] In some embodiments, the processing device 120 may add at least one annotation indicating the orientation of a target object to the second image and transmit the second image with at least one annotation to a terminal device for display. For example, an annotation "R" representing the right side of the target object and / or an annotation "L" representing the left side of the target object may be added to the second image.

[0258] In some embodiments, the processing device 120 can transmit the orientation of the target object and a first image to a terminal device. The terminal device can generate a second image of the target object based on the orientation of the target object and the first image. For example, the terminal device can determine display parameters based on the orientation of the target object and the first image. The terminal device can then generate and display the second image based on the first image and the display parameters. As an example only, the terminal device can adjust (e.g., rotate) the first image based on the display parameters and display the adjusted (rotated) first image (also referred to as the second image).

[0259] In some embodiments, the processing device 120 may determine display parameters based on the orientation of the target object and the first image. The processing device 120 may send the first image and display parameters to a terminal device. The terminal device may generate a second image of the patient based on the first image and display parameters. The terminal device may further display the second image. By way of example only, the terminal device may adjust (e.g., rotate) the first image based on the display parameters and display the adjusted (rotated) first image (also referred to as the second image).

[0260] According to some embodiments of this application, the orientation of a target object can be determined based on a first image. If the orientation of the target object is inconsistent with a reference orientation, the first image can be rotated to generate a second image indicating that the target object has the reference orientation. This makes the displayed second image easier for the user to view. Furthermore, annotations indicating the orientation of the target object can be added to the second image, allowing the user to process the second image more accurately and effectively.

[0261] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the description of this application. However, such changes and modifications do not depart from the scope of this application. In some embodiments, one or more operations may be added or omitted. For example, an operation of preprocessing (e.g., denoising) a first image of the target object may be added before operation 1320.

[0262] Figure 14 These are schematic diagrams of exemplary images 1401, 1402, 1403 and 1404 of hands in different orientations as shown in some embodiments of this application.

[0263] like Figure 14 As shown, in image 1401, the direction from the wrist to the fingers is (substantially) the same as the direction from the bottom to the top of image 1401. In image 1402, the direction from the wrist to the fingers is (substantially) the same as the direction from the top to the bottom of image 1402. In image 1403, the direction from the wrist to the fingers is (substantially) the same as the direction from the right to the left of image 1403. In image 1404, the direction from the wrist to the fingers is (substantially) the same as the direction from the left to the right of image 1404.

[0264] Suppose that the top, bottom, left, and right sides of the images (e.g., images 1401, 1402, 1403, and 1404) correspond to the top, bottom, left, and right edges of the scanning stage supporting the hand, respectively. The orientation of the hand in images 1401 to 1404 can be "head down", "head up", "head right", and "head left", respectively.

[0265] Figure 15 This is a flowchart illustrating an exemplary process for dose estimation according to some embodiments of this application. In some embodiments, process 1500 can be performed... Figure 1 This is implemented in the imaging system 100 shown. For example, at least a portion of process 1500 may be stored as instructions in a storage device (e.g., storage device 130, storage device 220, storage device 390) and processed by a processing device 120 (e.g., such as...). Figure 2 The processor 210 of the computing device 200 shown is, for example Figure 3 The CPU 340 of the mobile device 300 shown is, for example... Figure 7 The procedure 1500 may be invoked and / or executed by one or more modules shown. The operation of the procedures shown below is for illustrative purposes only. In some embodiments, procedure 1500 may be accomplished using one or more additional operations not described, and / or without the one or more operations discussed. Additionally, as Figure 15 The order of operations of process 1500 shown and described below is not intended to be restrictive.

[0266] In 1510, the processing device 120 (e.g., acquisition module 710) can obtain at least one parameter value of at least one scan parameter related to the scan to be performed on the target object.

[0267] For example, the scan can be a CT scan, X-ray scan, etc., performed by a medical imaging device (e.g., medical imaging device 110). At least one scan parameter may include the voltage (expressed in kV), the current (expressed in mA) of the radiation source of the medical imaging device, the exposure time of the scan (in milliseconds), the size of the light field, the scan mode, the movement speed of the scanning stage, the rotation speed of the gantry, the field of view (FOV), the distance between the radiation source and the detector (also known as the source-image distance or SID), etc., or any combination thereof.

[0268] In some embodiments, at least one parameter value can be obtained according to an imaging protocol for a scan related to the target object. The imaging protocol may include information related to the scan and / or the target object, such as the value or range of values ​​of at least one scan parameter (or a portion thereof), a portion of the target object to be imaged, characteristic information of the target object (e.g., gender, body shape, thickness), or any combination thereof. The imaging protocol may be pre-generated (e.g., manually entered by a user or determined by the processing device 120) and stored in a storage device. The processing device 120 may receive the imaging protocol from the storage device and determine at least one parameter value based on the imaging protocol.

[0269] In some embodiments, the processing device 120 may determine at least one parameter value based on the Region of Interest (ROI). An ROI refers to a region or portion thereof of a target object to be scanned. By way of example only, different ROIs of a person may have different default scanning parameter values, and the processing device 120 may determine at least one parameter value based on the type of ROI to be imaged. In some embodiments, the processing device 120 may determine at least one parameter value based on feature information of the ROI. Feature information of the ROI may include the ROI's location, height, width, thickness, etc. For example, the feature information of the ROI may be determined based on image data of the target object captured by an image capture device. Further description of determining feature information of the ROI based on image data can be found elsewhere in this application, for example, in operation 1220 and its description.

[0270] For illustrative purposes, the following explanation uses the determination of kV and mA values ​​based on the thickness of the ROI as an example. In some embodiments, the ROI may comprise different organs and / or tissues. The thickness values ​​of different portions of the ROI (e.g., different organs or tissues) may vary. The thickness of the ROI can be, for example, the average thickness of different portions of the ROI.

[0271] In some embodiments, the processing device 120 may obtain at least two historical protocols from at least two historical scans performed on the same object or one or more other objects (each referred to as a sample object). Each of the at least two historical protocols may include at least one historical parameter value of at least one scan parameter related to the historical scan performed on the sample object, wherein the scan type of the historical scan is the same as the scan type to be performed on the target object. Optionally, each historical protocol may further include feature information related to the corresponding sample object (e.g., the ROI of the sample object, the gender of the sample object, the body shape of the sample object, the thickness of the ROI of the sample object).

[0272] In some embodiments, the processing device 120 may select one or more historical protocols from at least two historical protocols based on feature information related to the target object (e.g., the ROI of the target object to be imaged and the thickness value of the ROI) and information related to the sample objects in each historical record. As an example only, the processing device 120 may select one of at least two historical protocols whose sample objects have the highest similarity to the target object. The similarity between the sample object and the target object may be determined based on feature information of the sample object and feature information of the target object, in a similar manner to that described in conjunction with operation 830. For a specific scanning parameter, the processing device 120 may also designate a historical parameter value of the specific scanning parameter in the selected historical protocol as the parameter value of that scanning parameter. For another example, the processing device 120 may modify the historical parameter value of a specific scanning parameter in the selected historical protocol based on feature information of the target object and the sample object, such as the thickness difference between the ROI of the target object and the ROI of the sample object. The processing device 120 may also designate the modified historical parameter value of the specific scanning parameter as the parameter value of the specific scanning parameter. Further descriptions of the parameter values ​​for determining scanning parameters based on at least two historical protocols can be found, for example, Chinese application No. 20102010185201.9, entitled "A method and system for determining acquisition parameters of a radiographic device," filed on March 17, 2020, and Chinese application No. 202010374378.3, entitled "A method and system for acquiring medical images," filed on May 6, 2020, the contents of which are incorporated herein by reference.

[0273] In some embodiments, the processing device 120 may use parameter values ​​to determine a model, determining at least one parameter value based on the ROI of the target object and the thickness of the ROI.

[0274] In 1520, processing device 120 (e.g., acquisition module 710) can obtain a relationship (also referred to as a third relationship) between a reference dose and at least one scanning parameter. In some embodiments, the reference dose may represent the dose per unit area to be delivered to the target object. Alternatively, the reference dose may indicate the total amount of dose to be delivered to the target object. For example, the third relationship may be generated in advance by a computing device (e.g., processing device 120 or another processing device) and stored in a storage device (e.g., storage device 130 or external storage device). Processing device 120 can obtain the third relationship from the storage device.

[0275] In some embodiments, a third relationship between a reference dose and at least one scanning parameter can be determined by performing at least two reference scans on a reference object. For example, processing device 120 can obtain at least two sets of reference values ​​for at least one scanning parameter. Each set of at least two reference values ​​may include a reference value for each of the at least one scanning parameter. For each set of at least two reference values, a medical imaging device (e.g., medical imaging device 110) can perform a reference scan on the reference object based on the set of reference values, and can measure the value of the reference dose during the reference scan. For example, the reference object may be air, and a radiation dosimeter may be used to measure the value of the reference dose during the reference scan. Processing device 120 (e.g., analysis module 720) can determine the third relationship based on at least two sets of reference values ​​for at least one scanning parameter and at least two values ​​of the reference dose corresponding to the at least two sets of reference values.

[0276] In some embodiments, the processing device 120 can determine a third relationship by performing at least one of the following operations: mapping, fitting, model training, etc., on a set of reference values ​​for at least one scan parameter and a reference dose value corresponding to the set of reference values. For example, the third relationship can be presented in tabular form, recording at least two sets of reference values ​​for at least one scan parameter and their corresponding reference dose values. As another example, the third relationship can describe how the reference dose value changes with the reference values ​​of at least one scan parameter in the form of a fitted curve or fitted function. As yet another example, the third relationship can be presented in the form of a dose prediction model. At least two second training samples can be generated based on the set of reference values ​​for at least one scan parameter and their corresponding reference dose values. This can be done as described in other parts of this application (e.g., Figure 12 (and related descriptions), based on the machine learning algorithm, a second preliminary model is trained using the second training samples to obtain a dose prediction model.

