Imaging method, electronic device, and computer-readable storage medium

Abstract

The present application relates to an imaging method, an electronic device and a computer-readable storage medium. The method comprises: performing a three-dimensional CT scan on a scanned object in a preset position to obtain a reference three-dimensional image of the scanned object; after the internal information of the scanned object changes, performing a positioning image CT scan on the scanned object in a preset position to obtain a positioning image of the scanned object; based on at least the reference three-dimensional image and the positioning image, obtaining a three-dimensional image of the scanned object through a trained mathematical model. The present application solves the problem of high scanning dose when the existing CT imaging technology performs multiple imaging on the same part, and reduces the scanning dose required for CT imaging.

Description

Technical Field

[0001] The present application relates to the field of medical imaging, and in particular to an imaging method, an electronic device, and a computer-readable storage medium. Background Art

[0002] The principle of CT imaging is that a radiation source generates a radioactive beam to scan a layer of a certain thickness of the scanned object at different scanning angles. The detector receives the beam that passes through the layer, and based on the attenuation coefficient or absorption coefficient of the beam at different scanning angles, the grayscale value of each voxel is solved together to obtain a three-dimensional image of the scanned object.

[0003] When the same part needs to be imaged multiple times, such as interventional imaging or repeated scanning of the same lesion at different times, the CT scanning method used in the related art is to perform multiple CT scans on the interventional imaging area or lesion. Taking interventional imaging as an example, in the related art, the doctor first scans the pure tissue image when the interventional needle does not enter the field of view, and then operates the interventional needle into the tissue. The CT scans and reconstructs the image repeatedly to show the position of the interventional needle and guide the doctor to place the interventional needle in a specific position. This method of repeated CT scanning and reconstruction has no connection between each scan and reconstruction, and the scanning dose generated by the radiation source is large and the scanning time is long, resulting in long-term exposure of doctors and patients to the radiation field. Summary of the invention

[0004] In this embodiment, an imaging method, an electronic device, and a computer-readable storage medium are provided to solve the problem of high scanning dose when performing multiple imaging of the same part in the existing CT imaging technology.

[0005] In a first aspect, an imaging method is provided in this embodiment, comprising:

[0006] Performing a three-dimensional CT scan on the scanned object in a preset position to obtain a reference three-dimensional image of the scanned object;

[0007] After the internal information of the scanned object changes, performing a scout CT scan on the scanned object maintaining the preset body position to obtain a scout image of the scanned object;

[0008] Based on at least the reference three-dimensional image and the scout image, a three-dimensional image of the scanned object is acquired through a trained mathematical model.

[0009] In some of the embodiments, the mathematical model is trained using as input data a three-dimensional image obtained by performing a three-dimensional CT scan of the scanned object before the internal information changes and one or more two-dimensional images obtained by performing a positioning CT scan of the scanned object at different scanning angles after the internal information changes, and using as a supervised learning target a three-dimensional image of the scanned object performed by three-dimensional CT scanning after the internal information changes.

[0010] In some embodiments, the mathematical model includes model parameters; and obtaining the three-dimensional image of the scanned object through the trained mathematical model based on at least the reference three-dimensional image and the scout image includes:

[0011] Predicting information of target voxels corresponding to changed internal information in the scanned object based on the model parameters, the scout image and the reference three-dimensional image, wherein the model parameters are used to characterize a transformation relationship among the scout image, the reference three-dimensional image and the target voxels;

[0012] A three-dimensional image of the scanned object is acquired based on the reference three-dimensional image and the information of the target voxel.

[0013] In some of the embodiments, the imaging method is applied to interventional imaging, wherein the internal information of the scanned object changes as the position of the interventional needle in the body of the scanned object changes.

[0014] In some embodiments, the acquiring the three-dimensional image of the scanned object by using a trained mathematical model based on at least the reference three-dimensional image and the scout image includes:

[0015] Based on the reference three-dimensional image, the scout image and the prior information, a three-dimensional image of the scanned object is acquired through a trained mathematical model;

[0016] The prior information includes the surface position of the intervention point of the intervention needle on the scanned object and the movement orientation of the intervention needle.

[0017] In some of the embodiments, the mathematical model is trained using a three-dimensional image obtained by performing a three-dimensional CT scan of the scanned object before the internal information changes, a two-dimensional image obtained by performing a positioning CT scan of the scanned object after the internal information changes, the surface position of the intervention point of the intervention needle on the scanned object, and the movement direction of the intervention needle as input data, and the three-dimensional image of the scanned object after the internal information changes as a supervised learning target.

