A positron emission tomography imaging method and system

Abstract

Embodiments of the present specification provide a positron emission tomography (PET) imaging system and method. The method includes: acquiring scan data of an object collected by positron emission tomography in a scan time period (410); determining a plurality of target scan data sets from the scan data based on a preset condition, wherein each of the plurality of target scan data sets corresponds to a target sub-time period in the scan time period (420); generating one or more intermediate images corresponding to one or more sub-time periods different from the plurality of target sub-time periods in the scan time period based on the plurality of target scan data sets (430); and generating a target image sequence of the object based on the plurality of target scan data sets and the one or more intermediate images (440).

Description

Technical Field

[0001] This specification relates to medical imaging technology, and in particular to a positron emission tomography (PET) imaging method and system. Background Technology

[0002] In recent years, positron emission tomography (PET) imaging has been widely used in clinical examinations and disease diagnosis. In particular, dynamic PET imaging can acquire a set of images during a dynamic scan, and dynamic PET data can also provide rich information related to physiological parameters (e.g., perfusion pressure), which can reveal the functional state of the imaged tissue or organ. However, dynamic PET imaging typically requires relatively long scan times and relatively long image reconstruction times, and the image quality is also relatively low. Therefore, it is desirable to propose a PET imaging system and method that can improve imaging efficiency and image quality. Summary of the Invention

[0003] One aspect of this specification provides a positron emission tomography (PET) imaging system. The PET imaging system includes: at least one storage device including an instruction set for medical imaging; and at least one processor communicating with the at least one storage device, wherein, when the instruction set is executed, the at least one processor is configured to control the system to perform operations including: acquiring scan data of an object collected by PET scanning within a scan time period; determining a plurality of target scan datasets from the scan data based on preset conditions, wherein each of the plurality of target scan datasets corresponds to a target sub-time period within the scan time period; generating one or more intermediate images corresponding to one or more sub-time periods different from the plurality of target sub-time periods within the scan time period based on the plurality of target scan datasets; and generating a target image sequence of the object based on the plurality of target scan datasets and the one or more intermediate images.

[0004] In some embodiments, in order to determine multiple target scan datasets from the scan data based on preset conditions, the system may perform the following operations: dividing the scan data into multiple candidate scan datasets; for each of the multiple candidate scan datasets, determining a three-dimensional (3D) count distribution map corresponding to the candidate scan dataset, wherein the three-dimensional count distribution map includes at least one pixel, and each pixel corresponds to a pixel value representing a coincidence event count associated with the pixel; and determining the multiple target scan datasets based on the multiple three-dimensional count distribution maps corresponding to the multiple candidate scan datasets respectively.

[0005] In some embodiments, in order to determine the plurality of target scan datasets based on the plurality of three-dimensional count distribution maps corresponding to the plurality of candidate scan datasets respectively, the system may perform the following operations: arranging the plurality of three-dimensional count distribution maps in chronological order to form a map sequence; and determining the plurality of target scan datasets by traversing the map sequence starting from the first three-dimensional count distribution map in the map sequence, wherein traversing the map sequence starting from the first three-dimensional count distribution map includes: sequentially determining the difference between the latest three-dimensional count distribution map corresponding to the latest determined target scan dataset and each three-dimensional count distribution map in the map sequence located after the latest three-dimensional count distribution map, until the difference between the latest three-dimensional count distribution map and a three-dimensional count distribution map located after the latest three-dimensional count distribution map is greater than or equal to a preset threshold, and determining the candidate scan dataset corresponding to the three-dimensional count distribution map as the target scan dataset.

[0006] In some embodiments, in order to determine multiple target scan datasets from the scan data based on preset conditions, the system may perform the following operations: acquire the time-radioactivity curve of the tracer in the positron emission tomography scan; and determine the multiple target scan datasets from the scan data based on the time-radioactivity curve.

[0007] In some embodiments, in order to determine multiple target scan datasets from the scan data based on preset conditions, the system may perform the following operations: acquire the vital signals of the objects corresponding to the scan data; and determine the multiple target scan datasets from the scan data based on the vital signals.

[0008] In some embodiments, in order to generate one or more intermediate images corresponding to one or more sub-time periods that are different from the multiple target sub-time periods in the scanning time period, the system may perform the following operations: generate multiple target images corresponding to the multiple target scanning datasets respectively; and generate the one or more intermediate images based on the multiple target images.

[0009] In some embodiments, in order to generate multiple target images corresponding to the multiple target scanning datasets respectively, the system may perform the following operations: determine multiple initial images corresponding to the multiple target scanning datasets respectively; and determine the multiple target images by performing a denoising operation on the multiple initial images using a denoising model and / or performing a resolution improvement operation on the multiple initial images using a resolution improvement model.

[0010] In some embodiments, in order to generate one or more intermediate images corresponding to one or more sub-time periods that are different from the plurality of target sub-time periods in the scanning time period, the system may perform the following operations: for each of the one or more target image pairs formed by the plurality of target images, using a motion field generation model to determine the motion field between the images within the target image pair; and using an image generation model to generate the one or more intermediate images corresponding to the target image pair based on the motion field.

[0011] In some embodiments, the sports field generation model and the image generation model are integrated into a single model.

[0012] In some embodiments, in order to generate a target image sequence of the object based on the plurality of target scan datasets and the one or more intermediate images, the system may perform the following operations: for each of one or more image pairs formed by the plurality of target images and the one or more intermediate images, using the motion field generation model to determine a secondary motion field between the images within the image pair; and using the image generation model to generate one or more secondary intermediate images corresponding to the image pair based on the secondary motion field; and generating the target image sequence of the object based on the plurality of target images, the one or more intermediate images, and the one or more secondary intermediate images.

[0013] In some embodiments, the difference between images within the image pair is greater than a preset difference threshold.

[0014] Another aspect of this specification provides a positron emission tomography (PET) imaging method. The PET imaging method includes: acquiring scan data of an object collected by PET scanning within a scan time period; determining multiple target scan datasets from the scan data based on preset conditions, wherein each of the multiple target scan datasets corresponds to a target sub-time period within the scan time period; generating one or more intermediate images corresponding to one or more sub-time periods different from the multiple target sub-time periods within the scan time period based on the multiple target scan datasets; and generating a target image sequence of the object based on the multiple target scan datasets and the one or more intermediate images.

[0015] Another aspect of this specification provides a positron emission tomography (PET) imaging system. The PET imaging system includes an acquisition module, a determination module, and a generation module. The acquisition module acquires scan data of an object collected via PET scanning within a scan time period. The determination module determines multiple target scan datasets from the scan data based on preset conditions, wherein each of the multiple target scan datasets corresponds to a target sub-time period within the scan time period. The generation module generates one or more intermediate images corresponding to one or more sub-time periods different from the multiple target sub-time periods within the scan time period, based on the multiple target scan datasets. It also generates a target image sequence of the object based on the multiple target scan datasets and the one or more intermediate images.

[0016] Another aspect of this specification provides a non-transient computer-readable medium. The non-transient computer-readable medium includes at least one set of instructions for positron emission tomography (PET) imaging, wherein, when the at least one set of instructions is executed by one or more processors of a computing device, the computing device performs a method comprising: acquiring scan data of an object acquired by PET scan within a scan time period; determining a plurality of target scan datasets from the scan data based on preset conditions, wherein each of the plurality of target scan datasets corresponds to a target sub-time period within the scan time period; generating one or more intermediate images corresponding to one or more sub-time periods different from the plurality of target sub-time periods within the scan time period based on the plurality of target scan datasets; and generating a target image sequence of the object based on the plurality of target scan datasets and the one or more intermediate images.

[0017] Another aspect of this specification provides a positron emission tomography (PET) imaging apparatus. The PET imaging apparatus includes at least one processor and at least one storage device for storing an instruction set, wherein, when the instruction set is executed by the at least one processor, the apparatus performs the PET imaging method.

[0018] Additional features will be set forth in the description below and through study of the following description and the accompanying drawings, or through learning of the production or operation of the embodiments. The features of this specification can be implemented and achieved through practice or use of various methods, means, and combinations thereof with respect to the specific embodiments described below. Attached Figure Description

[0019] This specification will be further illustrated by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and the same reference numerals denote the same structures.

[0020] Figure 1 This is a schematic diagram of a positron emission tomography (PET) imaging system according to some embodiments of this specification;

[0021] Figure 2 These are schematic diagrams of exemplary hardware and / or software components of an exemplary computing device according to some embodiments of this specification;

[0022] Figure 3 This is a frame diagram of an exemplary processing device according to some embodiments of this specification;

[0023] Figure 4 This is an exemplary flowchart illustrating the generation of a target image sequence of an object during dynamic positron emission tomography imaging, according to some embodiments of this specification.