[0277] By way of example only, at least one parameter value may include kV, mA, and ms. A first set of reference values ​​may include a first value of kV (denoted as kV1), a first value of mA (denoted as mA1), and a first value of ms (denoted as ms1). A second set of reference values ​​may include a second value of kV (denoted as kV2), a second value of mA (denoted as mA2), and a second value of ms (denoted as ms2). A first reference scan can be performed by scanning air using the first set of reference values, and a radiation dosimeter can measure the total dose or dose per unit area of ​​the reference dose corresponding to the first set of reference values ​​in the first scan as the first value. A second reference scan can be performed by scanning air using the second set of reference values, and a radiation dosimeter can measure the total dose or dose per unit area of ​​the reference dose corresponding to the second set of reference values ​​in the second scan as the second value. For example, a third relationship may be displayed in a table that includes recording the first values ​​of kV1, mA1, ms1, and the reference dose, and recording the second values ​​of kV2, mA2, ms2, and the reference dose. For example, the first values ​​of kV1, mA1, ms1, and the reference dose can be considered as training sample S1, and the second values ​​of kV2, mA2, ms2, and the reference dose can be considered as training sample S2. Training samples S1 and S2 can be used as the second training samples for generating the dose prediction model.

[0278] In 1530, the processing device 120 (e.g., analysis module 720) can determine the value of the estimated dose associated with the target object based on a third relationship and at least one parameter value of at least one scanning parameter.

[0279] In some embodiments, the reference dose may represent the total dose. The processing device 120 may determine the value of the reference dose corresponding to at least one parameter value of at least one scanning parameter based on a third relationship. The processing device 120 may also specify the value of the reference dose as the value of the estimated dose.

[0280] In some embodiments, the reference dose may represent the dose per unit area. The processing device 120 may determine the reference dose value corresponding to at least one parameter value of at least one scan parameter based on a third relationship and at least one parameter value. For example, the processing device 120 may determine the reference dose value corresponding to at least one parameter value of at least one scan parameter by looking up a table recording the third relationship or by inputting at least one parameter value of at least one scan parameter into a dose prediction model. The processing device 120 may also acquire the size (or area) of the optical field associated with the scan. For example, the processing device 120 may acquire the size (or area) of the optical field associated with the scan by performing a combination of... Figure 12One or more operations of the described process 1200 determine the size (or area) of the optical field. For example, the size (or area) of the optical field can be predetermined, for instance, determined manually by the user or by other computing devices and stored in a storage device. The processing device 120 can obtain the size (or area) of the optical field from the storage device. The processing device 120 can then determine the estimated dose value based on the size (or area) of the optical field and the dose per unit area. For example, the processing device 120 can determine the estimated dose value by multiplying the corresponding size (or area) of the optical field by the corresponding value of the dose per unit area.

[0281] In some embodiments, the estimated dose may include a first estimated dose to be delivered to the target object during scanning, which may be determined, for example, based on the size of the optical field and the dose per unit area value described above. In some embodiments, the processing device 120 may also determine a second estimated dose value based on the first estimated dose. The second estimated dose may indicate the dose absorbed by the target object (or a portion thereof) during scanning.

[0282] In some embodiments, at least two Regions of Interest (ROIs) of the target object can be scanned. For each of the at least two ROIs, the processing device 120 can determine the value of a second estimated dose absorbed by the ROI during the scan. For example, for each of the at least two ROIs, the processing device 120 can obtain the thickness and attenuation coefficient of the ROI. The processing device 120 can also determine the value of a second estimated dose absorbed by the corresponding ROI during the scan based on the value of a first estimated dose, the thickness of the ROI, and the attenuation coefficient of the ROI. Additionally or alternatively, the processing device 120 can further generate a dose distribution map based on the values ​​of the second estimated doses of the at least two ROIs. The dose distribution map can show the distribution of the estimated dose absorbed by different ROIs during the scan in a more intuitive and effective manner. For example, in the dose distribution map, at least two ROIs can be displayed in different colors according to their respective estimated dose values. As another example, if the value of the second estimated dose of an ROI exceeds an absorbed dose threshold, the ROI can be marked with a specific color or annotation to remind the user that the parameter value of at least one scan parameter may need to be checked and / or adjusted.

[0283] Optionally, the processing device 120 can determine the total estimated dose absorbed by the target object. In some embodiments, the processing device 120 can determine the total estimated dose absorbed by the target object by summing the values ​​of a second estimated dose for each ROI. Additionally or alternatively, different ROIs (e.g., different organs or tissues of the target object) may correspond to different thickness values ​​and / or different attenuation coefficient values. The processing device 120 can determine the average thickness of at least two ROIs and the average attenuation coefficient of at least two ROIs.

[0284] The first estimated dose and / or the second estimated dose can be used to assess whether the value of at least one parameter of at least one scan parameter obtained in operation 1510 is appropriate. For example, an insufficient first estimated dose (e.g., less than a first dose threshold) may indicate a reduction in the quality of the image generated based on the scan data acquired in the scan. Similarly, a second estimated dose exceeding the second dose threshold for a region of interest (ROI) may indicate that the ROI may be excessively damaged. By determining the first estimated dose and / or the second estimated dose and then assessing at least one scan parameter, several problems (e.g., relatively low quality of the generated image and / or excessive damage to the target object) can be avoided. Compared to the conventional approach where the user needs to manually determine the first estimated dose and / or the second estimated dose, the automated dose prediction system and method disclosed herein can be more accurate and efficient, for example, reducing the user's workload, reducing bias between different users, and reducing the time required to select at least one target ionization chamber.

[0285] In step 1540, processing device 120 (e.g., analysis module 720) can determine whether an estimated dose (e.g., a first estimated dose) is greater than a dose threshold (e.g., a dose threshold associated with the first estimated dose). In response to determining that the estimated dose is greater than the dose threshold, processing device 120 can operate in step 1550 to determine that the parameter value of at least one scan parameter needs to be adjusted.

[0286] In response to determining that the estimated dose is less than (or equal to) a dose threshold, processing device 120 may determine that the parameter value of at least one scanning parameter does not require adjustment. Optionally, processing device 120 may perform 1560 to send a control signal to a medical imaging apparatus to cause the medical imaging apparatus to scan the target object based on the parameter value of at least one of the at least one scanning parameters. In some embodiments, the dose threshold may be a preset value stored in a storage device (e.g., storage device 130) or manually set by a user. Alternatively, the dose threshold may be determined by processing device 120. By way of example only, a dose threshold may be selected from at least two candidate dose thresholds based on gender, age, and / or other reference information about the target object.

[0287] In some embodiments, the processing device 120 can transmit dose assessment results (e.g., the value of a first estimated dose, the value of a second estimated dose, and / or a dose distribution map) to a terminal device (e.g., terminal device 140). A user can view the dose assessment results through the terminal device. Optionally, the user can also input a response regarding whether the value of at least one scan parameter needs to be adjusted.

[0288] In 1550, in response to determining that the estimated dose exceeds the dose threshold, the processing device 120 (e.g., analysis module 720) can determine the parameter value that needs to be adjusted for at least one scan parameter.

[0289] In some embodiments, the processing device 120 may send a notification to the terminal device to inform the user that the parameter value of at least one scanning parameter needs to be adjusted. The user may manually adjust the parameter value of at least one scanning parameter. As an example only, the user may adjust (e.g., decrease or increase) the parameter value of the radiation source voltage, the parameter value of the radiation source current, the parameter value of the exposure time, SID, etc., or any combination thereof.

[0290] In some embodiments, the processing device 120 may send a control signal to cause the medical imaging apparatus to adjust the parameter value of at least one scanning parameter. For example, the control signal may cause the medical imaging apparatus to reduce the parameter value of the radiation source current by, for example, 10 mA.

[0291] In 1560, in response to determining that the estimated dose does not exceed a dose threshold, processing device 120 (e.g., control module 730) can cause a medical imaging device (e.g., medical imaging device 110) to scan the target object at least partially based on at least one parameter value of at least one scanning parameter. For example, processing device 120 can use at least one parameter value obtained in operation 1510 and / or parameter values ​​of other parameters associated with the scan (e.g., in...) Figure 10 The target position of the scanning stage or the target position of the detector determined in operation 1030 is sent to the medical imaging apparatus. In some embodiments, process 1500 (or a portion thereof) may be performed before, during, or after the target object is placed in the scanning position to receive a scan.

[0292] In some embodiments, after adjusting at least one parameter value of at least one scanning parameter, the processing device 120 can generate an updated parameter value for at least one scanning parameter. The processing device 120 can send the updated parameter value to a medical imaging apparatus. The medical imaging apparatus can perform scanning at least partially based on the updated parameter value.

[0293] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the teachings of this application. However, such changes and modifications do not depart from the scope of this application. In some embodiments, one or more operations may be added or omitted. For example, operations 1540-1560 may be omitted. In some embodiments, the operations in process 1500 may be performed in a different order. For example, operation 1520 may be performed before operation 1510.

[0294] Figure 16A This is a flowchart illustrating an exemplary process for selecting a target ionization chamber from a plurality of ionization chambers, according to some embodiments of this application. In some embodiments, process 1600A can be performed in... Figure 1This is implemented in the imaging system 100 shown. For example, process 1600A can be stored as instructions in a storage device (e.g., storage device 130, storage device 220, storage device 390) and processed by a processing device 120 (e.g., such as...). Figure 2 The processor 210 of the computing device 200 shown, such as Figure 3 The CPU 340 of the mobile device 300 shown is as follows: Figure 7 The procedure 1600A may be invoked and / or executed by one or more modules shown. The operation of the procedures shown below is for illustrative purposes only. In some embodiments, procedure 1600A may be accomplished by one or more additional operations not described and / or by removing one or more of the operations discussed. Additionally, as Figure 16A The order of operations of the process 1600A shown and described below is not intended to be restrictive.

[0295] In 1610, processing device 120 (e.g., acquisition module 710) can acquire target image data of a target object to be scanned by a medical imaging apparatus. The medical imaging apparatus may include multiple ionization chambers. In some embodiments, the medical imaging apparatus (e.g., medical imaging apparatus 110) may be a suspended X-ray medical imaging apparatus, a digital radiography (DR) device (e.g., a mobile digital X-ray medical imaging apparatus), a C-arm device, a CT device, or similar devices as described in other parts of this application.