[0018] In some of the embodiments, the mathematical model is a deep learning model based on an artificial neural network.

[0019] In some of the embodiments, the three-dimensional image used as the supervised learning target is processed by removing the needle tip artifact.

[0020] In some of the embodiments, the method of acquiring the image used to train the mathematical model includes at least one of the following:

[0021] Acquire two three-dimensional images of the scanned object before and after the internal information actually acquired changes, and acquire a two-dimensional image as a locator image based on the three-dimensional image of the scanned object after the internal information changes;

[0022] Simulating the transmission process of CT scan rays in a preset digital phantom before the internal information changes, and reconstructing a reference three-dimensional image; simulating the process of the internal information changing in the preset digital phantom, and obtaining a three-dimensional image of the preset digital phantom and a two-dimensional image as a locator image after the internal information changes;

[0023] A three-dimensional image of the scanned object after the actual collected internal information has been changed is obtained, a two-dimensional image as a locator image is obtained by orthographic projection of the scanned object after the internal information has been changed, and the changed voxels in the three-dimensional image of the scanned object after the internal information has been changed are segmented and tissue repaired to obtain a three-dimensional image before the internal information has been changed.

[0024] In some embodiments, there are one or more locator images; when there are multiple locator images, each locator image corresponds to a different scanning angle.

[0025] In a second aspect, an electronic device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the imaging method described in the first aspect when executing the computer program.

[0026] According to a third aspect, a storage medium is provided in this embodiment, on which a computer program is stored, and when the program is executed by a processor, the imaging method described in the first aspect is implemented.

[0027] Compared with related technologies, the imaging method, electronic device and computer-readable storage medium provided in this embodiment solve the problem of high scanning dose when performing multiple imaging of the same part with existing CT imaging technology, and reduce the scanning dose required for CT imaging.

[0028] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0030] Figure 1 is a schematic diagram of an imaging system according to an embodiment of the present application.

[0031] Figure 2 is a schematic diagram of exemplary hardware and / or software components of an imaging system according to some embodiments of the present application.

[0032] Figure 3 is a schematic diagram of exemplary hardware and / or software components of a computer device 200 according to some embodiments of the present application.

[0033] Figure 4 is a flowchart of an exemplary process of an imaging method according to an embodiment of the present application.

[0034] Figure 5 It is a schematic diagram of a training method for a deep learning model according to an embodiment of the present application.

[0035] Figure 6 It is a schematic diagram of another training method for a deep learning model according to an embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0037] To more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. However, it should be understood by those of ordinary skill in the art that the present application can be implemented without these details. In some cases, in order to avoid unnecessary descriptions that make various aspects of the present application obscure, well-known methods, processes, systems, components and / or circuits that have been described at a higher level will not be described in detail. For those of ordinary skill in the art, it is obvious that various changes can be made to the embodiments disclosed in the present application, and without departing from the principles and scope of the present application, the general principles defined in the present application can be applied to other embodiments and application scenarios. Therefore, the present application is not limited to the embodiments shown, but conforms to the broadest scope consistent with the scope claimed for protection of the present application.

[0038] Unless otherwise defined, the technical terms or scientific terms involved in this application should have the general meaning understood by people with general skills in the technical field to which this application belongs. The terms used in this application are only for the purpose of describing specific embodiments, and are not intended to limit this application. Words such as "one", "a", "a kind of", "the", "these" and the like as used in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices.

[0039] The term "plurality" used in this application refers to two or more than two. Generally, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. used in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0040] The terms "system", "engine", "unit", "module" and / or "block" involved in the present application are a method for distinguishing different components, elements, parts, components, assemblies, or functions of different levels by level. These terms can be replaced by other expressions that can achieve the same purpose. Generally, the "module", "unit" or "block" involved in the present application refers to a collection of logic or software instructions embodied in hardware or firmware. The "module", "unit" or "block" described in the present application can be implemented as software and / or hardware, and in the case of being implemented as software, they can be stored in any type of non-volatile computer-readable storage medium or storage device.