[0024] Figure 5A This is an exemplary flowchart illustrating the determination of multiple target scan datasets according to some embodiments of this specification;

[0025] Figure 5B This is a schematic diagram of an exemplary three-dimensional count distribution diagram shown according to some embodiments of this specification;

[0026] Figure 6 This is a schematic diagram of an exemplary time-radioactivity curve (TAC) according to some embodiments of this specification;

[0027] Figure 7 This is a schematic diagram of exemplary respiratory curves according to some embodiments of this specification;

[0028] Figure 8 This is an exemplary flowchart illustrating the generation of multiple target images according to some embodiments of this specification;

[0029] Figure 9 This is an exemplary flowchart illustrating the generation of a target image sequence according to some embodiments of this specification;

[0030] Figure 10A This is a schematic diagram illustrating an exemplary target image sequence according to some embodiments of this specification;

[0031] Figure 10B This is a schematic diagram of an exemplary target image sequence according to other embodiments of this specification. Detailed Implementation

[0032] In the following detailed description, numerous specific details are set forth by way of example in order to provide a thorough understanding of the relevant disclosure. However, it will be apparent to those skilled in the art that this specification may be practiced without these details. In other instances, well-known methods, processes, systems, components, and / or circuits have been described at a higher level to avoid unnecessarily obscuring various aspects of this specification. Various modifications to the disclosed embodiments will be apparent to those skilled in the art, and the general principles defined in this specification can be applied to other embodiments and applications without departing from the spirit and scope of this specification. Therefore, this specification is not limited to the embodiments shown, but is accorded the widest scope consistent with the claims.

[0033] The terminology used in this specification is for describing particular exemplary embodiments only and is not intended to be limiting. As used herein, the singular forms “a,” “an,” and / or “the” may also be intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and / or “including” specify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0034] It should be understood that the terms “system,” “device,” “unit,” “module,” and / or “block” used herein are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0035] It should be understood that when a unit, engine, module, or block is referred to as being "in," "connected to," or "coupled to" another unit, engine, module, or block, it may be directly in connection with or coupled to the other unit, engine, module, or block, or communicate with other units, engines, modules, or blocks, or there may be intermediate units, engines, modules, or blocks, unless the context clearly indicates otherwise. As used in this specification, the term "and / or" includes any and all combinations of at least one of the related listed items.

[0036] The terms "pixel" and "voxel" in this specification are used interchangeably to refer to elements of an image. Anatomical structures displayed in an image of an object (e.g., a patient) may correspond to actual anatomical structures present inside or on the surface of the object. The terms "object" and "subject" in this specification are used interchangeably to refer to biological objects (e.g., a patient, an animal) or non-biological objects (e.g., a phantom). In some embodiments, an object may include specific parts, organs, and / or tissues of an object. For example, an object may include a patient's head, bladder, brain, neck, torso, shoulder, arm, chest, heart, stomach, blood vessels, soft tissue, knee, foot, etc., or any combination thereof.

[0037] These and other features and characteristics of this specification, as well as the operation and function of related structural elements and the economy of assembly and manufacture of components, will become more apparent from the following description with reference to the accompanying drawings, all of which form part of this specification. However, it should be clearly understood that the drawings are for illustration and description only and are not intended to limit the scope of this specification. It should be understood that the drawings are not drawn to scale.

[0038] One aspect of this specification provides a positron emission tomography (PET) imaging system and method. The system can acquire scan data of an object obtained by PET scanning within a scan time period. The system can also determine multiple target scan datasets from the scan data. Each of the multiple target scan datasets corresponds to a target sub-time period within the scan time period. Furthermore, the system can generate one or more intermediate images corresponding to one or more sub-time periods different from the multiple target sub-time periods within the scan time period based on the multiple target scan datasets. For example, the system can generate multiple target images based on the multiple target scan datasets. For each pair of one or more target image pairs formed by the multiple target images, the system can use a motion field generation model to determine the motion field between the images within that target image pair, and use an image generation model to generate one or more intermediate images corresponding to that target image pair based on the motion field. The system can then generate a sequence of target images of the object based on the multiple target scan datasets and the one or more intermediate images.

[0039] According to some embodiments of this specification, intermediate images (e.g., based on motion fields between target image pairs) can be generated without image reconstruction, thus reducing image reconstruction time. Furthermore, intermediate images can be generated based on a motion field generation model and an image generation model, and / or denoising operations can be performed using a denoising model and / or resolution improvement operations can be performed using a resolution improvement model before generating the target images. Therefore, imaging efficiency and image quality can be improved.

[0040] Figure 1This is a schematic diagram of a positron emission tomography (PET) imaging system according to some embodiments of this specification. In some embodiments, such as Figure 1 As shown, the PET system 100 may include a PET scanner 110, a network 120, a terminal device 130, a processing device 140, and a storage device 150. The components of the PET system 100 can be connected in various ways. By way of example only, the PET scanner 110 can be connected to the processing device 140 via the network 120. As another example, the PET scanner 110 can be directly connected to the processing device 140, as indicated by the dashed double-headed arrows connecting the PET scanner 110 and the processing device 140. As another example, the processing device 140 can be connected to the storage device 150 via the network 120 or directly. As another example, the terminal device 130 can be connected to the processing device 140 via the network 120 or directly to the processing device 140, as indicated by the dashed double-headed arrows connecting the terminal device 130 and the processing device 140.

[0041] PET scanner 110 is configured to acquire scan data related to an object. For example, PET scanner 110 can scan an object or a portion thereof located within its detection area and generate scan data related to the object or a portion thereof. In some embodiments, PET scanner 110 can perform dynamic PET imaging of an object or a portion thereof within a dynamic scanning time period and acquire the corresponding scan data. The dynamic scanning time period may include multiple sub-time periods (which may be manually defined or automatically divided), each sub-time period corresponding to a set of scan data.

[0042] In some embodiments, the PET scanner 110 may include a frame 112, a scanning bed 114, and a detector 116. The frame 112 may support the detector 116. The scanning bed 114 may be used to support the object 118 to be scanned. The detector 116 may include components along the axial direction of the frame 112 (e.g., ...). Figure 1 Multiple detector rings are arranged in the Z-axis direction. In some embodiments, the detector ring includes multiple detector elements arranged along the circumference of the detector ring. In some embodiments, the detector 116 includes a scintillation detector (e.g., a cesium iodide detector), a gas detector, or any combination thereof.

[0043] In some embodiments, a tracer substance may be injected into the subject 118 prior to a PET scan. A tracer substance is a radioactive material that decays and emits positrons. In some embodiments, the tracer substance may be a radiolabeled radiopharmaceutical, which is a radioactive drug administered to the subject 118. For example, the tracer substance may include fluorine-18 (…). 18F) Fluorodeoxyglucose (FDG), etc. During scanning, positron annihilation from the tracer substance in object 118 may produce photon pairs (e.g., gamma photons). The photon pairs may move in opposite directions. Detector elements in detector 116 can detect and / or record at least a portion of the photon pairs. When a photon pair produced by positron annihilation is detected within a coincidence time window (e.g., within 6 to 12 nanoseconds), a coincidence event can be recorded. Assuming the coincidence event occurs on the line connecting a pair of detector elements, this line may be referred to as the "line of response" (LOR). Detector 116 can obtain a count of coincidence events based on the LOR of the detected coincidence event and the time point in time when the coincidence event occurred.

[0044] In some embodiments, the PET scanner 110 is a multimodal scanner, such as a positron emission tomography-magnetic resonance imaging (PET-MRI) system, a positron emission tomography-computed tomography (PET-CT) system, etc.

[0045] Network 120 can facilitate the exchange of information and / or data. In some embodiments, one or more components of the PET system 100 (e.g., PET scanner 110, terminal device 130, processing device 140, storage device 150) can send information and / or data to other components in the PET system 100 via network 120. For example, processing device 140 can obtain scan data related to object 118 or a portion thereof from PET scanner 110 via network 120. In some embodiments, network 120 can be any type of wired or wireless network or a combination thereof.

[0046] Terminal device 130 includes mobile device 130-1, tablet computer 130-2, laptop computer 130-3, etc., or any combination thereof. In some embodiments, terminal device 130 can remotely operate PET scanner 110. In some embodiments, terminal device 130 can operate PET scanner 110 via wireless connection. In some embodiments, terminal device 130 can receive information and / or instructions input by the user and send the received information and / or instructions to PET scanner 110 or processing device 140 via network 120. In some embodiments, terminal device 130 can receive data and / or information from processing device 140. In some embodiments, terminal device 130 may be part of processing device 140. In some embodiments, terminal device 130 may be omitted.