[0296] In some embodiments, after the target object is positioned to receive a scan from the medical imaging apparatus, target image data can be captured by an image capturing device (e.g., image capturing device 160). For example, process 1600A can be performed after one or more active components (e.g., detectors) of the medical imaging apparatus have been moved to their respective target positions. For example, the target position in one or more active components can be determined in a manner similar to operations 1010-1030. As another example, process 1600A can be performed before or after process 1500 for dose estimation.

[0297] Target image data may include 2D image data, 3D image data, depth image data, etc., or any combination thereof. In some embodiments, the processing device 120 may send an instruction to the image capturing device to capture image data of the target object after the target object is positioned at the scanning location. In response to the instruction, the image capturing device may capture image data of the target object as target image data and transmit the captured target image data directly or via a network (e.g., network 150) to the processing device 120. Alternatively, after the target object is positioned at the scanning location, the image capturing device may be instructed to capture image data of the target object continuously or intermittently (e.g., periodically). In some embodiments, after capturing image data, the image capturing device may transmit the image data to the processing device 120 as target image data for further analysis. In some embodiments, target image data may be acquired almost in real time via the image capturing device, the captured target image data may be transmitted to the processing device 120, and the target image data may be analyzed to provide information indicating the near real-time state of the target object.

[0298] Ionization chambers in a medical imaging apparatus can be configured to detect the amount of radiation reaching a detector within the medical imaging apparatus (e.g., radiation per unit area per unit time). For example, multiple ionization chambers may include ventilated chambers, sealed low-pressure chambers, high-pressure chambers, etc., or any combination thereof. In some embodiments, at least one target ionization chamber (described in conjunction with operation 1620) may be selected from among the multiple ionization chambers. At least one target ionization chamber may be activated during scanning of a target object, while other ionization chambers (if any) may be deactivated during the scanning of the target object.

[0299] In 1620, the processing device 120 (e.g., analysis module 720) can select at least one target ionization chamber from among a plurality of ionization chambers based on the target image data.

[0300] In some embodiments, the processing device 120 may select a single target ionization chamber from a plurality of ionization chambers. Alternatively, the processing device 120 may select multiple target ionization chambers from a plurality of ionization chambers. For example, the processing device 120 may compare the size (e.g., area) of the light field associated with the scan with a size threshold. In response to determining that the size of the light field is greater than the size threshold, the processing device 120 may select two or more target ionization chambers from the plurality of ionization chambers. As another example, if at least two organs of interest exist in the ROI, the processing device 120 may select at least two target ionization chambers from the plurality of ionization chambers. An organ of interest refers to a specific organ or tissue of the target object. By way of example only, if the ROI includes the chest, the processing device 120 may select two target ionization chambers from the plurality of ionization chambers, wherein one of the target ionization chambers may correspond to the left lung of the target object, and the other of the target ionization chambers may correspond to the right lung of the target object.

[0301] In some embodiments, the processing device 120 may select at least one candidate ionization chamber corresponding to the ROI from among multiple ionization chambers based on target image data and location information of multiple ionization chambers. The processing device 120 may also select a target ionization chamber from the candidate ionization chambers. As an example only, the processing device 120 (e.g., analysis module 720) may generate a target image at least partially based on the target image data (e.g., combined with...). Figure 16B The first target image and / or combination described Figure 16C The second target image is described, and the target ionization chamber is selected from the candidate ionization chambers based on the target image.

[0302] In some embodiments, the processing device 120 can perform a combination Figure 16B The described process 1600B and / or combination Figure 16C The process described is one or more operations at 1600°C to select the target ionization chamber.

[0303] In 1630, the processing device 120 (e.g., control module 730) enables the medical imaging device to scan a target object using at least one target ionization chamber.

[0304] For example, the processing device 120 can send an instruction to a medical imaging apparatus to instruct the medical imaging apparatus to begin scanning. This instruction may include information about at least one target ionization chamber, such as the identification number of each target ionization chamber, the location of each target ionization chamber, etc. Optionally, the instruction may further include parameter values ​​of one or more parameters related to the scan. For example, one or more parameters may include the current of the radiation source, the voltage of the radiation source, the exposure time, etc., or any combination thereof. In some embodiments, the processing device 120 can perform a combined... Figure 15The described process 1500 involves one or more operations to determine the current, voltage, and exposure time of the radiation source.

[0305] In some embodiments, an automatic exposure control (AEC) method may be implemented when scanning a target object. When the cumulative radiation detected in at least one target ionization chamber exceeds a threshold, a radiation controller (e.g., a component of a medical imaging device or processing equipment) may cause the radiation source of the medical imaging device to stop scanning.

[0306] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this disclosure. Various changes and modifications can be made by those skilled in the art based on the teachings of this disclosure. However, such changes and modifications do not depart from the scope of this disclosure. In some embodiments, one or more operations may be added or omitted. For example, a user (e.g., an operator) may view a target image and select at least one target ionization chamber from a plurality of ionization chambers. Process 1600A may further include an operation in which processing device 120 receives user input regarding the selection of at least one target ionization chamber.

[0307] Figure 16B This is a flowchart illustrating an exemplary process for selecting at least one target ionization chamber for a target object's ROI based on target image data of the target object, according to some embodiments of this application. In some embodiments, one or more operations of process 1600B may be performed to achieve the combination of... Figure 16A At least a portion of the described operation 1620.

[0308] In 1640, the processing device 120 (e.g., analysis module 720) can select at least one first candidate ionization chamber near the ROI of the target object from among a plurality of ionization chambers.

[0309] In some embodiments, the processing device 120 may select one or more first candidate ionization chambers near the ROI from among the ionization chambers based on the distance between the ionization chamber and the ROI. The distance between the ionization chamber and the ROI refers to the distance between a point (e.g., the center point) of the ionization chamber and a point (e.g., the center point) of the ROI. The distance between the ionization chamber and the ROI may be determined based on the location information of the ionization chamber and the location information of the ROI. For example, the location information of the ionization chamber may include the position of the ionization chamber relative to a reference component (e.g., a detector) of the medical imaging apparatus and / or the position of the ionization chamber in a 3D coordinate system. The location information of the ionization chamber may be stored in a storage device (e.g., storage device 130) or determined based on target image data. The location information of the ROI may include the position of the ROI relative to a reference component of the medical imaging apparatus (e.g., a detector). The location information of the ROI may be determined based on target image data, for example, by identifying a target region in the target image data. The target region may correspond to the ROI of a target object.

[0310] As an example only, for an ionization chamber, processing device 120 can determine the distance between the ionization chamber and the ROI. Processing device 120 can determine whether the distance is less than a distance threshold. In response to determining that the distance corresponding to the ionization chamber is less than the distance threshold, processing device 120 can determine that the ionization chamber is near the ROI and designate the ionization chamber as one of the first candidate ionization chambers. Alternatively, processing device 120 can select the ionization chamber closest to the ROI. The selected ionization chamber can be considered to be located near the ROI and designated as one of the first candidate ionization chambers.

[0311] In 1650, for each first candidate ionization chamber, the processing device 120 (e.g., analysis module 720) can determine whether the positional offset between the ROI and the first candidate ionization chamber is negligible based on the target image data and the positional information of the first candidate ionization chamber.

[0312] As used in this paper, if the positional offset between the ROI and the first candidate ionization chamber is negligible, the position of the first candidate ionization chamber and the position of the ROI can be considered to be matched, and the first candidate ionization chamber can be selected as one of at least one target ionization chamber.

[0313] In some embodiments, for a first candidate ionization chamber, the processing device 120 can determine whether the positional offset between the first candidate ionization chamber and the ROI is negligible by generating a first target image. The first target image can indicate the position of the first candidate ionization chamber relative to the ROI, and it can be generated based on target image data and the positional information of the first candidate ionization chamber. For example, the first target image can be generated by annotating the ROI and the first candidate ionization chamber (and optionally one or more other first ionization chambers) on the target image data. As another example, a target object model representing a target object can be generated based on the target image data. The first target image can be generated by annotating the ROI and at least one first candidate ionization chamber (and optionally other ionization chambers from a plurality of ionization chambers) on the target object model. By way of example only, the first target image can be... Figure 20 The image shown is similar to image 2000, in which at least two representations 2030 of multiple ionization chambers are annotated on representation 2010 of the target object (i.e., the target object model).

[0314] The processing device 120 can further determine whether the representation of a first candidate ionization chamber in the first target image is covered by a target region corresponding to a Region of Interest (ROI) in the first target image. As used herein, in an image, if the target region corresponding to the ROI covers all or more of the representation of the first candidate ionization chamber (e.g., 99%, 95%, 90%, 80%), the representation of the first candidate ionization chamber can be considered to be covered by the target region. In response to determining that the representation of the first candidate ionization chamber in the first target image is covered by the target region, the processing device 120 can determine that the positional offset between the first candidate ionization chamber and the ROI is negligible. In response to determining that the representation of the first candidate ionization chamber in the first target image is not covered by the target region, the processing device 120 can determine that the positional offset between the first candidate ionization chamber and the ROI is not negligible (or that there is a positional offset between the first candidate ionization chamber and the ROI).

[0315] Alternatively, processing device 120 may send the first target image to a terminal device (e.g., terminal device 140) to display the first target image to a user (e.g., an operator). The user can view the first target image and provide user input through terminal device 140. Processing device 120 may determine, based on user input, whether the positional offset between the first candidate ionization chamber and the ROI is negligible. For example, user input may indicate whether the positional offset between the first candidate ionization chamber and the ROI is negligible. As another example, user input may indicate whether the first candidate ionization chamber should be selected as the target ionization chamber.

[0316] In 1660, for each of the at least one first candidate ionization chambers, the processing device 120 (e.g., analysis module 720) can determine whether the first candidate ionization chamber is one of the at least one target ionization chamber based on the result of determining whether the positional offset is negligible.