[0041] In some embodiments, software modules / units / blocks can be compiled and linked into executable programs. It will be appreciated that software modules can be callable from other modules / units / blocks or from themselves, and / or can be called in response to detected events or interruptions. Software modules / units / blocks configured to be executed on a computing device can be arranged on a computer-readable storage medium, such as a compact disc, a digital video disc, a flash drive, a 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 codes can be stored in part or in whole on the storage device of the computing device being executed, and applied to the operation of the computing device. Software instructions can be embedded in firmware, such as an EPROM. It will also be appreciated that hardware modules / units / blocks can be included in connected logical components, such as gates and triggers, 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, and can also be represented in hardware or firmware. Generally, the modules / units / blocks described herein may be combined with other modules / units / blocks, or may be divided into sub-modules / sub-units / sub-blocks, although they are physically organized or stored. The description may apply to a system, an engine, or a portion thereof.

[0042] 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, coupled, or in communication 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 relevant listed items or combinations thereof.

[0043] The term "image" in this application is used to collectively refer to image data (e.g., scan data, projection data) and / or various forms of images, including two-dimensional (2D) images, three-dimensional (3D) images, etc. The terms "pixel" and "voxel" in this application are used interchangeably to refer to elements of an image. In this application, the terms "region", "position" and "area" may refer to the location of an anatomical structure shown in an image, or to the actual location of an anatomical structure present in or on a target object. Thus, an image may indicate the actual location of certain anatomical structures present in or on a target object.

[0044] This embodiment provides an imaging method. According to the imaging method provided by this embodiment, low-dose CT imaging can be achieved, thereby avoiding excessive exposure of doctors or patients to the radiation field. Figure 1An imaging system according to an embodiment of the present application is used to implement an imaging method.

[0045] like Figure 1 As shown, the imaging system may include a scanning device 110, a processing device 120, and a storage device 130. In some embodiments, one or more terminals 140 and / or a network 150 may also be included.

[0046] In some embodiments, the scanning device 110, the processing device 120, the storage device 130 and / or the terminal 140 may be directly connected to each other, or connected via a wireless network or a wired network. For example, the scanning device 110 may be directly connected to the processing device 120 via the network 150 or without the network. For another example, the storage device 130 may be directly connected to the processing device 120 via the network 150 or without the network.

[0047] The scanning device 110 can generate or provide image data related to the target object by scanning the target object. The scanning device 110 may include a single-modality scanner and / or a multi-modality scanner. The single-modality scanner may include, for example, a computed tomography (CT) scanner. The multi-modality scanner may include, for example, a single-photon emission computed tomography-magnetic resonance imaging (SPECT-MRI) scanner, a positron emission tomography-computed tomography (PETCT) scanner, etc.

[0048] In some embodiments, the scanning device 110 may include a frame 111 having a detection area 113, a scanning assembly, and a scanning bed 114. The scanning assembly may include: a detector 112 and a radiation source 115. The frame 111 may support the detector 112 and the radiation source 115. The target object may be placed on the scanning bed 114 and then moved to the detection area 113 for scanning. In some embodiments, the scanning bed 114 may be configured to rotate and / or translate in different directions to move the target object to a desired position. For example, the scanning bed 114 may be configured to rotate along or around Figure 1One or more of the X-axis, Y-axis and Z-axis of the coordinate system 170 shown are translated or rotated. The radiation source 115 can emit radioactive rays to the target object. The radioactive rays may include particle rays, photon rays, etc. or a combination thereof. In some embodiments, the radioactive rays may include at least two radioactive particles (e.g., neutrons, protons, electrons, muons, heavy ions), at least two radioactive photons (e.g., X-rays, gamma rays, ultraviolet rays, lasers), etc., or a combination thereof. The detector 112 can 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. The detector unit may include a scintillation detector (e.g., a cesium iodide detector) or a gas detector. The detector unit may be a single-row detector or a multi-row detector.

[0049] The processing device 120 can process data and / or information obtained from the scanning device 110, the storage device 130 and / or the terminal 140, and implement control of the scanning device 110, the storage device 130 and / or the terminal 140. For example, the processing device 120 can implement control of the imaging system to implement the imaging method provided in the present application.

[0050] In some embodiments, the processing device 120 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processing device 120 may be local or remote to the imaging system. In some embodiments, the processing device 120 may be composed of one or more servers such as Figure 2 The components described are implemented by the computer device 200 .

[0051] 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, etc., or any combination thereof.

[0052] Storage device 130 may store data, instructions, and / or any other information. In some embodiments, storage device 130 may store data acquired from processing device 120, terminal 140, and / or scanning device 110. In some embodiments, storage device 130 may store data and / or instructions that may be executed or used by processing device 120 to perform the exemplary methods described in this application.

