Positron emission tomography system and method

Abstract

The present application provides a method and system (100) for PET imaging. PET data (601) of a subject collected by performing a PET scan on the subject and physiological signals (602) related to physiological movement of the subject during the PET scan may be obtained. A plurality of gated PET images (603) corresponding to a plurality of physiological phases of the subject may be generated based on the PET data (601) and the physiological signals (602). Further, for each of the plurality of physiological phases, a first attenuation map (604) of the subject corresponding to the physiological phase is generated based on the gated PET image (603) corresponding to the physiological phase, and an attenuation-corrected gated PET image (605) corresponding to the physiological phase may be generated based on the first attenuation map and a portion of the PET data (601) corresponding to the physiological phase. A target PET image (613) corresponding to the reference physiological phase (608) may be generated based on the attenuation-corrected gated PET image (605).

Description

Technical Field

[0001] The present disclosure relates to medical imaging techniques, and more particularly to systems and methods for positron emission tomography (PET) imaging. Background Art

[0002] In recent years, PET imaging has been widely used in clinical examination and disease diagnosis. During the PET scan of the scanned subject, the physiological movement of the scanned subject may produce motion artifacts in the resulting image of the PET scan. Therefore, physiological motion correction is crucial for PET imaging. Summary of the invention

[0003] According to one aspect of the present disclosure, a system for positron emission tomography (PET) imaging may be provided. The system may include at least one storage device and at least one processor, the storage device including a set of instructions. When executing the instruction set, the at least one processor may be configured to instruct the system to perform the following operations. The system may acquire PET data of a subject collected by performing a PET scan on the subject and physiological signals associated with the physiological movement of the subject during the PET scan. The system may also generate a plurality of gated PET images corresponding to a plurality of physiological phases of the subject based on the PET data and the physiological signals. For each of the plurality of physiological phases, a first attenuation map of the subject corresponding to the physiological phase is generated based on the gated PET image corresponding to the physiological phase. In addition, for each of the plurality of physiological phases, an attenuation-corrected gated PET image corresponding to the physiological phase is generated based on the first attenuation map and a portion of the PET data corresponding to the physiological phase. Then, the system may generate a target PET image corresponding to a reference physiological phase in the plurality of physiological phases based on the attenuation-corrected gated PET images corresponding to the plurality of physiological phases.

[0004] In some embodiments, in order to obtain physiological signals related to the physiological motion of the subject during the PET scan, the system can determine a target area of ​​the subject affected by the physiological motion of the subject. The system can also determine a time activity curve (TAC) corresponding to the target area based on the PET data. In addition, the system can generate a physiological signal of the subject based on the TAC.

[0005] In some embodiments, in order to obtain physiological signals related to the physiological motion of the subject during the PET scan, the system can determine a target area affected by the physiological motion of the subject. For each time point during the PET scan, the distribution center of mass (COD) of the coincident events of the time point in the target area is determined based on the PET data. In addition, the system can generate a physiological signal of the subject based on the COD corresponding to each time point.

[0006] In some embodiments, for each of a plurality of physiological phases, based on a gated PET image corresponding to the physiological phase, a first attenuation map of a subject corresponding to the physiological phase is generated, and the system may perform the following operations. For each of a plurality of physiological phases, the system may generate a first attenuation map of the subject corresponding to the physiological phase by processing the gated PET image corresponding to the physiological phase using an attenuation map generation model. The attenuation map generation model is a trained machine learning model.

[0007] In some embodiments, the attenuation map generation model can be generated according to a model training process. The system can obtain multiple training samples, each training sample including a sample gated PET image and a ground-true attenuation map of a sample subject. The sample gated PET image and the ground-true attenuation map correspond to the same physiological phase of the sample subject. In addition, the system can generate the attenuation map generation model by training a preliminary model using multiple training samples.

[0008] In some embodiments, a target PET image corresponding to a reference physiological phase among the plurality of physiological phases is generated based on the attenuation-corrected gated PET images corresponding to the plurality of physiological phases. The system may determine a first attenuation-corrected gated PET image corresponding to the reference physiological phase and one or more second attenuation-corrected gated PET images corresponding to physiological phases other than the reference physiological phase from the attenuation-corrected gated PET images. For each of the one or more second attenuation-corrected gated PET images, the second attenuation-corrected gated PET image is transformed to generate a transformed gated PET image corresponding to the reference physiological phase. In addition, the system may generate a target PET image based on the first attenuation-corrected gated PET image and the one or more transformed gated PET images.