[0317] For the first candidate ionization chamber, in response to determining that the corresponding positional offset is negligible, the processing device 120 can designate the first candidate ionization chamber as one of the target ionization chambers corresponding to the ROI. In some embodiments, the processing device 120 can select a target ionization chamber and annotate the selected target ionization chamber in the first target image. The processing device 120 can also transmit the first target image with the annotation of the selected target ionization chamber to the user's terminal device. The user can verify the selection result of the target ionization chamber.

[0318] For a first candidate ionization chamber, in response to determining that the positional offset is not negligible (i.e., a positional offset exists), the processing device 120 may not identify the first candidate ionization chamber as one of the target ionization chambers. In some embodiments, if a positional offset (i.e., a non-negligible positional offset) exists for each of the first candidate ionization chambers, the processing device 120 may determine that the position of the ROI relative to the plurality of ionization chambers needs to be adjusted. For example, the processing device 120 and / or the user may move the scanning stage (e.g., scanning stage 114) and / or detector (e.g., detector 112, flat panel detector 440) of a medical imaging apparatus to adjust the position of the ROI relative to the plurality of ionization chambers. As another example, the processing device 120 may instruct the target object to move one or more body parts to adjust the position of the ROI relative to the plurality of ionization chambers. Further details regarding the adjustment of the position of the ROI relative to the plurality of ionization chambers can be found elsewhere in this application (e.g., Figure 17 (and related descriptions).

[0319] In some embodiments, after adjusting the position of the ROI relative to the ionization chamber, the processing device 120 may further select at least one target ionization chamber among a plurality of ionization chambers based on the adjusted ROI position. For example, after adjusting the position of the target object, the processing device 120 may again perform operation 1610 to obtain updated target image data of the target object. The processing device 120 may also perform 1620 to determine at least one target ionization chamber based on the updated target image data.

[0320] Figure 16C This is a flowchart illustrating an exemplary process for selecting at least one target ionization chamber for a target object's ROI based on target image data of the target object, according to some embodiments of this application. In some embodiments, one or more operations may be performed to achieve, as in combination Figure 16AAt least a portion of the described operation 1620.

[0321] In 1670, the processing device 120 (e.g., analysis module 720) can generate a second target image that indicates the position of at least some of the ionization chambers relative to the ROI of the target object.

[0322] For example, at least some ionization chambers may include all of the multiple ionization chambers. As another example, the multiple ionization chambers may include a portion of the ionization chambers, which may be selected randomly or according to specific rules. By way of example only, the multiple sets of ionization chambers may be located in different regions (e.g., relative to the detector), such as a set of ionization chambers located in the central region, a set of ionization chambers located in the left region, a set of ionization chambers located in the right region, a set of ionization chambers located in the upper region, a set of ionization chambers located in the lower region, etc. The processing device 120 may select one or more sets of ionization chambers as at least some of the ionization chambers. For example, if the ROI includes two target organs generally located on either side of the target object's body, such as the right lung and left lung, the processing device 120 may select at least one set of ionization chambers located in the left region and at least one set of ionization chambers located in the right region as at least some of the multiple ionization chambers.

[0323] In some embodiments, the processing device 120 can generate a second target image by annotating the ROI and at least some of the ionization chambers in a plurality of ionization chambers onto the target image data. For example... Figure 20 As shown, one or more candidate ionization chambers 2030 can be annotated in the displayed image, and the displayed image can be presented to the user via a terminal device. For example, an object model representing a target object can be generated based on target image data. A second target image can be generated by annotating at least some of the ionization chambers among a plurality of ionization chambers on the object model. In some embodiments, a second target image can be generated by overlaying the representation of each of at least some of the ionization chambers among a plurality of ionization chambers onto the representation of the target object in an image (e.g., the representation of the object model).

[0324] In 1680, the processing device 120 (e.g., analysis module 720) can identify at least one second candidate ionization chamber among a plurality of ionization chambers based on the second target image.

[0325] The second candidate ionization chamber refers to the ionization chamber in the second target image that is covered by the target region corresponding to the ROI in the second target image.

[0326] In 1690, the processing device 120 (e.g., analysis module 720) can select at least one target ionization chamber from a plurality of ionization chambers based on the identification result of at least one second candidate ionization chamber.

[0327] In some embodiments, the processing device 120 may determine whether at least one identified second candidate ionization chamber exists in the second target image. In response to determining that at least one identified second candidate ionization chamber exists in the second target image, the processing device 120 may select a target ionization chamber corresponding to the ROI from the at least one identified second candidate ionization chamber. For example, the processing device 120 may randomly select one or more from the at least one identified second candidate ionization chamber as the target ionization chamber. As another example, the processing device 120 may designate one of the at least one identified second candidate ionization chambers whose center point is closest to a specific point of the ROI (e.g., the center point of the ROI or a specific tissue of the ROI) as the target ionization chamber corresponding to the ROI. As yet another example, the ROI may include the left lung and the right lung. The processing device 120 may designate one of the at least one identified second candidate ionization chambers whose center point is closest to the center point of the left lung as the target ionization chamber corresponding to the left lung. The processing device 120 may also designate one of the at least one identified second candidate ionization chambers whose center point is closest to the center point of the right lung as the target ionization chamber corresponding to the right lung. In this way, the processing device 120 can automatically select a target ionization chamber from multiple ionization chambers, requiring almost no user input to select the target ionization chamber. Automatic selection of the target ionization chamber reduces user workload and is more accurate (e.g., unaffected by human error or subjectivity).

[0328] In some embodiments, the processing device 120 can transmit a second target image to a user's terminal device. The user can view the second target image through the terminal device. The processing device 120 can determine at least one target ionization chamber corresponding to the ROI based on user input received via the terminal device. For example, the user input can indicate a target ionization chamber to be selected from at least one identified second candidate ionization chamber. In some embodiments, the processing device 120 can select a target ionization chamber and annotate the selected target ionization chamber in the second target image. The processing device 120 can also transmit the second target image with the annotation of the selected target ionization chamber to the terminal device. The user can verify the selection result of the target ionization chamber.

[0329] In some embodiments, in response to determining that no second candidate ionization chamber has been identified in the second target image, the processing device 120 may determine that the position of the ROI relative to the plurality of ionization chambers needs to be adjusted. Further details regarding the adjustment of the position of the ROI relative to the plurality of ionization chambers can be found elsewhere in this application, for example, in relation to Figure 16B Operation 1660 and / or Figure 17 The description of operation 1730 is in the middle.

[0330] According to some embodiments of this application, the systems and methods disclosed herein can generate target images (first target images and / or second target images as described above) indicating the location of one or more ionization chambers (e.g., candidate ionization chambers and / or target ionization chambers) relative to a target object's ROI. Optionally, the systems and methods can also transmit the target images to a user's terminal device to assist or check the selection of the target ionization chamber.

[0331] Typically, the ionization chamber of existing medical imaging devices is located between the target object and the detector. Because the location of the ionization chamber is shielded by the target object and / or detector (e.g., flat panel detector 440), it can be difficult for users to directly observe the position of the ionization chamber relative to the ROI. By generating a target image (e.g., a first target image or a second target image), the position of the ionization chamber (or a portion thereof) relative to the ROI can be presented in the target image. Visualization of one or more ionization chambers from multiple ionization chambers facilitates the selection of a target ionization chamber from multiple ionization chambers and / or the verification of the selection results, and also improves the accuracy of target ionization chamber selection. Compared to the conventional approach where users need to manually select at least one target ionization chamber from multiple ionization chambers, the automated target ionization chamber selection system and method disclosed herein are more accurate and efficient, for example, reducing user workload, inter-user variability, and the time required to select at least one target ionization chamber.

[0332] Figure 17 This is a flowchart illustrating an exemplary process for object positioning according to some embodiments of this application. In some embodiments, process 1700 may be performed... Figure 1 This is implemented in the imaging system 100 shown. For example, process 1700 can be stored as instructions in a storage device (e.g., storage device 130, storage device 220, storage device 390) and processed by a processing device 120 (e.g., such as...). Figure 2 The processor 210 of the computing device 200 shown, such as Figure 3 The CPU 340 of the mobile device 300 shown is as follows: Figure 7 The procedure 1700 may be invoked and / or executed by one or more modules shown. The operation of the procedure shown below is for illustrative purposes only. In some embodiments, procedure 1700 may be accomplished using one or more additional operations not described, and / or by removing one or more operations discussed. Additionally, as Figure 17 The order of operations of process 1700 shown and described below is not intended to be restrictive.

[0333] In 1710, the processing device 120 (e.g., acquisition module 710) can acquire target image data of the target object to be examined (treated or scanned) while maintaining its pose. The target image data can be captured by an image capture device.

[0334] Pose can reflect the position, orientation, shape, size, etc. of a target object (or a part thereof). In some embodiments, operation 1720 can be combined with... Figure 16A Operation 1610 is performed in a similar manner, and its description will not be repeated here.

[0335] In 1720, the processing device 120 (e.g., acquisition module 710) can obtain a target pose model representing the target pose of the target object. (As in conjunction with...) Figure 9 The target pose of the target object, as described, can also be referred to as the reference pose of the target object. The target pose can be the standard pose that the target object needs to maintain during scanning. The target pose model can be a 2D skeleton model, a 3D skeleton model, a 3D mesh model, etc.

[0336] In some embodiments, the target pose model may be generated by processing device 120 or another computing device based on a reference pose model and image data of the target object. Image data of the target object may be acquired before capturing target image data. For example, image data of the target object may be acquired before or after the target object enters the examination room. Further description of the generation of the target pose model can be found elsewhere in this application (e.g., process 900 and its related description).

[0337] In 1730, the processing device 120 (e.g., analysis module 720) can determine whether the pose of the target object needs to be adjusted based on the target image data and the target pose model.

[0338] In some embodiments, the processing device 120 may generate a target object model based on target image data. The target object model may represent a pose-preserving target object model. For example, the target object model may be a 2D skeleton model, a 3D skeleton model, a 3D mesh model, etc. In some embodiments, the target object model and the target pose model may have the same model type. For example, both the target object model and the target pose model may be 3D skeleton models. In some embodiments, the target object model and the target pose model may have different model types. For example, the target object model may be a 2D skeleton model, while the target pose model may be a 3D skeleton model. The processing device 120 may need to convert the 3D skeleton model into a second 2D skeleton model, for example, by projecting the 3D skeleton model. The processing device 120 may further compare the 2D skeleton model corresponding to the target object model and the second 2D skeleton model corresponding to the target pose model.