[0053] In some embodiments, storage device 130 may be connected to network 150 to communicate with one or more other components of the imaging system (e.g., processing device 120, terminal 140). One or more components of the imaging system 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.

[0054] Terminal 140 can enable interaction between a user and an imaging system. For example, terminal 140 can display a target image of a target object having at least two annotations of at least two regions of the target object. For another example, terminal 140 can display a virtual scan performed using a virtual imaging system. In some embodiments, terminal 140 can include a mobile device, a tablet computer, a laptop computer, etc., or any combination thereof. For example, the mobile device can include a mobile phone, a personal digital assistant (PDA), a gaming device, a navigation device, a point of sale (POS) device, a laptop computer, a tablet computer, a desktop computer, etc., or any combination thereof. In some embodiments, terminal 140 can include an input device, an output device, etc. In some embodiments, terminal 140 can be part of processing device 120.

[0055] The network 150 may include any suitable network that can facilitate the exchange of information and / or data of the imaging system. In some embodiments, one or more components of the imaging system (e.g., the scanning device 110, the processing device 120, the storage device 130, the terminal 140) can communicate information and / or data with one or more other components of the imaging system via the network 150. For example, the processing device 120 can obtain medical image data from the scanning device 110 via the network 150. For another example, the processing device 120 can obtain user instructions from the terminal 140 via the network 150.

[0056] The network 150 may be or include a public network (e.g., the Internet), a private network (e.g., a local area network (LAN)), a wired network, a wireless network (e.g., an 802.11 network, a Wi-Fi network), a frame relay network, a virtual private network (VPN), a satellite network, a telephone network, a router, a hub, a switch, a server computer, and / or any combination thereof. For example, the network 150 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, a near field communication (NFC) network, etc., or any combination thereof. In some embodiments, the network 150 may include one or more network access points. For example, the network 150 may include a wired and / or wireless network access point such as a base station and / or an Internet exchange point, through which one or more components of the imaging system may be connected to the network 150 to exchange data and / or information.

[0057] It should be noted that the above description of the imaging system is intended to be illustrative, not to limit the scope of the present application. Many alternatives, modifications, and variations will be apparent to those of ordinary skill in the art. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and / or alternative exemplary embodiments. For example, the imaging system may include one or more additional components. Additionally or alternatively, one or more components of the imaging system, such as the network 150 described above, may be omitted. For another example, two or more components of the imaging system may be integrated into a single component. In some embodiments, the imaging system may further include a therapeutic device, such as a radiotherapy device.

[0058] Figure 2 is a schematic diagram of exemplary hardware and / or software components of an imaging system according to some embodiments of the present application. Figure 2 As shown, the imaging system includes: a scanning device 110 and a processing device 120 .

[0059] The scanning device 110 is used to perform a three-dimensional CT scan on the scanned object maintaining a preset position, and to perform a positioning image CT scan on the scanned object maintaining a preset position after the internal information of the scanned object changes.

[0060] The processing device 120 is used to obtain a reference three-dimensional image of the scanned object based on the data obtained by the three-dimensional CT scanning, obtain a positioning image of the scanned object based on the data obtained by the positioning image CT scanning, and obtain a three-dimensional image of the scanned object through a trained mathematical model based on at least the positioning image and the reference three-dimensional image.

[0061] Figure 3 2 is a schematic diagram of exemplary hardware and / or software components of a computer device 200 according to some embodiments of the present application. As described herein, the computer device 200 may be used to implement any component of the imaging system. For example, the processing device 120 and / or the terminal 140 may be implemented on the computer device 200 through its hardware, software program, firmware, or a combination thereof, respectively. Although only one such computing device is shown, for convenience, the computer functions related to the imaging system described herein may be implemented in a distributed manner on multiple similar platforms to distribute the processing load. Figure 3 As shown, computer device 200 may include processor 210 , memory 220 , input / output (I / O) 230 , and communication port 240 .

[0062] The processor 210 can execute computer instructions (e.g., program code) and perform the functions of the processing device 120 according to the techniques described herein. Computer instructions may include, for example, routines, programs, objects, components, data structures, processes, modules, and functions that perform specific functions described herein. For example, the processor 210 can process image data obtained from the scanning device 110, the terminal 140, the storage device 130, and / or any other component of the imaging system. In some embodiments, the processor 210 may include one or more hardware processors, such as a microcontroller, a microprocessor, a reduced instruction set computer (RISC), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a central processing unit (CPU), a graphics processing unit (GPU), a physical operation processing unit (PPU), a microcontroller unit, a digital signal processor (DSP), a field programmable gate array (FPGA), an advanced RISC machine (ARM), a programmable logic device (PLD), and any circuits and processors capable of performing one or more functions, or any combination thereof.