[0047] Processing device 140 can process data obtained from PET scanner 110, terminal device 130, storage device 150, or other components of PET system 100. For example, processing device 140 can obtain scan data (e.g., PET data) of an object (e.g., a human body) within a scan time period from PET scanner 110 or storage device 150. Processing device 140 can determine multiple target scan datasets from the scan data. Each of the multiple target scan datasets can correspond to a target sub-time period within the scan time period. Processing device 140 can then generate one or more intermediate images corresponding to one or more sub-time periods that are different from the multiple target sub-time periods within the scan time period based on the multiple target scan datasets. Furthermore, processing device 140 can generate a target image sequence of the object based on the multiple target scan datasets and one or more intermediate images.

[0048] In some embodiments, the processing device 140 may be a central processing unit (CPU), a digital signal processor (DSP), a system-on-a-chip (SoC), a microcontroller unit (MCU), or any combination thereof. In some embodiments, the processing device 140 may be a single server or a group of servers. In some embodiments, the processing device 140 may be located locally or remotely within the PET system 100. In some embodiments, the processing device 140 may be implemented on a cloud platform. By way of example only, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud cloud, multi-cloud, or any combination thereof.

[0049] For illustrative purposes only, only one processing device 140 is described in the PET system 100. However, it should be noted that the PET system 100 in this specification may also include multiple processing devices. Therefore, the operations and / or method steps performed by one processing device 140 as described in this specification may also be performed by multiple processing devices in combination or individually. For example, if in this specification, the processing device 140 of the PET system 100 performs process A and process B, it should be understood that process A and process B may also be performed by two or more different processing devices in the PET system 100 in combination or individually (e.g., a first processing device performs process A, a second processing device performs process B, or the first and second processing devices jointly perform process A and process B).

[0050] Storage device 150 may store data, instructions, and / or any other information. In some embodiments, storage device 150 may store data acquired from processing device 140, terminal device 130, and / or PET scanner 110. For example, storage device 150 may store scan data acquired by PET scanner 110. As another example, storage device 150 may store a target image sequence of an object. In some embodiments, storage device 150 may store data and / or instructions that processing device 140 may perform or be used to perform the exemplary methods described herein.

[0051] In some embodiments, storage device 150 may include mass storage, removable storage, volatile read-write storage, read-only storage (ROM), or any combination thereof. In some embodiments, storage device 150 may be implemented on a cloud platform as described elsewhere in this specification. In some embodiments, storage device 150 may be connected to network 120 to communicate with one or more components of PET system 100 (e.g., PET scanner 110, terminal device 130, processing device 140). One or more components of PET system 100 may access data or instructions stored in storage device 150 via network 120. In some embodiments, storage device 150 may be part of processing device 140.

[0052] It should be noted that the above description of the PET system 100 is for illustrative purposes only and is not intended to limit the scope of this specification. Various changes and modifications can be made by those skilled in the art based on the teachings of this specification. For example, the PET system 100 may include one or more additional components and / or one or more components of the PET system 100 described above may be omitted. Alternatively, two or more components of the PET system 100 may be integrated into a single component. Components of the PET system 100 may be implemented on two or more sub-components.

[0053] Figure 2 These are schematic diagrams of exemplary hardware and / or software components of an exemplary computing device according to some embodiments of this specification. In some embodiments, processing device 140 may be implemented on computing device 200. Figure 2 As shown, the computing device 200 may include a processor 210, a memory 220, an input / output (I / O) 230, and a communication port 240.

[0054] Processor 210 can execute computer instructions (program code) and perform the functions of processing device 140 according to the techniques described herein. Computer instructions may include routines, programs, objects, components, signals, data structures, flows, modules, and functions that perform the specific functions described herein. For illustrative purposes only, only one processor is described in computing device 200. However, it should be noted that computing device 200 in this specification may also include multiple processors; therefore, the operation of a method performed by one processor as described herein may also be performed jointly or individually by multiple processors.

[0055] The memory 220 may store data / information obtained from the PET scanner 110, terminal device 130, storage device 150, or any other component of the PET system 100. 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), 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 herein.

[0056] Input / output 230 can input or output signals, data, or information. In some embodiments, input / output 230 enables a user to interact with processing device 140. In some embodiments, input / output 230 may include input devices and output devices.

[0057] Communication port 240 can be connected to a network (e.g., network 120) to facilitate data communication. Communication port 240 can establish a connection between processing device 140 and PET scanner 110, terminal device 130, or storage device 150. This connection can be a wired connection, a wireless connection, or a combination of both to enable data transmission and reception.

[0058] It should be noted that the above description of the computing device 200 is for illustrative purposes only and is not intended to limit the scope of this specification. Various changes and modifications can be made by those skilled in the art under the guidance of this specification.

[0059] Figure 3 This is a frame diagram of an exemplary processing device according to some embodiments of this specification. Figure 3 As shown, the processing device 140 includes an acquisition module 310, a determination module 320, and a generation module 330. For example... Figure 1 As shown, the PET system 100 in this specification may also include multiple processing devices, and the acquisition module 310, the determination module 320 and the generation module 330 may be components of different processing devices.

[0060] The acquisition module 310 is configured to acquire data and / or information related to the PET system 100. For example, the acquisition module 310 may acquire scan data of an object obtained by PET scanning over a scanning period. Further description of acquiring scan data can be found elsewhere in this specification, for example, see [link to documentation]. Figure 4 Step 410 and its related description.

[0061] The determination module 320 is configured to determine multiple target scan datasets from the scan data based on preset conditions. Each of the multiple target scan datasets corresponds to a target sub-time period within the scan time period. Further description of the determination of multiple target scan datasets can be found elsewhere in this specification, for example, see [link to documentation]. Figure 4 Step 420 and its related description.

[0062] The generation module 330 is configured to generate one or more intermediate images corresponding to one or more sub-time periods of multiple target sub-time periods, different from those in the scanning time period, based on multiple target scan datasets. The generation module 330 is also configured to generate a target image sequence of the object based on the multiple target scan datasets and the one or more intermediate images. Further description of the generation of the one or more intermediate images and the target image sequence can be found elsewhere in this specification, for example, see [link to documentation]. Figure 4 Steps 430 and 440 and their related descriptions.

[0063] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this specification. Various changes and modifications can be made by those skilled in the art based on the guidance of this specification. However, these changes and modifications do not depart from the scope of this specification. In some embodiments, any of the modules may be divided into two or more units. For example, the acquisition module 310 may be divided into two units configured to acquire different data. In some embodiments, the processing device 140 may include one or more additional modules, such as a storage module (not shown) for storing data.

[0064] Figure 4 This is an exemplary flowchart illustrating the generation of a target image sequence of an object during dynamic positron emission tomography imaging, according to some embodiments of this specification. In some embodiments, process 400 may be executed by PET system 100. For example, process 400 may be implemented as a set of instructions (e.g., an application program) stored in a storage device (e.g., storage device 150, memory 220). In some embodiments, processing device 140 (e.g., processor 210 of computing device 200 and / or...) Figure 3One or more modules shown can execute this set of instructions and can be instructed to execute process 400 accordingly. The operation of the process shown below is for illustrative purposes. In some embodiments, process 400 can be implemented by one or more additional operations not described and / or one or more operations not discussed. Furthermore, Figure 4 The sequence of operations in process 400 shown and described below is not intended to be restrictive.

[0065] In step 410, the processing device 140 (e.g., acquisition module 310, processor 210) acquires scan data of the object (e.g., patient) acquired by positron emission tomography (PET) over a scanning time period.

[0066] In some embodiments, the processing device 140 may acquire scan data collected by a dynamic PET scan (also referred to as "dynamic PET imaging") performed by the PET scanner 110. In some embodiments, the scan time period may be a predetermined time period during the dynamic PET scan (e.g., 1-5 minutes, 5-10 minutes, 5-15 minutes, 10-20 minutes). In some embodiments, the scan data may be in the form of a list pattern, ultrasound image, tissue image, tissue projection, etc.

[0067] In some embodiments, the processing device 140 may acquire scan data from one or more components of the PET system 100 (e.g., PET scanner 110, storage device 150) or an external source via a network (e.g., network 120).

[0068] In step 420, the processing device 140 (e.g., the determining module 320, the processor 210) determines multiple target scan datasets from the scan data based on preset conditions, wherein each of the multiple target scan datasets corresponds to a target sub-time period in the scan time period.

[0069] Preset conditions can indicate the conditions that multiple target scan datasets need to meet. For example, a preset condition could be that the difference between two adjacent target scan datasets is relatively large, such as exceeding a difference threshold. This difference threshold can be the default setting of the PET system 100, or it can be adjusted under different circumstances.