[0339] Then, the processing device 120 can determine the degree of matching between the target object model and the target pose model. The processing device 120 can also determine whether the pose of the target object needs adjustment based on the degree of matching. For example, the processing device 120 can compare the degree of matching with a threshold. For example, the threshold could be 70%, 75%, 80%, 85%, etc. In response to determining that the degree of matching is greater than (or equal to) the threshold, the processing device 120 can determine that the pose of the target object does not need adjustment. In response to determining that the degree of matching is less than the threshold, the processing device 120 can determine that the pose of the target object needs adjustment. As an example only, the processing device 120 can further generate a notification. This notification can be configured to notify a user (e.g., an operator) that the pose of the target object needs adjustment. This notification can be provided to the user via a terminal device in the form of, for example, text, voice, image, video, haptic alarm, etc., or any combination thereof.

[0340] The matching degree between the target object model and the target pose model can be determined by various methods. As an example only, the processing device 120 can identify one or more first feature points from the target object model and one or more second feature points from the target pose model. The processing device 120 can also determine the matching degree between the target object model and the target pose model based on one or more first feature points and one or more second feature points. For example, one or more first feature points may include at least two first pixels corresponding to at least two joints of the target object. One or more second feature points may include at least two second pixels corresponding to at least two joints of the target object. The matching degree can be determined by comparing the first coordinates of each first pixel in the target object model with the second coordinates of the corresponding second pixel in the target pose model. If the first pixel and the second pixel correspond to the same body point of the target object, they can be considered to correspond to each other.

[0341] For example, processing device 120 can determine the distance between a first pixel and a second pixel based on a first coordinate of a first pixel and a second coordinate of a second pixel corresponding to the first pixel. Processing device 120 can compare this distance to a threshold. In response to determining that the distance is less than or equal to the threshold, processing device 120 can determine that the first pixel matches the second pixel. For example, the threshold can be 0.5cm, 0.2cm, 0.1cm, etc. In some embodiments, the threshold can have a default value or a value manually set by the user. Additionally or alternatively, the threshold can be adjusted as needed. In some embodiments, processing device 120 can further determine the matching degree between the target object model and the target pose model based on the proportion of first pixels in the target object model that match the corresponding second pixel in the target pose model. For example, if each of 70% of the first pixels in the target object model matches a corresponding second pixel, then processing device 120 can determine that the matching degree between the target object model and the target pose model is 70%.

[0342] In some embodiments, the processing device 120 (e.g., analysis module 720) can generate a synthetic image (e.g., such as) based on the target pose model and target image data. Figure 18 The synthetic image 1800 shown is used. The processing device 120 can further determine, based on the synthetic image, whether the pose of the target object needs adjustment. The synthetic image can show a target pose model and the target object. As an example only, in the synthetic image, a representation of the target pose model can be superimposed on a representation of the target object. For example, the target image data can include an image of the target object, such as a color image or an infrared image. A synthetic image can be generated by superimposing a representation of the target pose model onto the representation of the target object in the image of the target object. As another example, a target object model representing the target object can be generated based on the target image data of the target object. A synthetic image can be generated by superimposing a representation of the target pose model onto a representation of the target object model.

[0343] In some embodiments, the processing device 120 may determine the matching degree between a target object model and a target pose model based on a synthesized image, and determine whether the pose of the target object needs adjustment based on the matching degree. For example, the processing device 120 may determine the proportion of overlap between the representation of the target object model and the representation of the target pose model in the synthesized image. The higher the proportion, the higher the matching degree between the target object model and the target pose model. The processing device 120 may further determine whether the pose of the target object needs adjustment based on the matching degree and a threshold degree.

[0344] Additionally or alternatively, the processing device 120 can transmit the synthesized image to a terminal device. In some embodiments, the terminal device may include a first terminal device (e.g., a console) for a user (e.g., a doctor, medical imaging device operator). The processing device 120 can receive user input from the user regarding whether the pose of a target object needs adjustment. For example, the user's first terminal device may display the synthesized image to the user. The user can determine whether the pose of the target object needs adjustment based on the synthesized image and input his / her determination via the first terminal device. Compared to the conventional method of determining whether the pose of a target object needs adjustment by directly observing the pose of the target object, the synthesized image allows the user to more conveniently compare the pose of the target object with a target pose (i.e., a standard pose).

[0345] Alternatively or additionally, the terminal device may include a second terminal device (e.g., a patient) within the target object. For example, the second terminal device may include a display device located near the target object, such as mounted on the ceiling of a medical imaging device or examination room. The processing device 120 may transmit the synthesized image to the second terminal device. The target object can view the synthesized image through the second terminal device and obtain information about his / her current pose and the target pose he / she needs to maintain. In some embodiments, in response to determining that the target object's pose needs adjustment, the processing device 120 may generate an instruction. This instruction may instruct the target object to move one or more body parts to maintain the target pose. The instruction may be in the form of text, voice, image, video, haptic alarm, etc., or any combination thereof. The instruction may be provided to the target object through the second terminal device. For example, the instruction may be provided to the "target object" in the form of a voice instruction, such as "Please move to the left," "Please put your arm on the armrest of the medical imaging device," etc. Alternatively or additionally, the instruction may include image data (e.g., images, animations) instructing the target object to move one or more body parts. As an example only, a synthetic image showing the target pose model and the target object can be displayed to the target object via a second terminal device. Annotations can be provided on the synthetic image to indicate the need to move one or more body parts and / or suggest the direction of movement for one or more body parts. In some embodiments, a user (e.g., an operator) can view the synthetic image via a first terminal device and guide the target object to move one or more body parts.

[0346] In some embodiments, in response to determining that the pose of a target object needs adjustment (e.g., position), the processing device 120 may adjust the position of one or more moving components. For example, one or more moving components may include a scanning stage (e.g., scanning stage 114), a detector (e.g., detector 112, flat panel detector 440), a radiation source (e.g., a tube, radiation source 115, X-ray source 420), and any combination thereof. Adjusting the position of one or more moving components can change the position of the ROI relative to the medical imaging apparatus, thereby altering the pose of the target object.

[0347] According to some embodiments of this application, a target pose model of a target object can be generated and then used to check and / or guide the localization of the target object. The target pose model can be a customizable model whose contour parameters are the same as or similar to those of the target object. By using such a customizable target pose model, the efficiency and / or accuracy of target object localization can be improved. For example, the target pose model can be compared with a target object model representing the pose of the target object to determine whether the pose of the target object needs adjustment. Alternatively, the target pose model and the target object model can be displayed together in a composite image to guide the target object in adjusting its pose. Compared to conventional methods where users need to manually check and / or guide the localization of the target object, the automatic object localization system and method disclosed herein can be more accurate and efficient, for example, reducing user workload, inter-user variability, and the time required for object placement.

[0348] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this disclosure. Various changes and modifications can be made by those skilled in the art based on the teachings of this application. However, such changes and modifications do not depart from the scope of this application. In some embodiments, one or more operations may be added or omitted. For example, process 1700 may further include updating the target object model based on new target image data of the target object captured after adjusting the pose of the target object. As another example, process 1700 may further include determining whether further adjustment of the target object's pose is needed based on the updated target object model and the target pose model.

[0349] Figure 18 This is a schematic diagram of an exemplary composite image 1800 shown according to some embodiments of this application. Figure 18 As shown, the synthesized image 1800 may include a representation 1810 of the target object and a representation 1820 of the target pose model. The representation 1820 of the target pose model is superimposed on the representation 1810 of the target object.

[0350] For illustrative purposes only, the model is presented in 2D form. Figure 18The target object is represented in 1810. After the target object is located at the scanning position, a 2D model of the target object can be generated based on the target image data captured by the image capturing device. For example, the 2D model of the target object can show the pose (e.g., contour) of the target object in 2D space.

[0351] In some embodiments, the processing device 120 can determine whether the pose of the target object needs adjustment based on the synthesized image 1800. For example, the matching degree between the target object model and the target pose model can be based on the synthesized image 1800. Alternatively, the processing device 120 can transmit the synthesized image 1800 to a user's terminal device for display. The user can view the synthesized image 1800 and determine whether the pose of the target object needs adjustment based on it. Additionally or alternatively, the processing device 120 can transmit the synthesized image 1800 to a terminal device connected to the target object to guide the target object in adjusting its pose.

[0352] about Figure 18 The examples shown are provided for illustrative purposes only and are not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the teachings of this application. However, such changes and modifications do not depart from the scope of this disclosure. For example, the representation 1810 of the target object can be presented in the form of a 3D mesh model, a 3D skeleton model, a real image of the target object, etc. As another example, the representation 1820 of the target pose model can be in the form of a 2D skeleton model.

[0353] Figure 19 This is a flowchart illustrating an exemplary process for image display according to some embodiments of this application. In some embodiments, process 1900 may be performed... Figure 1 This is implemented in the imaging system 100 shown. For example, process 1900 can be stored as instructions in a storage device (e.g., storage device 130, storage device 220, storage device 390) and processed by a processing device 120 (e.g., such as...). Figure 2 The processor 210 of the computing device 200 shown is, for example Figure 3 The CPU 340 of the mobile device 300 shown calls or executes, such as Figure 7 One or more modules are shown. The operation of the process shown below is for illustrative purposes only. In some embodiments, process 1900 may be accomplished using one or more additional operations not described, and / or by removing one or more operations discussed. Additionally, as Figure 19 The order of operations of the process 1900 shown and described below is not intended to be restrictive.

[0354] In 1910, the processing device 120 (e.g., acquisition module 710) can acquire image data of a target object scanned or to be scanned by a medical imaging device.

[0355] Image data of the target object may include image data corresponding to the entire target object or image data corresponding to a portion of the target object. In some embodiments, the medical imaging apparatus (e.g., medical imaging apparatus 110) may be a suspended X-ray medical imaging apparatus, a digital radiography (DR) device (e.g., a mobile digital X-ray medical imaging apparatus), a C-arm device, a CT apparatus, a PET apparatus, an MRI apparatus, etc., as described elsewhere in this application.