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

[0064] The memory 220 may store data / information obtained from the scanning device 110, the terminal 140, the storage device 130, and / or any other component of the imaging system. In some embodiments, the memory 220 may include a mass storage device, a removable storage device, a volatile read-write memory, a read-only memory (ROM), etc., or any combination thereof. In some embodiments, the memory 220 may store one or more programs and / or instructions to perform the exemplary methods described in the present application. For example, the memory 220 may store a program for execution by the processing device 120 of the imaging system to perform automatic scan preparation for a scan to be performed on a target object. For another example, the memory 220 may store a program for execution by the processing device 120 during the scanning of the target object to perform real-time monitoring and / or adjustment operations.

[0065] I / O 230 can input and / or output signals, data, information, etc. In some embodiments, I / O 230 can implement user interaction with processing device 120. In some embodiments, I / O 230 can include input devices and output devices. Input devices can include letters and other keys input through a keyboard, a touch screen (e.g., with tactile input or tactile feedback), voice input, eye tracking input, a brain monitoring system, or any other similar input mechanism. Input information received by the input device can be transmitted to another component (e.g., processing device 120) through, for example, a bus for further processing. Other types of input devices can include cursor control devices, such as a mouse, a trackball, or cursor direction keys, etc. Output devices can include displays (e.g., liquid crystal displays (LCDs), displays based on light emitting diodes (LEDs), flat backplane displays, curved screens, television devices, cathode ray tubes (CRTs), touch screens), speakers, printers, etc., or combinations thereof.

[0066] The communication port 240 can be connected to a network (e.g., network 150) to facilitate data communication. The communication port 240 can establish a connection between the processing device 120 and the scanning device 110, the terminal 140 and / or the storage device 130. The connection can be a wired connection, a wireless connection, any other communication connection that can realize data transmission and / or reception, and / or a combination of these connections. The wired connection may include, for example, an electric cable, an optical cable, a telephone line, etc., or any combination thereof. The wireless connection may include, for example, a Bluetooth connection, a Wi-Fi connection, a WiMax connection, a WLAN connection, a Zigbee connection, a mobile network connection (e.g., 3G, 4G, 5G), etc., or a combination thereof. In some embodiments, the communication port 240 may be and / or include a standardized communication port, such as RS232, RS485, etc. In some embodiments, the communication port 240 may be a specially designed communication port.

[0067] For example, the communication port 240 may be designed according to the Digital Imaging and Communications in Medicine (DICOM) protocol.

[0068] In order to implement the various modules, units and functions described in this application, a computer hardware platform can be used as a hardware platform for one or more components described herein. A computer with a user interface component can be used to implement a personal computer (PC) or any other type of workstation or terminal device. If the computer is properly programmed, the computer can also be used as a server.

[0069] Figure 4 is a flow chart of an exemplary process of an imaging method according to an embodiment of the present application, such as Figure 4 As shown, the process of the imaging method includes the following steps:

[0070] Step S401 , performing a three-dimensional CT scan on a scanned object in a preset posture to obtain a reference three-dimensional image of the scanned object.

[0071] Step S402: after the internal information of the scanned object changes, a scout CT scan is performed on the scanned object in a preset position to obtain a scout image of the scanned object.

[0072] Step S403: Based on at least the reference three-dimensional image and the positioning image, a three-dimensional image of the scanned object is acquired through a trained mathematical model.

[0073] The principle of CT imaging is that a radioactive beam is generated by a radiation source to scan a layer of a certain thickness of the scanned object at different scanning angles, and the detector receives the beam that passes through the layer. Based on the attenuation coefficient or absorption coefficient of the beam at different scanning angles, the grayscale value of each voxel is solved together to obtain a three-dimensional image of the scanned object. The above-mentioned three-dimensional CT scanning includes but is not limited to spiral CT scanning and axial CT scanning. However, in traditional three-dimensional CT scanning, whether spiral CT scanning or axial CT scanning is used, the scanning dose generated by the radiation source needs to be larger and the scanning time is longer than that of the positioning image CT scanning. Especially in the case where a body part needs to be continuously scanned to present a real-time scanning image, or a body part is repeatedly examined, the direct use of the three-dimensional CT scanning method will cause the doctor and the patient to be exposed to the radiation field for a long time. For this reason, in the above embodiment, a reference three-dimensional image scan is performed on the scanned object for a small number of times (at least once), and in the subsequent continuous scanning or repeated examination, the positioning image of the scanned object is obtained by the positioning image CT scanning method, thereby reducing the scanning dose and reducing the scanning time. After obtaining the reference three-dimensional image and the positioning image, the information of the target voxels corresponding to the changed internal information in the scanned object is predicted by combining the prior information obtained in advance for characterizing the transformation relationship among the positioning image, the reference three-dimensional image and the target voxels, thereby obtaining a real-time three-dimensional image of the scanned object.