[0070] In some embodiments, the processing device 140 may divide the scan data into a plurality of candidate scan datasets. For each of the plurality of candidate scan datasets, the processing device 140 may determine a three-dimensional (3D) count distribution map corresponding to the candidate scan dataset. The 3D count distribution map may include at least one pixel, each pixel corresponding to a pixel value representing a count of coincidence events associated with the pixel. Furthermore, the processing device 140 may determine a plurality of target scan datasets based on the plurality of 3D count distribution maps corresponding to the plurality of candidate scan datasets respectively. Further description of determining a plurality of target scan datasets based on a plurality of 3D count distribution maps can be found elsewhere in this specification, for example... Figure 5A and Figure 5B , and its related descriptions.

[0071] In some embodiments, the scanning time period may include multiple sub-time periods (each corresponding to multiple sets of scan data). Therefore, the processing device 140 can determine multiple target sub-time periods within the multiple sub-time periods of the scanning time period, and designate the scan data collected in each of the multiple target sub-time periods as a target scan dataset. In some embodiments, the duration of the multiple target sub-time periods corresponding to the multiple target scan datasets may be the same. Alternatively or optionally, the duration of the multiple target sub-time periods corresponding to the multiple target scan datasets may be different.

[0072] In some embodiments, the processing device 140 may determine the first sub-time period and / or the last sub-time period as the target sub-time period and determine the corresponding scan dataset as the target scan dataset. In some embodiments, the processing device 140 may select (e.g., randomly select) some sub-time periods between the first and last sub-time periods as the target sub-time periods and determine the corresponding scan dataset as the target scan dataset.

[0073] In some embodiments, the processing device 140 may obtain a time-activity curve (TAC) related to the tracer in a PET scan and determine multiple target sub-time periods (and corresponding multiple target scan datasets) based on the TAC. The TAC can characterize the change in tracer concentration in the object over time. In some embodiments, the TAC may be an object-based TAC generated from the object's scan data. In some embodiments, the TAC may be a population-based TAC determined based on historical data statistics. In some embodiments, the processing device 140 may obtain the TAC from a storage device 150 or an external resource. This is merely an example. Figure 6 This is a schematic diagram of an exemplary time-radioactivity curve (TAC) according to some embodiments of this specification. Figure 6As shown in the figure, the horizontal axis of TAC represents time, and the vertical axis of TAC represents the concentration of the tracer.

[0074] In some embodiments, the processing device 140 can define a target duration and determine multiple target sub-time periods based on the target duration and the concentration change of the tracer (which can be defined by the slope of the TAC). For example, if the concentration change of the tracer is relatively large over a period of time (i.e., the slope of the TAC is relatively large over that period of time), the time interval between adjacent target sub-time periods within that period of time can be relatively small; if the concentration change of the tracer is relatively small over a period of time (i.e., the slope of the TAC is relatively small over that period of time), the time interval between adjacent target sub-time periods within that period of time can be relatively large, wherein all of the multiple target sub-time periods correspond to the same target duration. Specifically, for example... Figure 6 As shown, T k1 T k2 T k3 T k4 T k5 and T k6 This refers to the target sub-time period. It can be seen that the tracer concentration change is relatively large in time period OA, meaning the slope of the TAC is relatively large in time period OA. Therefore, the adjacent target sub-time periods T within time period OA... k1 T k2 and T k3 The time interval T between a and T b The concentration change of the tracer is relatively small within time period AB; however, the slope of the TAC is relatively small within time period OB. Therefore, the adjacent target sub-time period T... k3 T k4 T k5 and T k6 The time interval T between c and T d Relatively large.

[0075] In some embodiments, the processing device 140 can acquire vital signals of an object corresponding to scan data and determine multiple target sub-time periods (and corresponding multiple target scan datasets) based on the vital signals. In some embodiments, vital signals refer to physiological signals generated by the physiological movements of an object (such as heartbeat, respiratory movements, etc.). Exemplary vital signals may include heartbeat signals, respiratory signals, etc., or any combination thereof. In some embodiments, vital signals may be collected by a vital signal monitor and / or stored in a storage device (e.g., storage device 150). The processing device 140 can acquire vital signals from the vital signal monitor and / or storage device. This is only an example. Figure 7This is a schematic diagram of exemplary respiratory curves according to some embodiments of this specification. Figure 7 As shown, the horizontal axis of the breathing curve represents time, and the vertical axis represents the breathing amplitude.

[0076] In some embodiments, the processing device 140 may determine and define a target duration, and determine multiple target sub-time periods based on the target duration and the peak and / or trough values ​​of the respiratory curve. For example, the processing device 140 may determine a time period T' that includes the peak P1. k1 (Its duration is the target duration), including the time period T' of peak P2. k2 (Its duration is the target duration), including the time period T' of the trough M1. k3 (Its duration is the target duration), including the time period T' of the trough M2. k4 (Its duration is the target duration) is used as the target sub-time period.

[0077] In some embodiments, the processing device 140 may define target durations (e.g., 0.1 seconds, 0.5 seconds, 1 second) and target time periods (e.g., 3 seconds, 5 seconds, 8 seconds) between adjacent target sub-time periods, and determine multiple target sub-time periods based on the target durations and target time periods. Furthermore, the processing device 140 may determine the corresponding scan datasets within the multiple target sub-time periods as multiple target scan datasets.

[0078] In step 430, the processing device 140 (e.g., generation module 330, processor 210) generates one or more intermediate images corresponding to one or more sub-time periods that are different from the multiple target sub-time periods in the scanning time period, based on multiple target scanning datasets.

[0079] In short, the sub-time period corresponding to the intermediate image can be called an intermediate sub-time period. In some embodiments, one or more intermediate sub-time periods may include one or more sub-time periods other than multiple target sub-time periods. In some embodiments, one or more intermediate sub-time periods and multiple target sub-time periods may partially overlap.

[0080] In some embodiments, the processing device 140 may generate multiple target images corresponding to multiple target scan datasets, and generate one or more intermediate images based on these target images.

[0081] In some embodiments, for each of a plurality of target scan datasets, the processing device 140 may use image reconstruction techniques to determine an initial image based on the target scan dataset. Exemplary image reconstruction techniques may include filtered back projection (FBP), algebraic reconstruction (ART), statistical reconstruction (SR) algorithms, and any combination thereof. Those skilled in the art will understand that image reconstruction techniques may vary, and all such variations are within the scope of this specification.

[0082] In some embodiments, the processing device 140 may generate multiple initial images using an image reconstruction model. The image reconstruction model may be a training model (e.g., a machine learning model) for reconstructing PET images based on PET scan data. In some embodiments, the image reconstruction model may be trained based on multiple training samples, each training sample including sample scan data of a sample object collected via PET scan and a reference image of the sample object, wherein the reference image may be used as the ground truth (also called a label) for model training.

[0083] In some embodiments, the processing device 140 may designate a plurality of initial images corresponding to a plurality of target scan datasets as a plurality of target images corresponding to a plurality of target scan datasets.

[0084] In some embodiments, the processing device 140 can determine multiple target images by performing denoising operations on multiple initial images. In some embodiments, the denoising operation can be performed according to a denoising algorithm. Exemplary denoising algorithms may include mean filtering, adaptive Wiener filtering, median filtering, wavelet denoising, etc. In some embodiments, a denoising model (e.g., Figure 8 The denoising model 810 shown performs the denoising operation. In some embodiments, the denoising model is a trained model (e.g., a machine learning model) for reducing noise in an image. In some embodiments, the denoising model may include a deep learning model, such as a deep neural network (DNN) model, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, a feature pyramid network (FPN) model, etc. Exemplary CNN models may include V-Net models, U-Net models, Link Net models, etc., or any combination thereof.

[0085] In some embodiments, the denoising model can be trained based on multiple training samples. This is merely an example. Figure 8 This is an exemplary flowchart illustrating the generation of multiple target images according to some embodiments of this specification. Figure 8 As shown, a preliminary denoising model can be trained based on one or more first training samples to determine the denoising model. In some embodiments, each first training sample may include a sample image of a sample object and a reference image of the sample object, wherein the reference image has relatively low noise and can be used as the base ground (also called a label) for model training. In some embodiments, the reference image may be user-defined or automatically determined by the training device. In some embodiments, the sample object may be the same as or similar to the object described elsewhere in this specification. In some embodiments, the reference image may be generated based on sample data of the sample object collected by a sample PET scan using any image reconstruction technique described in step 430. The sample PET scan may be performed for a relatively long time to obtain sufficient sample scan data. In some embodiments, a uniform downsampling operation may be performed on at least a portion of the sample data, and a sample image may be generated based on the downsampled sample data using any image reconstruction technique described in step 430.