[0356] In some embodiments, the image data may include first image data captured by a third image capturing device (e.g., image capturing device 160) before the target object is placed in a scanning position for receiving a scan. For example, the third image capturing device may acquire the first image data when or after the target object enters the examination room. The first image data may be used to generate a target pose model in the target object. Additionally or alternatively, the first image data may be used to determine one or more scanning parameters related to a scan to be performed on the target object by a medical imaging device. For example, one or more scanning parameters may include each target position in one or more active components of the medical imaging device, such as a scanning stage (e.g., scanning stage 114), a detector (e.g., detector 112, flat panel detector 440), an X-ray source (e.g., a tube, radiation source 115, X-ray source 420), etc., or any combination thereof. As another example, one or more scanning parameters may include parameters related to the medical imaging device in the light field, such as parameters related to the target size in the light field.

[0357] In some embodiments, the image data may include second image data (or target image data) captured by a fourth image capturing device (e.g., image capturing device 160) at a scanning location where the target object is positioned for scanning. The third and fourth image capturing devices may be the same or different. For example, the target object may maintain a pose after it is positioned at the scanning location, and the second image data may be used to generate a representation of the target object's maintained pose (e.g., a model of the target object). As another example, the scanning may include a first scan of a first ROI of the target object and a second scan of a second ROI of the target object. The processing device may identify a first region corresponding to the first ROI and a second region corresponding to the second ROI based on the second image data.

[0358] In some embodiments, the image data may include third image data. The third image data may include a first image of the target object captured using a fifth image capturing device or a medical imaging device (e.g., medical imaging device 110). The fifth image capturing device may be the same as or different from the third or fourth image capturing device. For example, the first image may be captured by a camera after the target object is positioned at the scan location. Alternatively, the first image may be generated based on medical image data acquired by an X-ray imaging device during an X-ray scan of the target object. The processing device 120 may process the first image to determine the orientation of the target object.

[0359] In 1920, the processing device 120 (e.g., the analysis module 720) can generate a display image based on the image data.

[0360] In some embodiments, the display image may include a first display image that is a composite image (e.g., Figure 18 The composite image 1800 shown illustrates a target object and a target pose model of the target object. In the first display image, a representation of the target pose model can be superimposed on a representation of the target object. For example, the representation of the target object can be a real person or a target object model representing the target object. In some embodiments, the image data obtained in 1910 may include the image data described above. The processing device 120 can generate the first display image based on the second image data and the target pose model. The processing device 120 can further determine whether the pose of the target object needs adjustment based on the first display image. Further description of the generation of the first display image and the determination of whether the pose of the target object needs adjustment can be found elsewhere in this application (e.g., Figure 17 (and its related description) were found.

[0361] In some embodiments, the displayed image may include a second displayed image. The second displayed image may be an image showing the position of one or more components of a medical imaging apparatus relative to a target object. For example, the medical imaging apparatus may include a plurality of ionization chambers. The second displayed image may include a first target image indicating the position of each of one or more candidate ionization chambers relative to the ROI of the target object. One or more candidate ionization chambers may be selected from a plurality of ionization chambers of the medical imaging apparatus. As another example, the second displayed image may include a second target image showing the position of at least some of the ionization chambers relative to the ROI of the target object. The first target image and / or the second target image may be used to select one or more target ionization chambers from a plurality of ionization chambers, wherein the target ionization chamber can play a role in scanning the ROI of the target object. Further description of the first target image and / or the second target image can be found elsewhere in this application (e.g., Figures 16A-16C(and its related description) were found.

[0362] As yet another example, the second displayed image may include a third target image showing the target position of one or more active components of the medical imaging apparatus (e.g., detectors, radiation sources) relative to a target object. The third target image can be used to determine whether the target position in one or more active components of the medical imaging apparatus needs adjustment. For example, the target position in one or more active components can be determined by performing operations 1010-1030.

[0363] In some embodiments, the displayed image may include a third displayed image showing the position of the light field of the medical imaging apparatus relative to a target object. For example, processing device 120 may acquire one or more parameters of the light field and generate the third displayed image based on one or more parameters of the light field and image data acquired in operation 1910. For example, one or more parameters of the light field may include the position of the light field, target size, width, height, etc. By way of example only, in the third displayed image, an area corresponding to the light field may be marked on the representation of the target object. The third displayed image can be used to determine whether one or more parameters of the light field in the medical imaging apparatus need to be adjusted. Additionally or alternatively, the third displayed image may be used to determine whether the pose of the target object needs to be adjusted. For example, to determine one or more parameters of the light field, processing device 120 may perform a combination of Figure 12 The operation described is similar to one or more operations like 1210-1220.

[0364] In some embodiments, the displayed image may include a fourth displayed image, wherein the representation of the target object has a reference orientation (e.g., a "head-up" orientation). For example, the processing device 120 may determine the orientation of the target object based on image data in the target object. The processing device 120 may also generate a fourth displayed image based on the orientation of the target object and the image data of the target object. In some embodiments, the processing device 120 may, based on the image data, combine... Figure 13 The location of the target object is determined in a similar manner to determining the location of the target object based on the first image. For example, the processing device may determine the location of the target object based on the location within the target region corresponding to the ROI of the target object in the image data. Alternatively, the processing device 120 may determine the location of the target object based on the position of the target region corresponding to the ROI of the target object in the image data.

[0365] Please note that the functions of the first, second, third, and fourth display images provided above are for illustrative purposes only and are not intended to be limiting. In some embodiments, the display image may have a combination of two or more features of the first, second, third, and fourth display images. For example, the display image (e.g., as...) Figure 20 The displayed image 2000 can indicate the target position of one or more active components of a medical imaging device relative to the target object, the position of one or more ionization chambers relative to the target object, and the position of the light field relative to the target object.

[0366] In 1930, the processing device 120 (e.g., the analysis module 720) can transmit the display image to the terminal device for display.

[0367] In some embodiments, the terminal device may include a first terminal device for a user (e.g., a doctor, operator). The user can view a displayed image via the first terminal device. In some embodiments, the displayed image can assist the user in analysis and / or decision-making. For example, the user can view a first displayed image via the first terminal device and determine whether the pose of a target object needs adjustment. Alternatively, the processing device 120 can determine whether the pose of a target object needs adjustment based on the first displayed image. The user can view the first displayed image and confirm the determination that the pose of the target object needs adjustment. As another example, the user can view a second displayed image and determine whether the target position in one or more active components of the target object needs adjustment. Typically, for medical imaging apparatuses containing a scanning stage, the detector is located below the scanning stage, making direct observation of the detector's position very difficult. The second displayed image can help the user understand the detector's position more intuitively, thereby improving the accuracy of the detector's target position. As yet another example, the user can view a third displayed image and determine whether one or more parameters related to the light field need adjustment. The user can adjust one or more parameters of the light field via the first terminal device, such as the size and / or position of the light field (e.g., by moving the position represented by the light field in the third displayed image). As another example, a user can view a fourth display image where the representation of the target object has a reference orientation. The fourth display image (e.g., a CT image, PET image, MRI image) may include anatomical information related to the target object's region of interest (ROI) and / or metabolic information related to the ROI. Users can perform diagnostic analysis based on the fourth display image.

[0368] Additionally or alternatively, the terminal device may include a second terminal device located near the target object. For example, the second terminal device may be a display device mounted on the ceiling of a medical imaging apparatus or examination room. The second terminal device may display the first image to the target object. In some embodiments, instructions may be provided to the target object to guide it to move one or more body parts to assume a target pose. Instructions may be provided to the target object via the second terminal device in the form of text, voice, images, video, haptic alarms, etc., or any combination thereof. More information regarding instructions for guiding the target object can be found elsewhere in this application, for example, in Operation 1930 and its description.

[0369] In some embodiments, the terminal device may display an image along with one or more interactive elements. One or more interactive elements can be used to enable one or more interactions between the user (or target object) and the terminal device. For example, an interactive element may include one or more buttons, keys, and / or input boxes for the user to adjust or confirm the analysis results generated by the processing device 120. As another example, one or more interactive elements may include one or more image display options for the user to manipulate (e.g., zoom in, zoom out, add or modify annotations) the displayed image. As an example only, a user can manually adjust one or more parameters of the light field in a third image by adjusting the represented contour of the light field in the third image, for example, by dragging one or more contour lines representing the light field using a mouse or touchscreen.

[0370] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this disclosure. Various changes and modifications can be made by those skilled in the art based on the teachings of this disclosure. However, such changes and modifications do not depart from the scope of this disclosure. In some embodiments, one or more operations may be added or omitted. For example, at least one of the first display image, the second display image, the third display image, or the fourth display image may be transferred to a storage device (e.g., storage device 130) for storage.

[0371] Figure 20 This is a schematic diagram of an exemplary display image 2000 relating to a target object, according to some embodiments of this application. The chest of the target object can be scanned by a medical imaging device. Figure 20 As shown, the displayed image 2000 may include a representation 2010 of the target object, a representation 2020 of the detector of the medical imaging device (e.g., flat panel detector 440), at least two representations 2030 of the plurality of ionization chambers of the medical imaging device, and a representation 2040 of the light field in the medical imaging device.

[0372] In some embodiments, displaying image 2000 can be used to determine whether parameters of the target object and / or medical imaging device need adjustment. This is merely an example. Figure 20 As shown, the representation of Mitsuno 2040 covers the ROI corresponding to the target object (e.g., including the thoracic cavity, not in...). Figure 20 The target area shown in the diagram indicates that the target size of the optical field is suitable for scanning and requires no adjustment. The detector representation covers [area missing]. Figure 20 Nakamitsu's figure of 2040 indicates that the position of the detector does not need to be adjusted.