[0074] In the above step S402, the internal information of the scanned object changes. For example, the properties of the scanned object itself may change over time, or the scanned object may be interfered with by external objects, resulting in changes in its internal information.

[0075] For example, the imaging method of this embodiment can be used for interventional imaging. Interventional imaging refers to using CT imaging as a guiding tool for the interventional needle to guide the interventional needle to a specified position inside the scanned object. During the interventional imaging process, if the position of the interventional needle in the scanned object changes, the internal information of the scanned object will also change accordingly, and the target voxel is the voxel of the interventional needle. By using the above-mentioned imaging method in interventional imaging, after a larger dose and longer time of three-dimensional CT imaging, a smaller dose and shorter time of positioning CT scanning can be used to predict the position of the interventional needle, thereby reducing the risks for doctors and patients. During the interventional imaging process, the imaging speed is required to be as fast as possible or even real-time imaging, so as to guide the doctor's interventional operation; using the above-mentioned method for interventional imaging has the beneficial effects of fast imaging speed and real-time imaging.

[0076] For another example, the imaging method of this embodiment can be used for repeated examinations. Repeated examinations refer to re-scanning and imaging the same location after a certain period of time in order to track changes in the patient's site after the first three-dimensional CT imaging. For example, the patient's site may be a tumor, inflammation, or other lesions that may change at the same examination location. During the repeated examination, the body position of the scanned object will remain consistent with the body position of the first scan. During the repeated examination, a smaller dose and shorter time positioning CT scan is used to obtain a two-dimensional positioning image. Thereafter, the current three-dimensional image is predicted based on the baseline three-dimensional image obtained in the first examination, the positioning image obtained by the new scan, and the prior information, thereby reducing the risks for doctors and patients.

[0077] Specifically, when a patient's part is repeatedly examined to monitor tumor progression, it includes: first obtaining a baseline 3D image through 3D CT imaging, and when monitoring the tumor progression of the same location again, only the 2D image of the locator CT scan is used, and the current 3D image is obtained by combining the baseline 3D image obtained in the first examination, the locator image obtained by the new scan, and the prior information prediction. Of course, this type of detection is not only used for tumor progression, but can also be used for incremental and progressive examinations such as inflammation and fracture recovery.

[0078] The scout image CT scan is a two-dimensional image obtained by scanning when the radiation source tube and the detector are stationary and the scanning bed is moving. It is similar to the two-dimensional image obtained by projecting a three-dimensional image onto a plane. Therefore, the changes in the information inside the scanned object will also be reflected in the scout image. Combined with the projection relationship between the reference three-dimensional image and the scout image, it is possible to know which voxels have changed the information inside the scanned object and how the grayscale values ​​of these voxels change.

[0079] In some embodiments, there are one or more locator images. When there are multiple locator images, the scanning angle (i.e., the position of the tube) corresponding to each locator image is different. Preferably, when there are multiple locator images, the locator images include an anteroposterior locator image and a lateral locator image. Each locator image is used to predict the position and grayscale value of voxels whose information inside the scanned object has changed in a series of mutually parallel planes.

[0080] In other embodiments, when performing interventional imaging, the locator image may be at least one locator image. In order to more accurately predict the information of the target voxel, the above-mentioned prior information may include the surface position of the intervention point of the intervention needle on the scanned object, and the movement direction of the intervention needle. Wherein, the radiation source tube and the detector are not in the movement direction of the intervention needle or the opposite direction, so that the movement direction of the intervention needle is not perpendicular to the imaging plane of the locator image, so as to obtain more information of the voxels that have changed inside the scanned object.