[0086] In some embodiments, an initial denoising model can be trained iteratively until a termination condition is met. In some embodiments, the termination condition relates to the value of the loss function. For example, the termination condition is considered met if the value of the loss function is minimized or less than a preset threshold. As another example, the termination condition is considered met if the value of the loss function converges. In some embodiments, "convergence" means that the change in the value of the loss function over two or more consecutive iterations is equal to or less than a preset threshold. In some embodiments, "convergence" means that the difference between the value of the loss function and the target value is equal to or less than a preset threshold. In some embodiments, the termination condition is considered met when a specified number of iterations have been performed in the training process.

[0087] In some embodiments, the processing device 140 may determine multiple target images by performing a resolution improvement operation on multiple initial images. In some embodiments, the resolution improvement operation may be performed based on a resolution improvement algorithm (e.g., an interpolation method). In some embodiments, the resolution improvement operation may be performed based on a resolution improvement model (e.g., Figure 8 The resolution improvement model 820 shown is used to perform the resolution improvement operation. In some embodiments, the resolution improvement model can be a trained model (e.g., a machine learning model) for improving image resolution. In some embodiments, the type of the resolution improvement model can be the same as the type of the denoising model.

[0088] In some embodiments, the resolution improvement model can be trained based on multiple training samples. This is merely an example. Figure 8As shown, the resolution improvement model can be determined by training an initial resolution improvement model based on one or more second training samples. In some embodiments, each second training sample may include a sample image of the sample object and a reference image of the sample object, wherein the reference image has a relatively high resolution and can be used as the ground truth (also called the label) for model training. In some embodiments, the sample image may correspond to a relatively large pixel size (e.g., a pixel size of 4mm × 4mm), and the reference image may correspond to a relatively small pixel size (e.g., a pixel size of 2mm × 2mm). In some embodiments, the reference image may be user-defined or automatically determined by the training device. In some embodiments, the sample object may be the same as or similar to the object described elsewhere in this specification. In some embodiments, the sample image may be generated based on sample data of the sample object collected by a sample PET scan using any image reconstruction technique described in step 430. In some embodiments, the sample PET scan may be performed for a relatively long time to obtain sufficient sample scan data. In some embodiments, the initial resolution improvement model may be trained iteratively until a termination condition is met. Further description can be found above and will not be repeated here.

[0089] In some embodiments, processing device 140 may obtain denoising models and / or resolution improvement models from one or more components of PET system 100 (e.g., storage device 150, memory 210) or external sources via a network (e.g., network 120). For example, the denoising models and / or resolution improvement models may be pre-trained by computing devices (e.g., processing device 140 or other processing devices) and stored in the storage devices of PET system 100 (e.g., storage device 150, memory 210). Processing device 140 may access the storage devices and retrieve the denoising models and / or resolution improvement models.

[0090] In some embodiments, the processing device 140 can determine multiple target images by performing denoising and resolution improvement operations on multiple initial images. For example, the processing device 140 can determine multiple target images by performing denoising operations on multiple initial images using a denoising model and performing resolution improvement operations on these initial images using a resolution improvement model. This is merely an example. Figure 8 As shown, an initial image can be input into a denoising model, the output of the denoising model can be input into a resolution improvement operation, and the resolution improvement model can output a target image corresponding to the initial image. In some embodiments, the denoising model and the resolution improvement model can be integrated into a single model.

[0091] In some embodiments of this specification, multiple target images are obtained by performing denoising operations and / or resolution improvement operations on multiple initial images, thereby improving the image quality of the target images.

[0092] In some embodiments, the processing device 140 may determine one or more target image pairs from a plurality of target images. In some embodiments, a target image pair may be any two target images from the plurality of target images. For example, such as Figure 10A As shown, a target image pair can be two adjacent target images from a plurality of target images (e.g., 1001a and 1002a, 1002a and 1003a). In some embodiments, one or more target image pairs can be manually determined by a user (e.g., a doctor, imaging specialist, technician). In some embodiments, one or more target image pairs can be automatically determined by the processing device 140.

[0093] Furthermore, for each pair of target images among a plurality of target images, the processing device 140 may generate one or more intermediate images between the pair of target images. For example, such as Figure 10A As shown, for target image pairs 1001a and 1002a, processing device 140 can generate intermediate images 1001b and 1002b corresponding to target image pairs 1001a and 1002a; for target image pairs 1002a and 1003a, processing device 140 can generate intermediate images 1003b and 1006b corresponding to target image pairs 1002a and 1003a. In some embodiments, the durations of intermediate sub-time periods corresponding to multiple intermediate images between target image pairs can be the same or different. In some embodiments, the duration of one or more intermediate sub-time periods corresponding to one or more intermediate images between target image pairs can be the same or different from the duration of the target sub-time periods corresponding to the target image pairs (assuming the target image pairs correspond to the same duration).

[0094] In some embodiments, for each of one or more target image pairs, the processing device 140 may determine one or more intermediate images based on the motion field between the target image pairs.

[0095] In some embodiments, for each pair of pairs in one or more target images, the processing device 140 can use a motion field generation model (e.g., Figure 9 The motion field generation model 910 shown in the figure determines the motion field between the target image pairs and uses an image generation model (e.g., Figure 9 The first image generation model 920 shown generates one or more intermediate images corresponding to the target image based on the motion field.

[0096] In some embodiments, the motion field generation model can be a trained model (e.g., a machine learning model) for determining the motion field between two images. In some embodiments, the motion field generation model can include a deep learning model, such as a deep neural network (DNN) model, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, and a feature pyramid network (FPN) model. Exemplary CNN models can include V-Net models, U-Net models, Link Net models, etc., or any combination thereof.

[0097] In some embodiments, the motion field generation model can be trained based on multiple training samples. This is merely an example. Figure 9 As shown, an initial motion field generation model can be trained based on one or more third training samples to determine the motion field generation model. In some embodiments, each third training sample may include a pair of sample images of a sample object and a reference motion field between the pair of sample images, wherein the reference motion field can be used as the ground truth (also called the label) for model training. In some embodiments, the reference motion field may be user-defined or automatically determined by the training device. In some embodiments, the sample object may be the same as or similar to the object described elsewhere in this specification. In some embodiments, the pair of sample images may be generated based on sample data of the sample object collected via sample PET scans using any image reconstruction technique described in step 430. In some embodiments, the sample PET scans may be performed for a relatively long time to obtain sufficient sample scan data. In some embodiments, the initial motion field generation model may be trained iteratively until a termination condition is met. Further description can be found above and will not be repeated here.

[0098] In some embodiments, the image generation model is a trained model (e.g., a machine learning model) used to generate one or more intermediate images between two images. In some embodiments, the image generation model may include a generative adversarial network (GAN) model, a diffusion model, etc.

[0099] In some embodiments, the image generation model can be trained based on multiple training samples. This is merely an example. Figure 9As shown, the first image generation model can be determined by training an initial first image generation model based on one or more fourth training samples. In some embodiments, each fourth training sample may include a pair of sample images of a sample object, a sample motion field between the pair of sample images, and one or more reference intermediate images between the pair of sample images, wherein the one or more reference intermediate images may be used as the ground truth (also called labels) for model training. In some embodiments, the one or more reference intermediate images may be defined by the user or automatically determined by the training device.

[0100] In some embodiments, the sample object may be the same as or similar to the object described elsewhere in this specification. In some embodiments, the pair of sample images may be generated based on sample data of the sample object collected via a dynamic PET scan of the sample object using any image reconstruction technique described in step 430. In some embodiments, the dynamic PET scan of the sample may be performed for a relatively long time to obtain sufficient sample scan data. In some embodiments, multiple reconstructed images may be generated corresponding to multiple sample sub-time periods (whose durations may be the same or different) of the dynamic PET scan of the sample, and a pair of reconstructed images from the multiple reconstructed images may be designated as a pair of sample images in a fourth training sample. In some embodiments, the difference between the pair of sample images may be relatively large (e.g., greater than a difference threshold). In some embodiments, one or more reconstructed images between the pair of sample images may be designated as one or more reference intermediate images. In some embodiments, the duration corresponding to one or more reference intermediate images may be less than or equal to the duration corresponding to the pair of sample images.

[0101] In some embodiments, the initial first image generation model can be trained iteratively until a termination condition is met. Further details can be found above and will not be repeated here.

[0102] In some embodiments, processing device 140 may obtain motion field generation models and / or image generation models from one or more components of PET system 100 (e.g., storage device 150, memory 210) or external sources via a network (e.g., network 120). For example, the motion field generation models and / or image generation models may be pre-trained by computing devices (e.g., processing device 140 or other processing devices) and stored in the storage devices of PET system 100 (e.g., storage device 150, memory 210). Processing device 140 may access the storage devices and retrieve the motion field generation models and / or image generation models.