[0373] In some embodiments, displaying image 2000 can be used to select one or more target ionization chambers among a plurality of ionization chambers. For example... Figure 20 As shown, four ionization chambers are illustrated. The representations of three ionization chambers are covered by the target region, and the representation of one ionization chamber is not covered by the target region. In some embodiments, the processing device 120 can select a target ionization chamber from a plurality of ionization chambers based on the displayed image 2000. For example, the processing device 120 can select the ionization chamber closest to the center point of the ROI of the target object as a candidate ionization chamber. The processing device 120 can also determine whether the target region corresponding to the ROI in the displayed image 2000 covers the representation of the candidate ionization chamber. In response to determining that the representation of the candidate ionization chamber is covered by the target region, the processing device 120 can determine that the positional offset between the candidate ionization chamber and the ROI is negligible. The processing device 120 can also designate the candidate ionization chamber as the target ionization chamber corresponding to the ROI of the target object.

[0374] Alternatively, the processing device 120 may add annotations indicating candidate ionization chambers to the displayed image 2000 and / or use a different color than other ionization chambers in the displayed image 2000 to mark the representations of candidate ionization chambers. The displayed image 2000 may be displayed to a user via a display (e.g., display 320 of the mobile device 300). The user can determine whether a candidate ionization chamber should be designated as one of the target ionization chambers. In some embodiments, three ionization chambers represented in the displayed image 2000 that are covered by a target area corresponding to the ROI may be selected as candidate ionization chambers. The user may provide user input indicating the target ionization chamber to be selected from the candidate ionization chambers.

[0375] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the teachings of this application. However, such changes and modifications do not depart from the scope of this application. For example, the displayed image 2000 may further include other information related to the target object, such as the scanning imaging protocol.

[0376] Figure 21This is a flowchart illustrating an exemplary process for imaging a target object according to some embodiments of this application. In some embodiments, process 2100 may be performed in... Figure 1 This is implemented in the imaging system 100 shown. For example, process 2100 can be stored as instructions in a storage device (e.g., storage device 130, storage device 220, storage device 390) and processed by a processing device 120 (e.g., such as...). Figure 2 The processor 210 of the computing device 200 shown, such as Figure 3 The CPU 340 of the mobile device 300 shown is, for example Figure 7 The procedure 2100 may be invoked and / or executed by one or more modules shown. The operation of the procedure shown below is for illustrative purposes only. In some embodiments, procedure 2100 may be accomplished using one or more additional operations not described, and / or by omitting one or more operations discussed. Additionally, as Figure 21 The order of operations of process 2100 shown and described below is not intended to be restrictive.

[0377] In some embodiments, process 2100 may be performed during a scan of the ROI of the target object. In some embodiments, the ROI may include the lower limb or a portion of the lower limb of the target object. For example, the lower limb may include the foot, ankle, leg (e.g., calf and / or thigh), pelvis, etc., or any combination thereof.

[0378] In some embodiments, process 2100 can be implemented in a stitched scan of the target object. In the stitched scan of the target object, at least two ROIs of the target object can be scanned sequentially at least twice to obtain a stitched image of the ROIs. For illustrative purposes, the following description is made with reference to a stitched scan of a first ROI and a second ROI of the target object and is not intended to limit the scope of this application. The first and second ROIs can be two distinct regions that partially overlap each other or do not overlap at all. In the stitched scan, the first ROI can be scanned before the second ROI. By way of example only, the first ROI can be the chest of the target object, and the second ROI can be the lower limb (or a portion of the lower limb) of the target object. A stitched image corresponding to the chest and lower limb of the target object can be generated by the stitched scan.

[0379] In 2110, the processing device 120 (e.g., control module 730) can move the support device from the initial device position to the target device position.

[0380] In some embodiments, the support device may include, as elsewhere in this application (e.g., Figures 4A-4BThe processing device 120 describes the support components (e.g., support component 451), first drive components (e.g., first drive component 452), second drive components (e.g., second drive component 453), fixing components (e.g., fixing component 454), handles (e.g., handles 456), and backplates (e.g., backplates 455) as described in the description and related information. In some embodiments, prior to scanning (e.g., a first stitching scan), the processing device 120 may control the first drive components to move the support device from an initial device position to a target device position. The initial device position refers to the initial position of the support device before the target object is stitched scanned. For example, when the support device is not in use, it can be stored and / or charged at a preset position in the examination room, and this preset position can be considered the initial device position. The target device position refers to the position of the support device during the stitching scan of the target object. For example, during the stitching scan, the support device may be located near a medical imaging device, such as... Figure 4B As shown, a certain distance (e.g., 5 cm, 10 cm) is placed in front of the detector (e.g., flat panel detector 440) in the medical imaging device. In some embodiments, the support device may be fixed to the initial device position and / or the target device position by a fixing component.

[0381] In 2120, the processing device 120 (e.g., control module 730) can cause the support device to move the target object from the initial object position to the target object position (or the first position).

[0382] In some embodiments, prior to the first scan, the target object can be moved to the target object location so that the first region of interest (ROI) is positioned appropriately for the first scan. For example, when the target object is at the target object location, during the first scan, a radiation source in the medical imaging apparatus can emit a beam of radiation toward the first ROI, and a detector in the medical imaging apparatus (e.g., flat panel detector 440) can cover the entire first ROI of the target object. In some embodiments, after the first scan, the detector can be moved to another location so that the detector can cover the entire second ROI of the target object during a second scan. During both the first and second scans, the target object can be supported at the target object location. In some embodiments, the processing device 120 can determine the target object location based on a first region, a second region, the range of movement of the detector, the range of movement of the radiation source, the height of the target object, and any combination thereof.

[0383] In some embodiments, the target object location may be represented as the coordinates of a body point of the target object in a coordinate system (e.g., at the feet, head, or on a first ROI). This is merely an example. Figure 4AAs shown, the target object position can be represented as the Z-axis coordinate of the target object's foot in coordinate system 470. The target object position can be manually set by a user (e.g., a doctor, operator of a medical imaging device, etc.). For example, a user can manually input information about the target object position (e.g., the value of the vertical distance between the target object position and the floor of the examination room) via a terminal device. The support device can receive information about the target object position and set the target object position based on that information. Alternatively, the user can set the target object position by manually controlling the movement of the support device (e.g., using one or more buttons on the support device and / or the terminal device). Alternatively, the processing device 120 can determine the target object position based on image data from the target object.

[0384] For example, processing device 120 can acquire image data of a target object from an image capture device installed in an inspection chamber. Then, processing device 120 can generate an object model representing the target object based on the image data, and identify a first region corresponding to a first Region of Interest (ROI) from the object model. Further description of identifying the region corresponding to the ROI from the object model can be found elsewhere in this application (e.g., operation 1020 in process 1000 and its description). Alternatively, processing device 120 can identify the first and second regions from the raw image data or a target pose model of the target object.

[0385] In some embodiments, after moving the support device to the target device location, the processing device 120 may generate a first notification, which can be used to notify the target object to step onto the support device before the first scan. The first notification may be in the form of text, voice, image, video, tactile alarm, etc., or any combination thereof. The first notification may be output by a terminal device, for example, near the target object, the support device, or the medical imaging device. For example, the processing device 120 may cause the support device to output a voice notification of "Please step onto the support device".

[0386] In some embodiments, before the first scan and after the target object steps onto the support device, the processing device 120 can control the second drive component to move the target object from its initial position along the target direction to its current position. The initial position refers to the position of the target object after it steps onto the support device. For example, as... Figure 4A As shown, the target direction can be the Z-axis direction of coordinate system 470. The second drive component may include a lifting mechanism that can raise the target object to move the target object from its initial position to its current position.

[0387] Additionally or alternatively, the position of the handle of the support device can be adjusted before or after the target object steps onto the support device, so that the target object can place his / her hand on the handle when supported by the support device. The position of the handle can be manually set by a user (e.g., a doctor, operator of a medical imaging device, etc.). For example, the user can manually input information about the handle position (e.g., a value of the vertical distance between the handle and the ground) via a terminal device. The support device can receive the information about the handle and set the position of the handle based on the information about the handle position. Alternatively, the user can set the position of the handle by manually controlling the movement of the handle (e.g., using one or more buttons on the support device and / or the terminal device). Alternatively, the processing device 120 can determine the position of the handle based on image data of the target object, the scan position of the target object (e.g., the target object position), etc. For example, the processing device 120 can determine the distance from the handle to the support component of the support device as 2 / 3 of the height of the target object.

[0388] In 2130, the processing device 120 (e.g., control module 730) can enable the medical imaging device to perform a first scan of the first ROI of the target object. The target object can maintain an upright pose.

[0389] The upright posture can include standing, sitting, kneeling, etc. During the first scan, a support device (e.g., support device 460) can support the target object in the target object position. For example, the target object can stand, sit, or kneel on the support device to receive the first scan. In some embodiments, the medical imaging device (e.g., medical imaging device 110) can be an X-ray imaging device as described in other parts of this application (e.g., a suspended X-ray imaging device, a C-arm X-ray imaging device), a digital radiography (DR) device (e.g., a mobile digital X-ray imaging device), a CT device, etc.

[0390] In some embodiments, the processing device 120 may acquire one or more first scan parameters related to the first scan and perform a first scan on the ROI of the target object based on one or more first scan parameters. For example, one or more first scan parameters may include scan angle, radiation source position, scan stage position, scan stage tilt angle, detector position, gantry angle, field of view (FOV) size, collimator shape, radiation source current, radiation source voltage, etc., or any combination thereof.

[0391] In some embodiments, the processing device 120 may acquire parameter values ​​of scan parameters based on an imaging protocol associated with a first scan performed on a target object. For example, this protocol may be preset and stored in a storage device (e.g., storage device 130). Alternatively, at least a portion of the protocol may be manually determined by a user (e.g., an operator). In some embodiments, the processing device 120 may determine parameter values ​​of scan parameters based on image data associated with an examination room acquired by an image capture device installed in the examination room. For example, the image data may show a radiation source and / or detector in a medical imaging apparatus. The processing device 120 may determine the location of the radiation source and / or detector based on the image data.

[0392] In 2140, the processing device 120 (e.g., control module 730) can enable the medical imaging device to perform a second scan of the second ROI of the target object.