[0009] In some embodiments, the system may also perform the following operations. The system may obtain a second attenuation map of the subject generated based on a computed tomography (CT) scan of the subject. The system may also select a reference attenuation map having the highest similarity to the second attenuation map from the first attenuation maps corresponding to the plurality of physiological phases. The system may determine the physiological phase corresponding to the reference attenuation map as the reference physiological phase.

[0010] In some embodiments, for each of the one or more second attenuation-corrected gated PET images, the second attenuation-corrected gated PET image is transformed to generate a transformed gated PET image corresponding to a reference physiological phase, and the system may also perform the following operations. The system may determine a target region affected by physiological motion of the subject. For each of the one or more second attenuation-corrected gated PET images, the system may determine a motion field between a first region of the first attenuation-corrected gated PET image corresponding to the target region and a second region of the second attenuation-corrected gated PET image corresponding to the target region. In addition, the system may transform the second region in the second attenuation-corrected gated PET image based on the motion field to generate a transformed gated PET image corresponding to the reference physiological phase.

[0011] In some embodiments, the system may also perform the following operations. The system may acquire a second attenuation map of the subject generated based on a computed tomography (CT) scan of the subject. The system may determine a motion field between the second attenuation map and the first attenuation map corresponding to a reference physiological phase. In addition, the system may generate a PET image matched to a physiological phase corresponding to the CT scan based on the motion field and the target PET image.

[0012] In some embodiments, the plurality of gated PET images may be tissue images.

[0013] In some embodiments, the plurality of gated PET images may be non-attenuation corrected (NAC) PET images.

[0014] According to another aspect of the present disclosure, a method for PET imaging may be provided. The method may be implemented on a computing device having at least one storage device and at least one processor. The method may include acquiring PET data of a subject collected by performing a PET scan on the subject and a physiological signal associated with the physiological movement of the subject during the PET scan. The method may also include generating a plurality of gated PET images corresponding to a plurality of physiological phases of the subject based on the PET data and the physiological signal. The method may also include, for each of the plurality of physiological phases, generating a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase. The method may also include, for each of the plurality of physiological phases, generating an attenuation-corrected gated PET image corresponding to the physiological phase based on the first attenuation map and a portion of the PET data corresponding to the physiological phase. The method may also include generating a target PET image corresponding to a reference physiological phase among the plurality of physiological phases based on the attenuation-corrected gated PET image corresponding to the plurality of physiological phases.

[0015] According to another aspect of the present disclosure, a system for PET imaging may be provided. The system may include an acquisition module, a first generation module, a second generation module, a third generation module, and a fourth generation module. The acquisition module may be configured to acquire PET data of a subject collected by performing a PET scan on the subject and a physiological signal related to the physiological movement of the subject during the PET scan. The first generation module may be configured to generate a plurality of gated PET images corresponding to a plurality of physiological phases of the subject based on the PET data and the physiological signal. The second generation module may be configured to, for each of the plurality of physiological phases, generate a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase. The third generation module may be configured to, for each of the plurality of physiological phases, generate an attenuation-corrected gated PET image corresponding to the physiological phase based on the first attenuation map and a portion of the PET data corresponding to the physiological phase. The fourth generation module may be configured to generate a target PET image corresponding to a reference physiological phase among the plurality of physiological phases based on the attenuation-corrected gated PET image corresponding to the plurality of physiological phases.

[0016] According to another aspect of the present disclosure, a non-transitory computer-readable medium may be provided. The non-transitory computer-readable medium may include at least one set of instructions for PET imaging. When executed by one or more processors of a computing device, the at least one set of instructions may cause the computing device to perform a method. The method may include acquiring PET data of a subject collected by performing a PET scan on the subject and a physiological signal associated with the physiological movement of the subject during the PET scan. The method may also include generating a plurality of gated PET images corresponding to a plurality of physiological phases of the subject based on the PET data and the physiological signal. The method may also include, for each of the plurality of physiological phases, generating a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase. The method may also include, for each of the plurality of physiological phases, generating an attenuation-corrected gated PET image corresponding to the physiological phase based on the first attenuation map and a portion of the PET data corresponding to the physiological phase. The method may also include generating a target PET image corresponding to a reference physiological phase among the plurality of physiological phases based on the attenuation-corrected gated PET images corresponding to the plurality of physiological phases.