[0103] In some embodiments, at least two of the image reconstruction model, denoising model, resolution improvement model, motion field generation model, or image generation model can be integrated into a single model. For example, the motion field generation model and the image generation model can be integrated into a single model. As another example, the image reconstruction model and the motion field generation model can be integrated into a single model. As another example, the image reconstruction model, the motion field generation model, and the image generation model can be integrated into a single model. As yet another example, the image reconstruction model, the denoising model, the resolution improvement model, the motion field generation model, and the image generation model can be integrated into a single model.

[0104] In some embodiments, the sports field generation model is further configured to generate multiple target images based on multiple target sets of scan data. The processing device 140 can determine the sports field by directly inputting multiple target scan datasets into the sports field generation model.

[0105] In some embodiments, the sports field generation model is also configured to generate one or more intermediate images based on multiple target sets or multiple target images of the scan data. For example, the processing device 140 can determine one or more intermediate images by inputting multiple target scan datasets into the sports field generation model. As another example, the processing device 140 can determine one or more intermediate images by inputting multiple target images into the sports field generation model.

[0106] In step 440, the processing device 140 (e.g., generation module 330, processor 210) generates a sequence of target images of the object based on multiple target scan datasets and one or more intermediate images.

[0107] In some embodiments, the processing device 140 can arrange multiple target images and one or more intermediate images in chronological order according to the target sub-time period and the intermediate sub-time period to form a target image sequence. For example, Figure 10A This is a schematic diagram illustrating exemplary target image sequences according to some embodiments of this specification. For example... Figure 10A As shown, target images 1001a, 1002a and 1003a and intermediate images 1001b, 1002b, 1003b, 1004b, 1005b and 1006b are arranged in sequence (e.g. 1001a, 1005b, 1002b, 1002a, 1003b, 1004b, 1005b, 1006b and 1003a) to form target image sequence 1000A.

[0108] In some embodiments, the processing device 140 can obtain one or more image pairs from a plurality of arranged target images and one or more intermediate images (also referred to as an "initial target image sequence"). Similarly, an image pair can be any two images from the initial target image sequence (e.g., Figure 10B (See 1002a and 1005b shown). In some embodiments, the difference between each pair of images in one or more image pairs is greater than a preset difference threshold, which may be the default setting of the PET system 100 or may be adjustable under different conditions. In some embodiments, one or more image pairs may be manually determined by a user (e.g., a doctor, imaging specialist, or technician). In some embodiments, one or more image pairs may be automatically determined by the processing device 140.

[0109] Furthermore, for each of one or more image pairs in the initial target image sequence, the processing device 140 can generate one or more secondary intermediate images between these pairs. For example, such as Figure 10B As shown, for image pairs 1002a and 1005b, processing device 140 can generate secondary intermediate images 1001c, 1002c, 1003c, and 1004c corresponding to image pairs 1002b and 1005b. In some embodiments, the duration corresponding to one or more secondary intermediate images may be less than or equal to the duration corresponding to the image pair.

[0110] In some embodiments, for each of one or more image pairs, the processing device 140 can use a motion field generation model (e.g., Figure 9 The motion field generation model 910 shown in the figure determines the motion field (also called "secondary motion field") between the pair of images, and uses a second image generation model (such as...) Figure 9 The second image generation model 930 shown generates one or more secondary intermediate images corresponding to the pair of images based on the motion field. In some embodiments, the second image generation model may be a trained model (e.g., a machine learning model) for generating one or more intermediate images between two images. In some embodiments, the second image generation model may be the same as or similar to the image generation model (also referred to as the "first image generation model").

[0111] In some embodiments, a second image generation model can be trained based on multiple training samples. This is merely an example. Figure 9As shown, a second image generation model can be determined by training an initial second image generation model based on one or more fifth training samples. In some embodiments, each fifth training sample may include a pair of sample images of a sample object, a sample motion field between the pair of sample images, and one or more reference intermediate images between the pair of sample images, wherein the one or more reference intermediate images may be used as the ground truth (also known as labels) for model training. In some embodiments, the one or more reference intermediate images may be defined by the user or determined automatically by the training device.

[0112] In some embodiments, the sample object may be the same as or similar to the object described elsewhere in this specification. In some embodiments, the pair of sample images may be generated based on sample data of the sample object collected by a dynamic PET scan of the sample object using any image reconstruction technique described in step 430. In some embodiments, the dynamic PET scan of the sample may be performed for a relatively long time to obtain sufficient sample scan data. In some embodiments, multiple reconstructed images may be generated corresponding to multiple sample sub-time periods (whose durations may be the same or different) of the dynamic PET scan of the sample, and a pair of reconstructed images in the multiple reconstructed images may be designated as a pair of sample images in the fifth training sample. In some embodiments, the difference between the pair of sample images may be relatively large (e.g., greater than a difference threshold). In some embodiments, one or more reconstructed images between a pair of sample images may be designated as one or more reference intermediate images. In some embodiments, the duration corresponding to one or more reference intermediate images in the fifth training sample may be less than the duration corresponding to one or more reference intermediate images in the fourth training sample.

[0113] In some embodiments, a second image generation model can be integrated into the image generation model.

[0114] Furthermore, the processing device 140 can generate a target image sequence of an object based on multiple target images, one or more intermediate images, and one or more secondary intermediate images corresponding to one or more image pairs. Similarly, in some embodiments, the processing device 140 can arrange multiple target images, one or more intermediate images, and one or more secondary intermediate images corresponding to one or more image pairs in chronological order according to the target sub-time period and the intermediate sub-time period to form a target image sequence. For example, Figure 10B This is a schematic diagram illustrating exemplary target image sequences according to other embodiments of this specification. For example... Figure 10BAs shown, target images 1001a, 1002a and 1003a, intermediate images 1001b, 1002b, 1005b and 1006b, and secondary intermediate images 1001c, 1002c, 1003c and 1004c are arranged in sequence (e.g. 1001a, 1001b, 1002b, 1002a, 1001c, 100c, 1003c, 1004c, 1005b, 1006b and 1003a) to form target image sequence 1000B.

[0115] In some embodiments of this specification, image reconstruction time can be reduced by generating intermediate images (e.g., based on motion fields between target image pairs) without image reconstruction. Furthermore, imaging efficiency and image quality can be improved by generating intermediate images based on motion field generation models and image generation models, and / or by performing denoising operations using a denoising model and / or performing resolution improvement operations using a resolution improvement model before generating the target images.

[0116] In some embodiments, if the tracer used in the PET scan includes multiple types of tracers, the processing device 140 can determine the scan data corresponding to each type of tracer by performing the steps 410 to 440 described above, and accordingly determine the target image sequence corresponding to each type of tracer.

[0117] It should be noted that the above description of process 400 is for illustrative purposes only and is not intended to limit the scope of this specification. Various changes and modifications can be made by those skilled in the art under the guidance of this specification. However, these changes and modifications do not depart from the scope of this specification. In some embodiments, process 400 may be implemented by one or more additional operations not described and / or without one or more of the above operations.

[0118] Figure 5A This is an exemplary flowchart illustrating the determination of multiple target scan datasets according to some embodiments of this specification. In some embodiments, process 500 may be executed by PET system 100. For example, process 500 may be implemented as a set of instructions (e.g., an application program) stored in a storage device (e.g., storage device 150, memory 220). In some embodiments, processing device 140 (e.g., processor 210 of computing device 200 and / or Figure 3 One or more modules shown can execute this set of instructions and can be instructed to execute process 500 accordingly. The operation of the process shown below is for illustrative purposes. In some embodiments, process 500 can be implemented by one or more additional operations not described and / or one or more operations not discussed. Furthermore, Figure 5AThe order of operations of process 500 shown and described below is not intended to be limiting. In some embodiments, one or more operations of process 500 may be performed to achieve, as in combination Figure 4 At least a portion of step 420.

[0119] In step 510, the processing device 140 (e.g., determination module 320, processor 210) divides the scan data into multiple candidate scan datasets.

[0120] In some embodiments, as described above, scan data can be collected during a dynamic scan time period via dynamic PET imaging. Therefore, the processing device 140 can divide the dynamic scan time period into multiple candidate time periods. Furthermore, the processing device 140 can divide the scan data into multiple candidate scan datasets based on the multiple candidate time periods. Specifically, the processing device 140 can designate scan data collected in each of the multiple candidate time periods as one of the multiple candidate scan datasets.

[0121] In step 520, for each of the multiple candidate scan datasets, the processing device 140 (e.g., determination module 320, processor 210) can determine a three-dimensional (3D) count distribution map corresponding to the candidate scan dataset.