[0081] In some embodiments, the implementation process of step S403 also includes the following steps: the mathematical model includes model parameters, and the information of the target voxels corresponding to the changed internal information in the scanned object is predicted based on the model parameters, the positioning image and the reference three-dimensional image, wherein the model parameters are used to characterize the transformation relationship between the positioning image, the reference three-dimensional image and the target voxels; based on the reference three-dimensional image and the information of the target voxels, a three-dimensional image of the scanned object is acquired.

[0082] The above mathematical models include but are not limited to shallow machine learning models or deep learning models based on artificial neural networks. Compared with shallow machine learning models, the use of deep learning models based on artificial neural networks in the above imaging methods is conducive to the deep learning model learning more information about model parameters, thereby obtaining more accurate information about target voxels based on the information about these model parameters. For example, a locator image represents the projection of a three-dimensional image on a two-dimensional plane, and the information in the projection direction is missing.

[0083] refer to Figure 5 When a deep learning model is used for supervised learning, a three-dimensional image obtained by performing a three-dimensional CT scan of the scanned object before the internal information changes and one or more two-dimensional images obtained by performing a positioning CT scan of the scanned object at different scanning angles after the internal information changes are used as input data, and the three-dimensional image of the scanned object after the internal information changes is used as a supervised learning target, so that the information of the model parameters learned by the deep learning model can be richer. When the parameters of the deep learning model converge, the deep learning model is sufficient to predict the information of the target voxel based on the reference three-dimensional image and the corresponding positioning image, thereby obtaining a real-time three-dimensional image of the scanned object based on the information of the reference three-dimensional image and the target voxel.

[0084] refer to Figure 6When a deep learning model is used for supervised learning, a three-dimensional image obtained by performing a three-dimensional CT scan of the scanned object before the internal information changes, a two-dimensional image obtained by performing a positioning CT scan of the scanned object after the internal information changes, the surface position of the intervention point of the intervention needle on the scanned object, and the movement orientation of the intervention needle are used as input data, and the three-dimensional image of the scanned object after the internal information changes is used as a supervised learning target, so that the information of the model parameters learned by the deep learning model also includes the initial intervention point position and initial movement orientation information related to the intervention needle. Based on this information, when the parameters of the deep learning model converge, the deep learning model is sufficient to predict the information of the target voxel based on the reference three-dimensional image, the positioning image, the initial position of the intervention point of the intervention needle, and the initial movement orientation, thereby obtaining a real-time three-dimensional image of the scanned object based on the reference three-dimensional image and the information of the target voxel.

[0085] The three-dimensional CT scanning and reconstruction methods in the related art are used for interventional imaging, and the interventional needles in the obtained three-dimensional images often have serious hardening artifacts, which makes it difficult to judge the needle tip of the interventional needle. In order to reduce or eliminate artifacts, a dedicated artifact removal function can be used, but the use of the artifact removal function in real-time three-dimensional scanning imaging has a large impact on the reconstruction speed, and the real-time needle tip artifact removal effect is generally poor. For interventional imaging using the imaging method provided in this embodiment, on the one hand, since the baseline three-dimensional image does not have a needle tip image; on the other hand, the three-dimensional image used as the supervised learning target in the deep learning model can be processed offline for needle tip artifact removal, so that the target voxels predicted by the deep learning model after parameter convergence are not affected by artifacts, thereby obtaining a real-time three-dimensional image with almost no needle tip artifacts.

[0086] Figure 5 and Figure 6 In the present invention, the three-dimensional image obtained by performing a three-dimensional CT scan on the scanned object before the internal information changes, the two-dimensional image obtained by performing a positioning image CT scan on the scanned object after the internal information changes, and the three-dimensional image of the scanned object after the internal information changes can be obtained in a variety of ways:

[0087] Method 1: obtain two 3D images of the scanned object before and after the internal information of the scanned object changes, and pre-process the 3D image of the scanned object after the internal information changes (for example, cropping, removing needle tip artifacts, etc.); then obtain a 2D image as a locator image based on the 3D image of the scanned object after the internal information changes. This method can make full use of the existing 3D images that are actually collected.

[0088] Method 2: Preset a digital phantom, simulate the transmission process of CT scan rays in the preset digital phantom before the internal information changes, and reconstruct a reference 3D image; simulate the process of internal information change in the preset digital phantom (such as the process of an interventional needle entering the digital phantom), and obtain a 3D image of the digital phantom after the internal information changes and a 2D image as a positioning image. This method can simulate and obtain a large amount of training data in a short time, and the training data can be highly customized, such as customizing the size and material of the interventional needle, so as to obtain a more specialized deep learning model.