[0017] According to another aspect of the present disclosure, a device for PET imaging may be provided. The device may include at least one processor and at least one storage device for storing a set of instructions. When the set of instructions is executed by at least one processor, the device may perform the method of the present disclosure.

[0018] Additional features will be described in the following description, and some of the additional characteristics of this specification will be apparent to those skilled in the art through study of the following description and the corresponding drawings or understanding of the production or operation of the embodiments. The features of the present application can be realized and achieved through the practice or use of the methods, means and combinations of various aspects of the specific embodiments described below. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present application is further described according to exemplary embodiments. These exemplary embodiments are described in detail with reference to the accompanying drawings. These embodiments are non-limiting exemplary embodiments, in which the same reference numerals represent similar structures throughout the multiple views of the drawings, and in which:

[0020] Figure 1 is a schematic diagram of an exemplary PET system according to some embodiments of the present disclosure;

[0021] Figure 2 is a block diagram of an exemplary processing device according to some embodiments of the present disclosure;

[0022] Figure 3 is a flowchart of an exemplary process for generating a target PET image according to some embodiments of the present disclosure;

[0023] Figure 4 is a flowchart of an exemplary process for generating an attenuation map generation model according to some embodiments of the present disclosure;

[0024] Figure 5 is a flowchart of an exemplary process for generating a target PET image by performing physiological motion correction according to some embodiments of the present disclosure; and

[0025] Figure 6 is a schematic diagram of an exemplary process of PET imaging according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0026] In the detailed description that follows, many 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 implemented without these details. In other cases, in order to avoid unnecessarily obscuring various aspects of the present application, well-known methods, processes, systems, components and / or circuits have been described at a higher level. Various modifications to the disclosed embodiments will be apparent to those skilled in the art, and the general principles defined in this specification may 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 in accordance with the widest scope consistent with the claims.

[0027] The terms used in this specification are only used to describe specific example embodiments and are not intended to be limiting. As used in this specification, the singular forms "a", "an", and "the" may also be intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the terms "include" and / or "comprise" when used in this specification specify the presence of stated features. Integers, steps, operations, elements and / or components, but do not exclude the presence and addition of at least one other feature, integer, step, operation, element, component and / or combination thereof.

[0028] It should be understood that the terms "system", "engine", "unit", "module" and / or "block" used herein are a method of distinguishing different components, elements, parts, portions or assemblies at different levels in ascending order. However, if these terms achieve the same purpose, they may be replaced by another expression.

[0029] It should be understood that when a unit, engine, module or block is referred to as being "on," "connected to," or "coupled to" another unit, engine, module or block, it may be directly connected or coupled to, or in communication with, the other unit, engine, module or block, or there may be intermediate units, engines, modules or blocks, unless the context clearly indicates otherwise. As used in this specification, the term "and / or" includes any and all combinations of at least one of the associated listed items.

[0030] The terms "pixel" and "voxel" in this application are used interchangeably to refer to elements of an image. The anatomical structures displayed in an image of a subject (e.g., a patient) may correspond to actual anatomical structures present in or on the body of the subject. The terms "subject" and "subject" in this application may be used interchangeably to refer to a biological subject (e.g., a patient, an animal) or a non-biological subject (e.g., a phantom). In some embodiments, a subject may include a specific part, organ, and / or tissue of a subject. For example, a subject may include a patient's head, bladder, brain, neck, torso, shoulders, arms, chest, heart, stomach, blood vessels, soft tissue, knees, feet, etc., or any combination thereof.

[0031] These and other features, as well as the features of the present application, as well as the methods of operation and function of the related structural elements and the combination and manufacturing economy of the parts, may become more apparent after considering the following description with reference to the accompanying drawings, all of which form a part of this application. However, it is to be expressly understood that the drawings are for illustration and description purposes only and are not intended to limit the scope of the present disclosure. It is understood that the drawings are not drawn to scale.