[0122] In some embodiments, the three-dimensional count distribution map may include at least one pixel, wherein each pixel corresponds to a pixel value representing the count of coincident events associated with the pixel.

[0123] In some embodiments, for each matching event in the candidate scan dataset, the processing device 140 can determine the annihilation location of the annihilation response corresponding to the matching event. In some embodiments, the annihilation location can be represented by the maximum likelihood coordinates corresponding to the matching event. As an example only, the processing device 140 can determine the maximum likelihood coordinates corresponding to the matching event according to the following formula (1):

[0124]

[0125] in, Tbin represents the maximum likelihood coordinates corresponding to the coincident event, Tbin represents the sequence number of the Time of Flight (TOF) interval on the Response Line (LOR) corresponding to the coincident event, and TbinSuize represents the width of the TOF interval. and This represents the coordinates of the two detector units that detected the coincidence event.

[0126] Furthermore, the processing device 140 can determine a three-dimensional count distribution map based on the annihilation locations corresponding to coincidence events in the candidate scan dataset. For example, the processing device 140 can obtain an initial three-dimensional count distribution map that includes the field of view of a PET scanner used for PET scanning. Each pixel in the initial three-dimensional count distribution map may correspond to a spatial location, and the pixel value is 0. For each pixel in the initial three-dimensional count distribution map, the processing device 140 can determine the count of the coincidence event corresponding to that pixel based on the annihilation location corresponding to the coincidence event in the candidate scan dataset. The count of the coincidence event corresponding to a pixel refers to the count of the annihilation reaction that occurs at the spatial location corresponding to that pixel. The processing device 140 can assign the count of the coincidence event corresponding to the pixel as the new pixel value of the pixel. In addition, the processing device 140 can use the new pixel values ​​of the pixels in the initial three-dimensional count distribution map to update the initial three-dimensional count distribution map to obtain a three-dimensional count distribution map corresponding to the candidate set of scan data.

[0127] In step 530, the processing device 140 (e.g., determination module 320, processor 210) determines multiple target scan datasets based on multiple three-dimensional count distribution maps corresponding to multiple candidate scan datasets.

[0128] In some embodiments, multiple 3D count distribution maps corresponding to multiple candidate scan datasets can be arranged in chronological order according to multiple candidate time periods to form a map sequence. The processing device 140 can determine multiple target scan datasets by traversing the map sequence starting from the first 3D count distribution map in the map sequence. Specifically, the processing device 140 can sequentially determine the difference between the latest 3D count distribution map corresponding to the most recently determined target scan dataset and each subsequent 3D count distribution map, until the difference between the latest 3D count distribution map and one of the subsequent 3D count distribution maps is greater than or equal to a preset threshold. The processing device 140 can then designate the candidate scan dataset corresponding to that 3D count distribution map as the target scan dataset. As used herein, each time a target scan dataset is determined, the target dataset is considered the most recently determined target scan dataset, and the 3D count distribution map corresponding to the most recently determined target scan dataset is considered the most recently determined 3D count distribution map. For example, the processing device 140 can designate the candidate scan dataset corresponding to the first 3D count distribution map as the target scan dataset. The processing device 140 can determine the difference between the first 3D count distribution map and the next adjacent 3D count distribution map. In response to determining that the difference is greater than or equal to a preset threshold, the processing device 140 designates the candidate scan dataset corresponding to the next adjacent 3D count distribution map as the target scan dataset, and then continues to determine the difference between the next adjacent 3D count distribution map and the next adjacent 3D count distribution map of the next adjacent 3D count distribution map. In response to determining that the difference is less than a preset threshold, the processing device 140 may determine the difference between the first 3D count distribution map and the next adjacent 3D count distribution map of the next adjacent 3D count distribution map.

[0129] For example, Figure 5B This is a schematic diagram of an exemplary three-dimensional count distribution map shown according to some embodiments of this specification. For example... Figure 5BAs shown, multiple three-dimensional count distribution maps 501-509, each corresponding to a multiple candidate scan dataset, are arranged in chronological order according to the candidate time period. The processing device 140 can determine the difference between the first three-dimensional count distribution map 501 and the second three-dimensional count distribution map 502. In response to determining that the difference is less than a preset threshold, the processing device 140 can determine the difference between the first three-dimensional count distribution map 501 and the third three-dimensional count distribution map 503. In response to determining that the difference is less than the preset threshold, the processing device 140 can also determine the difference between the first three-dimensional count distribution map 501 and the fourth three-dimensional count distribution map 504. In response to determining that the difference is greater than the preset threshold, the processing device 140 can designate the candidate scan dataset corresponding to the fourth three-dimensional count distribution map 504 as the target scan dataset. Then, the processing device 140 can determine the difference between the fourth three-dimensional count distribution map 504 and the fifth three-dimensional count distribution map 505, and so on, until all three-dimensional count distribution maps have been traversed. Figure 5B As shown, the final target scan dataset corresponds to the three-dimensional count distribution maps 501, 504, 507, and 509.

[0130] For those skilled in the art, various changes and modifications can be made to this specification without departing from its spirit and scope. In this way, this specification may be intended to include any modifications and variations that fall within the scope of the appended claims and their equivalents.

[0131] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0132] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0133] Furthermore, those skilled in the art will understand that various aspects of this specification can be described and illustrated in several patentable ways or situations, including any new and useful combination of processes, machines, products, or substances, or any new and useful improvements thereof. Accordingly, various aspects of this specification may be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software, and are generally referred to herein as “modules,” “units,” “components,” “devices,” or “systems.” Additionally, various aspects of this specification may be represented as computer products located on one or more computer-readable media, including computer-readable program code.

[0134] Computer storage media may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and suitable combinations thereof. Computer storage media can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0135] The computer program code required for the operation of each part of this manual can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc.; conventional procedural programming languages ​​such as C, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP; dynamic programming languages ​​such as Python, Ruby, and Groovy; or other programming languages. This program code can run entirely on the user's computer, or as a standalone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer through any network, such as a local area network (LAN) or wide area network (WAN), or connected to an external computer (e.g., through the internet provided by an internet service provider), or in a cloud computing environment, or as a service such as Software as a Service (SaaS).

[0136] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0137] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the claims contain fewer features than all the features of the single embodiment disclosed above.

[0138] In some embodiments, numbers describing the quantity of components or attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples by the terms "approximately," "approximately," or "generally." For example, unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary slightly (e.g., ±1%, ±5%, ±10%, or ±20%). Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters are taken into account a specified number of significant digits and are rounded using general methods. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such numerical values ​​are set as precisely as feasible. In some embodiments, classification criteria for classification or determination are provided for illustrative purposes and are modified according to different circumstances. For example, a classification criterion of "a value greater than a threshold" may further include or exclude the criterion of "a probability value equal to a threshold."

Claims

1. A positron emission tomography (PET) imaging system, comprising: At least one storage device, including an instruction set for medical imaging; as well as At least one processor communicating with the at least one storage device, wherein, when executing the instruction set, the at least one processor is configured to control the system to perform operations including: Acquire scan data of an object obtained by positron emission tomography within a scanning time period; Multiple target scan datasets are determined from the scan data based on preset conditions, wherein each of the multiple target scan datasets corresponds to a target sub-time period in the scan time period; Based on the multiple target scan datasets, generate one or more intermediate images corresponding to one or more intermediate sub-time periods, wherein the one or more intermediate sub-time periods are one or more sub-time periods within the scan time period other than the multiple target sub-time periods; and A sequence of target images of the object is generated based on the multiple target scan datasets and the one or more intermediate images.

2. The system of claim 1, wherein, The step of determining multiple target scan datasets from the scan data based on preset conditions includes: The scan data is divided into multiple candidate scan datasets; For each of the plurality of candidate scan datasets, a three-dimensional (3D) count distribution map corresponding to the candidate scan dataset is determined, wherein the 3D count distribution map includes at least one pixel, and each pixel corresponds to a pixel value representing the count of coincidence events associated with the pixel; and Based on the multiple three-dimensional count distribution maps corresponding to the multiple candidate scan datasets, the multiple target scan datasets are determined, wherein the difference between the three-dimensional count distribution maps corresponding to two adjacent target scan datasets in the multiple target scan datasets is greater than or equal to a preset threshold.

3. The system of claim 2, wherein, The determination of the plurality of target scan datasets based on the plurality of three-dimensional count distribution maps corresponding to the plurality of candidate scan datasets includes: The multiple three-dimensional count distribution maps are arranged in chronological order to form a map sequence; and The plurality of target scan datasets are determined by traversing the image sequence starting from the first three-dimensional count distribution map in the image sequence, wherein traversing the image sequence starting from the first three-dimensional count distribution map includes: The difference between the latest 3D count distribution map corresponding to the latest determined target scan dataset and each 3D count distribution map in the image sequence that follows the latest 3D count distribution map is determined sequentially until the difference between the latest 3D count distribution map and a 3D count distribution map that follows the latest 3D count distribution map is greater than or equal to the preset threshold, and the candidate scan dataset corresponding to the 3D count distribution map is determined as the target scan dataset.