[0089] Method 3: Acquire the three-dimensional image of the scanned object after the internal information has changed, perform orthographic projection on the scanned object after the internal information has changed to obtain a two-dimensional image as a locator image, and then perform segmentation and tissue repair on the changed voxels in the three-dimensional image of the scanned object after the internal information has changed, such as interpolation, to obtain the three-dimensional image before the internal information has changed. Since the three-dimensional image of the scanned object after the internal information has changed is the easiest to obtain, while the three-dimensional image before the internal information has changed is relatively rare, this method can make full use of the diagnostic images for which the three-dimensional image before the internal information has changed has not been acquired.

[0090] In summary, through the above-mentioned embodiments or preferred embodiments, the prediction of real-time three-dimensional images based on the reference three-dimensional images and the positioning images can not only improve the imaging speed and reduce the safety hazards of doctors and patients exposed to the radiation field, but also more efficiently obtain real-time three-dimensional images without needle tip artifacts.

[0091] In this embodiment, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned imaging method are implemented.

[0092] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0093] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0094] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0095] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. An imaging method, comprising: Performing a three-dimensional CT scan on the scanned object in a preset position to obtain a reference three-dimensional image of the scanned object; After the internal information of the scanned object changes, performing a scout CT scan on the scanned object maintaining the preset body position to obtain a scout image of the scanned object; Based on at least the reference three-dimensional image and the scout image, acquiring a three-dimensional image of the scanned object through a trained mathematical model; The step of acquiring the three-dimensional image of the scanned object by using a trained mathematical model based on at least the reference three-dimensional image and the scout image comprises: Based on the reference three-dimensional image, the scout image and the prior information, a three-dimensional image of the scanned object is acquired through a trained mathematical model.

2. The imaging method according to claim 1, characterized in that: The mathematical model is trained using as input data a three-dimensional image obtained by performing a three-dimensional CT scan on the scanned object before the internal information changes and one or more two-dimensional images obtained by performing a positioning CT scan on the scanned object at different scanning angles after the internal information changes, and using the three-dimensional image of the three-dimensional CT scan of the scanned object after the internal information changes as a supervised learning target.

3. The imaging method according to claim 1, characterized in that: The imaging method is applied to interventional imaging, wherein the internal information of the scanned object changes as the position of the interventional needle in the body of the scanned object changes.

4. The imaging method according to claim 3, characterized in that: The prior information includes the surface position of the intervention point of the intervention needle on the scanned object and the orientation of the intervention needle.

5. The imaging method according to claim 4, characterized in that: The mathematical model is trained using a three-dimensional image obtained by performing a three-dimensional CT scan of the scanned object before the internal information changes, a two-dimensional image obtained by performing a positioning CT scan of the scanned object after the internal information changes, the surface position of the intervention point of the intervention needle on the scanned object, and the movement direction of the intervention needle as input data, and using the three-dimensional image of the scanned object after the internal information changes as a supervised learning target.

6. The imaging method according to claim 2 or 5, characterized in that: The mathematical model is a deep learning model based on artificial neural network.

7. The imaging method according to claim 2 or 5, characterized in that: The 3D images used as supervised learning targets were processed with needle tip artifact removal.

8. The imaging method according to claim 2 or 5, characterized in that: The method of acquiring the image used to train the mathematical model includes at least one of the following: Acquire two three-dimensional images of the scanned object before and after the internal information actually acquired changes, and acquire a two-dimensional image as a locator image based on the three-dimensional image of the scanned object after the internal information changes; Simulating the transmission process of CT scan rays in a preset digital phantom before the internal information changes, and reconstructing a reference three-dimensional image; simulating the process of the internal information changing in the preset digital phantom, and obtaining a three-dimensional image of the preset digital phantom and a two-dimensional image as a locator image after the internal information changes; A three-dimensional image of the scanned object after the actual collected internal information has been changed is obtained, a two-dimensional image as a locator image is obtained by orthographic projection of the scanned object after the internal information has been changed, and the changed voxels in the three-dimensional image of the scanned object after the internal information has been changed are segmented and tissue repaired to obtain a three-dimensional image before the internal information has been changed.

9. The imaging method according to claim 1, characterized in that: There are one or more locator images; when there are multiple locator images, the scanning angles corresponding to the locator images are different.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the steps of the imaging method according to any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the imaging method according to any one of claims 1 to 9 are implemented.

Images