[0032] PET scanning can be used in conjunction with CT scanning to achieve simultaneous acquisition of structural and functional information of a subject. CT scanning and PET scanning are performed on the same subject to acquire CT data and PET data. The PET data are selected as multiple sets of gated PET data, and an attenuation map is generated based on the CT data to perform attenuation correction on the gated PET data. Traditional physiological motion correction methods usually generate attenuation-corrected gated PET images by reconstructing a gated PET data set based on the attenuation map, and further transforming the attenuation-corrected gated PET image to generate a transformed gated PET image corresponding to the same physiological phase. Finally, a target PET image of the subject is generated by summing the transformed gated PET map. However, CT scanning is very fast, and the CT data may correspond to the same or substantially the same physiological phase, while the gated PET data set may correspond to multiple physiological phases, that is, the phase of the gated PET data set and the attenuation map of the subject generated based on the CT scan are usually different, which may acquire a low-precision attenuation-corrected gated PET image, which then generates artifacts in the target PET image, resulting in low precision of the target PET image, which in turn may affect the interpretation of the target PET image or the diagnosis based on the target PET image. In addition, conventional physiological motion correction methods focus on how to reduce the displacement between gated PET images by performing physiological motion correction on the gated PET images, without considering the phase mismatch between the target PET image and the CT image generated based on the subject's CT scan, which may result in a low image accuracy of the fused image of the target PET image and the CT image. Therefore, it is desirable to provide a system and method for physiological motion correction in PET imaging with improved image quality.

[0033] As one aspect of the present disclosure, a system and method for PET imaging are provided. The system can acquire PET data of a subject collected by performing a PET scan on the subject and physiological signals related to the physiological movement of the subject during the PET scan. The system can generate a plurality of gated PET images corresponding to a plurality of physiological phases of the subject based on the PET data and the physiological signals. For each of the plurality of physiological phases, the system can generate a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase, and further generate an attenuation-corrected gated PET image corresponding to the physiological phase based on the first attenuation map and a portion of the PET data corresponding to the physiological phase (i.e., a set of gated PET data). Then, the system can generate a target PET image corresponding to a reference physiological phase among the plurality of physiological phases based on the attenuation-corrected gated PET images corresponding to the plurality of physiological phases.

[0034] Compared with traditional physiological motion correction methods, the method and system disclosed in the present invention can generate an attenuation-corrected gated PET image with better attenuation correction effect by using a first attenuation map that matches the physiological phase with the gated PET data set, thereby improving the image quality of the target PET image, that is, improving the imaging quality of PET imaging.

[0035] In addition, according to some embodiments, the system can also obtain a second attenuation map of the subject generated based on the CT scan of the subject, and determine the motion field between the second attenuation map and the first attenuation map corresponding to the reference physiological phase. Then, the system can generate a PET image that matches the physiological phase corresponding to the CT scan based on the motion field and the target PET image. In this way, the method and system of the present disclosure can further improve the imaging quality of PET imaging by performing physiological motion correction on the target PET image relative to the CT image.

[0036] Figure 1 is a schematic diagram of an exemplary PET system according to some embodiments of the present disclosure. 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 may be connected in various ways.

[0037] The PET scanner 110 may be configured to acquire scan data associated with a subject. For example, the PET scanner 110 may scan a subject or a portion thereof within its detection region and generate scan data associated with the subject or the portion thereof.

[0038] In some embodiments, the PET scanner 110 may include a gantry 112, a bed 114, and a detector 116. The gantry 112 may support the detector 116. The bed 114 may be used to support a subject 118 to be scanned. The detector 116 may include an axial direction (e.g., Figure 1 In some embodiments, the detector 116 may include a plurality of detector rings arranged along the Z-axis direction of the detector ring. In some embodiments, the detector 116 may include a scintillation detector (e.g., a cesium iodide detector), a gas detector, etc., or any combination thereof.