4. The system of claim 1, wherein, The step of determining multiple target scan datasets from the scan data based on preset conditions includes: Obtain the time-radioactivity profile of the tracer in the positron emission tomography (PET) scan; and The plurality of target scan datasets are determined from the scan data based on the time-radioactivity curves.

5. The system of claim 1, wherein, The step of determining multiple target scan datasets from the scan data based on preset conditions includes: Obtain the life signal of the object corresponding to the scan data; The plurality of target scan datasets are determined from the scan data based on the vital signs.

6. The system according to any one of claims 1 to 5, wherein, The generation of one or more intermediate images corresponding to one or more intermediate sub-time periods includes: Generate multiple target images corresponding to the multiple target scan datasets, respectively; and One or more intermediate images are generated based on the multiple target images.

7. The system according to claim 6, wherein, The generation of multiple target images corresponding to the multiple target scanning datasets includes: Determine multiple initial images corresponding to the multiple target scan datasets respectively; and The plurality of target images are determined by performing denoising operations on the plurality of initial images using a denoising model and / or performing resolution improvement operations on the plurality of initial images using a resolution improvement model.

8. The system according to claim 7, wherein, The generation of one or more intermediate images corresponding to one or more intermediate sub-time periods includes: For each of the one or more target image pairs formed from the plurality of target images Use a motion field generation model to determine the motion field between images within the target image pair; and The image generation model is used to generate one or more intermediate images corresponding to the target image pair based on the sports field.

9. The system according to claim 8, wherein, The sports field generation model and the image generation model are integrated into a single model.

10. The system according to any one of claims 1 to 5, wherein, The process of generating the target image sequence of the object based on the plurality of target scan datasets and the one or more intermediate images includes: Generate multiple target images corresponding to the multiple target scan datasets, respectively; For each of the one or more image pairs formed by the plurality of target images and the one or more intermediate images Use a motion field generation model to determine the secondary motion field between images within the image pair; and Using an image generation model, one or more secondary intermediate images corresponding to the image pair are generated based on the secondary motion field; and The target image sequence of the object is generated based on the plurality of target images, the one or more intermediate images, and the one or more secondary intermediate images.

11. The system according to claim 10, wherein, The difference between the images within the image pair is greater than a preset difference threshold.

12. A positron emission tomography (PET) imaging method, said method being implemented on a computing device having at least one storage device and at least one processor, the method comprising: Acquire scan data of an object obtained by positron emission tomography within a scanning time period; Multiple target scan datasets are determined from the scan data based on preset conditions, wherein each of the multiple target scan datasets corresponds to a target sub-time period in the scan time period; Based on the multiple target scan datasets, generate one or more intermediate images corresponding to one or more intermediate sub-time periods, wherein the one or more intermediate sub-time periods are one or more sub-time periods within the scan time period other than the multiple target sub-time periods; and A sequence of target images of the object is generated based on the multiple target scan datasets and the one or more intermediate images.

13. The method according to claim 12, wherein, The step of determining multiple target scan datasets from the scan data based on preset conditions includes: The scan data is divided into multiple candidate scan datasets; For each of the plurality of candidate scan datasets, a three-dimensional (3D) count distribution map corresponding to the candidate scan dataset is determined, wherein the 3D count distribution map includes at least one pixel, and each pixel corresponds to a pixel value representing the count of coincidence events associated with the pixel; and Based on the multiple three-dimensional count distribution maps corresponding to the multiple candidate scan datasets, the multiple target scan datasets are determined, wherein the difference between the three-dimensional count distribution maps corresponding to two adjacent target scan datasets in the multiple target scan datasets is greater than or equal to a preset threshold.

14. The method according to claim 13, wherein, The determination of the plurality of target scan datasets based on the plurality of three-dimensional count distribution maps corresponding to the plurality of candidate scan datasets includes: The multiple three-dimensional count distribution maps are arranged in chronological order to form a map sequence; and The plurality of target scan datasets are determined by traversing the image sequence starting from the first three-dimensional count distribution map in the image sequence, wherein traversing the image sequence starting from the first three-dimensional count distribution map includes: The difference between the latest 3D count distribution map corresponding to the latest determined target scan dataset and each 3D count distribution map in the image sequence that follows the latest 3D count distribution map is determined sequentially until the difference between the latest 3D count distribution map and a 3D count distribution map that follows the latest 3D count distribution map is greater than or equal to the preset threshold, and the candidate scan dataset corresponding to the 3D count distribution map is determined as the target scan dataset.

15. The method according to claim 12, wherein, The step of determining multiple target scan datasets from the scan data based on preset conditions includes: Obtain the time-radioactivity profile of the tracer in the positron emission tomography (PET) scan; and The plurality of target scan datasets are determined from the scan data based on the time-radioactivity curves.

16. The method according to claim 13, wherein, The step of determining multiple target scan datasets from the scan data based on preset conditions includes: Obtain the life signal of the object corresponding to the scan data; The plurality of target scan datasets are determined from the scan data based on the vital signs.

17. The method according to any one of claims 12 to 16, wherein, The generation of one or more intermediate images corresponding to one or more intermediate sub-time periods includes: Generate multiple target images corresponding to the multiple target scan datasets, respectively; and One or more intermediate images are generated based on the multiple target images.

18. The method according to claim 17, wherein, The generation of multiple target images corresponding to the multiple target scanning datasets includes: Determine multiple initial images corresponding to the multiple target scan datasets respectively; and The plurality of target images are determined by performing denoising operations on the plurality of initial images using a denoising model and / or performing resolution improvement operations on the plurality of initial images using a resolution improvement model.

19. The method according to claim 18, wherein, The generation of one or more intermediate images corresponding to one or more intermediate sub-time periods includes: For each of the one or more target image pairs formed from the plurality of target images Use a motion field generation model to determine the motion field between images within the target image pair; and The image generation model is used to generate one or more intermediate images corresponding to the target image pair based on the sports field.

20. The method according to claim 19, wherein, The sports field generation model and the image generation model are integrated into a single model.

21. The method according to any one of claims 12 to 16, wherein, The process of generating the target image sequence of the object based on the plurality of target scan datasets and the one or more intermediate images includes: Generate multiple target images corresponding to the multiple target scan datasets, respectively; For each of the one or more image pairs formed by the plurality of target images and the one or more intermediate images Use a motion field generation model to determine the secondary motion field between images within the image pair; and Using an image generation model, one or more secondary intermediate images corresponding to the image pair are generated based on the secondary motion field; and The target image sequence of the object is generated based on the plurality of target images, the one or more intermediate images, and the one or more secondary intermediate images.

22. The method according to claim 21, wherein, The difference between the images within the image pair is greater than a preset difference threshold.

23. A positron emission tomography (PET) imaging system, comprising: The acquisition module is used to acquire scan data of an object obtained by positron emission tomography within a scanning time period; The determining module determines multiple target scan datasets from the scan data based on preset conditions, wherein each of the multiple target scan datasets corresponds to a target sub-time period in the scan time period; and Generate modules for: Based on the multiple target scan datasets, generate one or more intermediate images corresponding to one or more intermediate sub-time periods, wherein the one or more intermediate sub-time periods are one or more sub-time periods within the scan time period other than the multiple target sub-time periods; and A sequence of target images of the object is generated based on the multiple target scan datasets and the one or more intermediate images.

24. A non-transient computer-readable medium comprising at least one set of instructions for positron emission tomography (PET) imaging, wherein, When the at least one set of instructions is executed by one or more processors of a computing device, the computing device is caused to perform a method comprising: Acquire scan data of an object obtained by positron emission tomography within a scanning time period; Multiple target scan datasets are determined from the scan data based on preset conditions, wherein each of the multiple target scan datasets corresponds to a target sub-time period in the scan time period; Based on the multiple target scan datasets, generate one or more intermediate images corresponding to one or more intermediate sub-time periods, wherein the one or more intermediate sub-time periods are one or more sub-time periods within the scan time period other than the multiple target sub-time periods; and A sequence of target images of the object is generated based on the multiple target scan datasets and the one or more intermediate images.

25. A positron emission tomography (PET) imaging apparatus, comprising at least one processor and at least one storage device for storing an instruction set, wherein, When the instruction set is executed by the at least one processor, the apparatus performs the method of any one of claims 12 to 22.

Images