[0393] In some embodiments, after the first scan and before the second scan, the radiation source and / or detector can be moved to a suitable location for a second scan of the second ROI. The suitable location of the radiation source and / or detector can be determined based on image data captured by the image capture device. Further description of determining suitable locations for scanning a target object using active components in a medical imaging apparatus can be found elsewhere in this application (e.g., in...). Figure 10 The operation 1020 and its related description were found.

[0394] In some embodiments, after the first scan and before the second scan, the processing device 120 may control the second drive assembly to move the support device from a first position (e.g., the target object position during the first scan) to a second position. Additionally or alternatively, when the support device moves the target object from the first position to the second position, one or more active components of the medical imaging apparatus (e.g., detectors) may move in, for example, the target direction or the opposite direction. For example, when the support device moves the target object upward from the target object position to the second position, the detector (e.g., flat panel detector 440) may move downward to a suitable position.

[0395] In some embodiments, after the second scan, the processing device 120 may generate a second notification, which can be used to notify the target object to leave the support device. The second notification may be in the form of text, voice, image, video, tactile alarm, etc., or any combination thereof. The form of the second notification may be the same as or different from the form of the first notification. The second notification may be output by a terminal device, for example, near the target object, the support device, or the medical imaging device. For example, the processing device 120 may cause the support device to output a voice notification saying "Please leave the support device."

[0396] In some embodiments, after the second scan, the processing device 120 may control the first drive component to move the support device from the target device position back to the initial device position. For example, after the target object leaves the support device, the processing device 120 may control the first drive component to move the support device from the target device position back to the initial device position for charging.

[0397] In 2150, the processing device 120 (e.g., analysis module 720) can acquire first scan data and second scan data respectively associated with the first scan and the second scan.

[0398] The first and second scan data (also referred to as medical image data) may include projection data, one or more images generated based on the projection data, etc. In some embodiments, the processing device 120 may acquire the first and second scan data from a medical imaging apparatus. Alternatively, the first and second scan data may be acquired by the medical imaging apparatus and stored in a storage device (e.g., storage device 130, storage device 220, memory 390, or an external source). The processing device 120 may retrieve the first and second scan data from the storage device.

[0399] In 2160, the processing device 120 (e.g., analysis module 720) can generate images corresponding to the first ROI and the second ROI of the target object.

[0400] In some embodiments, the processing device 120 can generate image A corresponding to a first ROI based on first scan data and image B corresponding to a second ROI based on second scan data. The processing device 120 can also generate images corresponding to the first ROI and the second ROI based on images A and B. For example, the processing device 120 can generate images corresponding to the first ROI and the second ROI by stitching images A and B according to one or more image stitching algorithms. Exemplary image stitching algorithms may include image stitching algorithms based on normalized cross-correlation, image stitching algorithms based on mutual information, image stitching algorithms based on low-level features (e.g., image stitching algorithms based on Harris corner detectors, fast image stitching algorithms based on corner detectors, image stitching algorithms based on filter function detectors, image stitching algorithms based on surf feature detectors), contour-based image stitching algorithms, etc.

[0401] The above description of process 2100 is provided for illustrative purposes and is not intended to limit the scope of this application. In some embodiments, two or more Regions of Interest (ROIs) of a target object may be scanned according to a specific order in the stitching scan. Each pair of adjacent ROIs in the specific sequence may include an ROI scanned at a first time point and an ROI scanned at a second time point after the first time point. The ROI scanned at the first time point may be considered the first ROI, and the ROI scanned at the second time point may be considered the second ROI. Processing device 120 may perform process 2100 (or a portion thereof) for each pair of adjacent ROIs in the specific order. In some embodiments, one or more additional scans (e.g., a third scan, a fourth scan) may be performed on one or more other ROIs of the target object (e.g., a third ROI, a fourth ROI). A stitched image corresponding to the first ROI, the second ROI, and the other ROIs can be generated.

[0402] Compared to conventional stitching imaging procedures that require a user (e.g., a doctor) to determine at least two scanning positions (e.g., a first position, a second position) of the target object, the stitching imaging process disclosed in this application (e.g., process 2100) can be implemented with reduced or minimized or no user intervention, saving time and being more efficient and accurate. For example, the scanning position of the target object can be determined by analyzing image data in the target object instead of manual user intervention. Furthermore, the stitching imaging process disclosed herein can utilize a support device to achieve automatic positioning of the target object, for example, by automatically moving the target object to the target position and / or the second position. This allows for more accurate determination of the scanning position and more precise positioning of the target object to the scanning position, which in turn improves the efficiency and / or accuracy of the stitching scan of the target object. In addition, the position of the handle can be automatically determined based on the scanning position of the target object and / or the height of the target object, facilitating the target object's stepping onto and / or leaving the support device.

[0403] In some embodiments, one or more operations may be added or omitted. For example, an operation to determine the target object location may be added before operation 2120. As another example, the scan of the target object may be a non-stitched scan. In operation 2130, when the target object is supported at the target object location by a support device, the processing device 120 (e.g., control module 730) may perform a single scan of the first ROI of the target object. Based on the scan data acquired during the scanning process, an image may be generated. Operations 2140-2160 may be omitted. In some embodiments, two or more operations of process 2100 may be performed simultaneously or in any suitable order.

[0404] The basic concepts have been described thus, and it will be apparent to those skilled in the art, upon reading this detailed disclosure, that the foregoing detailed disclosure is intended to be illustrative only and not restrictive. Although not explicitly stated herein, various changes, modifications, and alterations may be made, and such changes, modifications, and alterations are intended to be made by those skilled in the art. These changes, modifications, and alterations are intended to be made as set forth in this disclosure and are within the spirit and scope of the exemplary embodiments of this disclosure.

[0405] Furthermore, certain terms have been used to describe embodiments of this disclosure. For example, the terms "one embodiment," "an embodiment," and / or "some embodiments" indicate that a particular feature, structure, or characteristic described in connection with that embodiment is included in at least one embodiment of this disclosure. Therefore, it should be emphasized and understood that two or more references to "one embodiment" or "an alternative embodiment" in various parts of this specification do not necessarily refer to the same embodiment. Additionally, specific features, structures, or characteristics may be appropriately combined in one or more embodiments of this disclosure.

[0406] Furthermore, those skilled in the art will recognize that various aspects of the disclosure herein can be described and illustrated in any of many patentable classes or environments, including any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof. Therefore, various aspects of this application can be implemented entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or a combination of software and hardware implementations, generally referred to herein collectively as a “unit,” “module,” or “system.” Furthermore, various aspects of this application can take the form of a computer program product containing computer-readable program code on one or more computer-readable media.

[0407] Computer-readable signal media may include, for example, a propagated data signal in baseband or as part of a carrier wave, having computer-readable program code embodied therein. Such propagated signals may take many forms, including electromagnetic, optical, and other suitable combinations. A computer-readable signal medium may be any computer-readable medium that is not a computer-readable storage medium and may communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable signal medium may be transmitted using any suitable medium, including wireless, wired, fiber optic cable, RF, or similar media, or any suitable combination thereof.

[0408] The computer program code used to perform the operations of various aspects of this application may be written using a combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C, and C++. The program code may reside entirely on the user's computer, partially on the user's computer, execute as a standalone software package, partially on the user's computer and partially on a remote computer, or execute entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or may be connected to an external computer (e.g., via the Internet through an Internet service provider) or provided in a cloud computing environment or as a service (e.g., Software as a Service (SaaS)).

[0409] Furthermore, the order of the processing elements or sequences stated, or the use of numbers, letters, or other names thereof, unless specified in the claims, are not intended to limit the claimed processes and methods to any particular order. Although the foregoing disclosure has discussed various useful embodiments currently considered to be part of this disclosure by way of various examples, it should be understood that such details are for this purpose only, and the appended claims are not limited to the disclosed embodiments, but rather are intended to cover modifications and equivalent arrangements within the spirit and scope of the disclosed embodiments. For example, while the implementation of the various components described above can be embodied in a hardware device, it can also be implemented as a purely software solution, such as an installation on an existing server or mobile device.

[0410] Similarly, it should be understood that in the foregoing description of embodiments of this disclosure, various features are sometimes combined in a single embodiment, drawing, or description thereof to simplify the disclosure and aid in understanding one or more of the various embodiments. However, the approach of this disclosure should not be construed as reflecting an intention that the claimed subject matter requires more features than expressly recited in each claim. Rather, the claimed subject matter may have fewer than all the features of a single foregoing embodiment.

Claims

1. A method for generating a target pose model of a target object, implemented on a computing device having one or more processors and one or more storage devices, the method comprising: In automatic scan preparation Obtain the image data of the target object; Generate an object model of the target object based on the image data; Obtain a reference pose model related to the target object; Obtain one or more reference pose parameters of the reference pose model, wherein the one or more reference pose parameters are a quantitative expression describing the pose of the reference pose model or the reference object; as well as Based on one or more reference pose parameters, the target pose model of the target object is generated by transforming the object model.

2. The method according to claim 1, characterized in that, The image data of the target object is acquired by an image capture device installed in the inspection room.

3. The method according to claim 1, characterized in that, The object model includes at least one of a two-dimensional (2D) skeleton model, a three-dimensional (3D) skeleton model, or a three-dimensional mesh model.

4. The method according to claim 1, characterized in that, The one or more reference pose parameters include: one or more positions of one or more feature points of the reference pose model.

5. The method according to claim 4, characterized in that, The one or more feature points correspond to one or more anatomical joints of the reference pose model or representative physical points of the body regions of the target object.

6. The method according to claim 1, characterized in that, Obtaining a reference pose model related to the target object includes: The reference pose model is obtained based on the imaging protocol of the target object.

7. The method according to claim 1, characterized in that, The reference pose of the reference pose model includes one of the following: head-forward supine position, feet-forward prone position, head-forward left-side horizontal position, and feet-forward right-side horizontal position.

8. A system for generating a target pose model of a target object, characterized in that, It includes at least one storage medium and at least one processor, the at least one storage medium being used to store computer instructions, and the at least one processor being used to execute the computer instructions to implement the method for generating a target pose model of a target object according to any one of claims 1 to 7.

Images