[0039] In some embodiments, a tracer substance may be injected into the subject 118 prior to the PET scan. The tracer substance may refer to a radioactive substance that decays and emits positrons. In some embodiments, the tracer substance may be a radioactive labeled radiopharmaceutical, which is a radioactive drug that is administered to the subject 118. For example, the tracer substance may include fluorine-18 (18F) fluorodeoxyglucose (FDG), etc. During the scan, pairs of photons (e.g., gamma photons) may be caused by the annihilation of positrons generated by the tracer substance in the subject 118. A pair of photons may propagate in opposite directions. The detector unit in the detector 116 may detect and / or record at least a portion of the photon pair. When a pair of photons generated by the positron annihilation is detected within the coincidence time window (e.g., within 6 to 12 nanoseconds), a coincidence event may be recorded. It may be assumed that the coincidence event occurs on a line connecting a pair of detector units, which may be referred to as a "line of response" (LOR). The detector 116 may obtain a count of coincidence events based on the LOR of the detected coincidence events and the time points at which the coincidence events occurred.

[0040] In some embodiments, the PET scanner 110 may also be a multi-modality scanner, such as a positron emission tomography-computed tomography (PET-CT) scanner, etc.

[0041] The 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., the PET scanner 110, the terminal device 130, the processing device 140, the storage device 150) can send information and / or data to other components in the PET system 100 via the network 120. For example, the processing device 140 can obtain scan data related to the subject 118 or a portion thereof from the PET scanner 110 via the network 120. In some embodiments, the network 120 can be any type of wired or wireless network, or a combination thereof.

[0042] The terminal device 130 may include a mobile device 130-1, a tablet computer 130-2, a laptop computer 130-3, etc., or any combination thereof. In some embodiments, the terminal device 130 may remotely operate the PET scanner 110. In some embodiments, the terminal device 130 may operate the PET scanner 110 via a wireless connection. In some embodiments, the terminal device 130 may receive information and / or instructions input by a user, and send the received information and / or instructions to the PET scanner 110 or the processing device 140 via the network 120. In some embodiments, the terminal device 130 may receive data and / or information from the processing device 140. In some embodiments, the terminal device 130 may be a part of the processing device 140. In some embodiments, the terminal device 130 may be omitted.

[0043] The processing device 140 may process data acquired from the PET scanner 110, the terminal device 130, the storage device 150, or other components of the PET system 100. In some embodiments, the processing device 140 (e.g., Figure 2 One or more modules shown in ) can perform the method of the present disclosure. For example, any of processes 300, 400, or 500 can be implemented as a set of instructions (e.g., an application) stored in a storage device (e.g., storage device 150). Processing device 140 can execute the set of instructions and can be instructed to execute processes 300, 400, or 500 accordingly. As an example only, processing device 140 can obtain scanning data (e.g., PET data) of a subject (e.g., a human body) from PET scanner 110 or storage device 150, and by executing process 300, generate a target PET image of the subject or a respiratory phase-matched PET image based on the scanning data of the subject.

[0044] In some embodiments, the processing device 140 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processing device 140 may be local or remote. For illustration only, only one processing device 140 is described in the medical system 100. However, it should be noted that the medical system 100 in the present disclosure may also include multiple processing devices. Therefore, as described in the present disclosure, the operations and / or method steps performed by one processing device 140 may also be performed jointly or individually by multiple processing devices. For example, if in the present disclosure, the processing device 140 of the medical system 100 simultaneously executes process A and process B, it should be understood that process A and process B may also be jointly or individually executed by two or more different processing devices in the medical system 100 (for example, the first processing device executes process A, the second processing device executes process B, or the first and second processing devices jointly execute processes A and B).

[0045] 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 collected by PET scanner 110. As another example, storage device 150 may store a target PET image of a subject. In some embodiments, storage device 150 may store data and / or instructions that processing device 140 may execute or use to execute the exemplary methods described in the present disclosure.

[0046] 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 the present disclosure. For those of ordinary skill in the art, various changes and modifications may be made in light of the teachings of the present disclosure. 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. Additionally or 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.

[0047] Figure 2 is a block diagram of an exemplary processing device according to some embodiments of the present disclosure.

[0048] like Figure 2 As shown, the processing device 140 may include an acquisition module 210, a first generation module 220, a second generation module 230, a third generation module 240, and a fourth generation module 250. In some embodiments, the processing device 140 may also include a fifth generation module 260. Figure 1 As shown, the medical system 100 in the present disclosure may also include multiple processing devices, and the first generation module 220, the second generation module 230, the third generation module 240, the fourth generation module 250 and the fifth generation module 260 may be components of different processing devices.

[0049] The acquisition module 210 can be configured to acquire PET data of a subject collected by performing a PET scan on the subject and physiological signals related to physiological motion of the subject during the PET scan. More description on acquiring PET data of a subject can be found elsewhere in this disclosure. For example, see Figure 3 Step 310 and its related description in .

[0050] The first generation module can be configured to generate a plurality of gated PET images corresponding to a plurality of physiological phases of the subject based on the PET data and the physiological signal. More descriptions on generating a plurality of gated PET images can be found elsewhere in this disclosure. For example, see Figure 3 Step 320 and its related description in .

[0051] The second generation module can be configured to, for each of the plurality of physiological phases, generate a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase. More descriptions on the generation of the first attenuation map of the subject can be found elsewhere in this disclosure. For example, see Figure 3 Step 330 and its related description in .

[0052] The third generation module can be configured to, for each of the plurality of physiological phases, generate an attenuation-corrected gated PET image corresponding to the physiological phase based on the first attenuation map and a portion of the PET data corresponding to the physiological phase. More descriptions of the generation of attenuation-corrected gated PET images corresponding to the physiological phase can be found elsewhere in the present disclosure. For example, see Figure 3 Step 340 and its related description in .

[0053] The fourth generation module may be configured to generate a target PET image corresponding to a reference physiological phase among the plurality of physiological phases based on the attenuation-corrected gated PET images corresponding to the plurality of physiological phases. More descriptions on the generation of the target PET image corresponding to the reference physiological phase may be found elsewhere in the present disclosure. For example, see Figure 3 Step 350 and its related description in .

[0054] The fifth generation module 260 can be configured to generate a physiological phase-matched PET image based on the target PET image. The physiological phase-matched PET image can have a physiological phase that matches the CT image (e.g., the same physiological phase or substantially the same physiological phase). More description of the generation of physiological phase-matched PET images can be found elsewhere in this disclosure. For example, see Figure 3 Step 360 and its related description in .

[0055] It should be noted that the above description is for illustrative purposes only and is not intended to limit the scope of the present disclosure. For those of ordinary skill in the art, various changes and modifications can be made under the teachings of the present disclosure. However, these changes and modifications do not depart from the scope of the present disclosure. In some embodiments, any one of the modules can be divided into two or more units. For example, the acquisition module 210 can be divided into two units for acquiring different data. In some embodiments, the processing device 140 may include one or more additional modules, for example, a storage module (not shown) for storing data.

[0056] Figure 3 is a flowchart of an exemplary process for generating a target PET image according to some embodiments of the present disclosure.

[0057] In step 310 , the processing device 140 (eg, the acquisition module 210 ) may acquire PET data of the subject collected by performing a PET scan on the subject and a physiological signal associated with the physiological motion of the subject during the PET scan.

[0058] In some embodiments, the physiological motion may include cardiac motion, respiratory motion, etc. The physiological signal is generated by the physiological motion. Exemplary physiological signals may include heartbeat signals, respiratory signals, etc., or any combination thereof.

[0059] In some embodiments, PET data can be collected by scanning a region of interest (ROI) of a subject by a PET scanner 110. The subject can include a patient, an animal, a phantom, or a portion thereof, including, for example, a prosthesis, an artificial heart, a tumor, any structure or organ that can be inspected using X-rays, etc., or any combination thereof. The ROI can include any part of the subject. For example, the ROI can include the entire body of the subject. Alternatively, the ROI can be a part of the subject, for example, the brain, lungs, liver, kidneys, bones, etc. In some embodiments, the ROI can include at least a portion of the chest and abdomen of the subject.

[0060] In some embodiments, the PET scan may be performed in one or more bed positions, that is, the PET data may include data collected when the bed is in one or more specific positions. In some embodiments, the processing device 140 may obtain the PET data directly from the PET scanner 110. In some embodiments, the PET data may be previously collected and stored in a storage device (e.g., the storage device 150 or an external source). The processing device 140 may retrieve the PET data directly from the storage device.

[0061] In some embodiments, processing device 140 may generate a physiological signal based on PET data of the subject.

[0062] In some embodiments, the processing device 140 can determine the target area of ​​the subject affected by the physiological movement of the subject. For example, the target area can include at least a portion of the subject's chest and abdomen area. As an example only, the target area can correspond to the portion surrounded by the subject's ribs and spine in the subject's chest and abdomen area, and the subject's ribs and spine can be excluded from the target area. As used herein, the chest and abdomen area can refer to the area including the chest and abdominal cavity and the muscle skin of the ribs and spine surrounding the chest and abdominal cavity. When the subject breathes during the scanning process, the internal organs in the chest and abdomen area may move (this movement can be called physiological movement). The portion outside the chest and abdominal cavity may have no or almost no physiological movement.

[0063] In addition, the processing device 140 can determine a time activity curve (TAC) corresponding to the target area based on the PET data. Specifically, the processing device 140 can divide the PET data into multiple groups of PET data, each group of PET data is collected within a period of time (e.g., 100 milliseconds, 150 milliseconds, etc.) during the PET scan. For each of the multiple groups of PET data, the processing device 140 can reconstruct an initial PET image and determine the pixel average of an area in the initial PET image corresponding to the target area of ​​the subject. In addition, the processing device 140 can generate a TAC corresponding to the target area based on the time period and the average value of the pixels corresponding to the initial PET image. For example, the processing device 140 can determine a point in a first coordinate system based on the time period and the average value of the pixels corresponding to the initial PET image, wherein the first coordinate system uses the average value of time and pixels as two coordinate axes. Then, the processing device 140 can generate a TAC corresponding to the target area by fitting the points in the first coordinate system.

[0064] Then, the processing device 140 may generate a physiological signal of the subject based on the TAC. For example, the processing device 140 may generate a frequency curve corresponding to the TAC by converting the TAC from a time domain signal to a frequency domain signal. The processing device 140 may perform a filtering operation on the frequency curve to generate a target frequency curve corresponding to the physiological signal. In addition, the processing device 140 may generate a physiological signal by converting the target frequency curve from a frequency domain signal to a time domain signal.

[0065] In some embodiments, for each time point during the PET scan, the processing device 140 can determine the distribution center of mass (COD) of the coincident events in the target area at that time point based on the PET data. In addition, the processing device 120 can generate a physiological signal of the subject based on the COD corresponding to each time point. For example, the processing device 140 can determine a point in a second coordinate system based on the time point and the corresponding COD, wherein the second coordinate system uses time and COD as two coordinate axes. Then, the processing device 140 can generate a COD curve corresponding to the target area by fitting the points in the second coordinate system.

[0066] In some embodiments, the COD at a time point can be represented by a three-dimensional (3D) spatial position. The processing device 140 can generate three COD curves, each corresponding to a dimension of the 3D spatial position. The processing device 140 can select one of the three COD curves as the target COD curve. For example, the processing device 140 can select a COD curve with the largest signal-to-noise ratio from the three COD curves as the target COD curve. Then, the processing device 120 can generate a physiological signal of the subject based on the target COD curve. For example, the processing device 140 can generate a physiological signal of the subject in a manner similar to how to generate a physiological signal based on TAC.

[0067] In some embodiments, the breathing signal can be obtained from a source other than PET data. For example, the breathing signal can be collected by a physiological detection device (e.g., a chest strap, a chest reflector module, a radar device, etc.). The processing device 140 can obtain the physiological signal from the physiological detection device.

[0068] In step 320 , the processing device 140 (eg, the first generating module 220 ) may generate a plurality of gated PET images corresponding to a plurality of physiological phases of the subject based on the PET data and the physiological signal.

[0069] In some embodiments, exemplary physiological phases of the subject may include a mid-inspiratory phase, an end-inspiratory phase, a mid-expiratory phase, an end-expiratory phase, the like, or any combination thereof.

[0070] In some embodiments, the physiological signal can be divided into a plurality of parts, each of which corresponds to one of a plurality of physiological phases. In some embodiments, the physiological signal can be divided according to the amplitude of the physiological signal. For example, the cycle of the physiological signal can be divided based on the amplitude of the physiological signal. The amplitude of the physiological signal is evenly divided into n parts (e.g., from the maximum amplitude to the minimum amplitude), thereby generating n physiological signal parts corresponding to n physiological phases. In some embodiments, the physiological signal can be divided into N parts based on the time of the physiological signal, and these N parts can correspond to N physiological phases. For example, if one cycle of the physiological signal lasts for 5 seconds, one cycle of the physiological signal can be divided according to a unit interval (e.g., 0.5 seconds, or 1 second), and this cycle of the physiological signal can be divided into N physiological phases (e.g., 5 / 0.5 physiological phases or 5 / 1 physiological phases). In some embodiments, the physiological signal can be divided according to the count of coincident events. For example, one cycle of the physiological signal can be divided into multiple physiological phases according to the same coincident event count, that is, substantially the same number of coincident events are detected in each physiological phase. Multiple physiological phases can correspond to the same count of coincident events.

[0071] In addition, the processing device 140 may divide the gated PET data into multiple groups of gated PET data based on multiple physiological phases of the respiratory signal. Each group of gated PET data may correspond to one of the multiple physiological phases. For example, the physiological signal may include N physiological phases, and the processing device 140 may divide the gated PET data into N groups of gated PET data, each group of gated PET data corresponding to one of the N physiological phases. When the subject is in a specific physiological phase, a group of gated PET data corresponding to the specific physiological phase is collected.

[0072] In some embodiments, the processing device 140 may reconstruct a gated PET image for each physiological phase based on the corresponding gated PET data set using a reconstruction algorithm. Exemplary reconstruction algorithms may include a maximum likelihood reconstruction (MLAA) algorithm for attenuation and activity, an iterative reconstruction algorithm (e.g., a statistical reconstruction algorithm), a Fourier slice theorem algorithm, a filtered back projection (FBP) algorithm, a compressed sensing (CS) algorithm, a fan-beam reconstruction algorithm, a maximum likelihood expectation maximization (MLEM) algorithm, an ordered subset expectation maximization, a maximum a posteriori (MAP) algorithm, an analytical reconstruction algorithm, etc., or any combination thereof. Since the reconstruction in step 320 is performed without any attenuation map, the reconstructed image generated in step 320 may be regarded as a gated PET image without attenuation correction.

[0073] In some embodiments, the PET data may be in the form of list mode, sinograms, etc. The gated PET images may be in the form of non-attenuation corrected (NAC) PET images, tissue images.

[0074] In step 330 , for each of the plurality of physiological phases, the processing device 140 (eg, the second generating module 230 ) may generate a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase.

[0075] In PET scanning, since different tissues have different attenuation degrees for gamma rays, when gamma rays pass through different tissues of the subject, different degrees of attenuation may occur, thereby causing distortion of the PET image and / or PET scan data. In PET reconstruction, attenuation correction is required. The attenuation map of the subject can indicate the tissue attenuation coefficients corresponding to different parts of the subject (e.g., different organs, different tissues).

[0076] Usually, the same attenuation map is used to reconstruct attenuation-corrected gated PET images corresponding to different physiological phases, and it is undesirable to produce an attenuation correction effect on the attenuation-corrected gated PET images. In the present disclosure, different first attenuation maps corresponding to different physiological phases are generated for generating attenuation-corrected gated PET images to improve the attenuation correction effect. In addition, it should be noted that the first attenuation map disclosed herein is generated based on the gated PET image rather than CT data, and the first attenuation map can be regarded as a predicted or simulated attenuation map.

[0077] In some embodiments, for each of a plurality of physiological phases, the processing device 140 may generate a first attenuation map of the subject corresponding to the physiological phase by processing the gated PET image corresponding to the physiological phase using an attenuation map generation model. The attenuation map generation model may be a trained machine learning model for generating attenuation maps. As an example only, the gated PET image corresponding to the physiological phase may be input into the attenuation map generation model, and the attenuation map generation model may output a first attenuation map of the subject corresponding to the physiological phase. The attenuation map generation model may be a deep learning model, such as a deep neural network (DNN) model, a convolutional neural network (CNN) model, a recurrent neural network, a feature pyramid network (FPN) model, a generative adversarial network (GAN) model, a Transformer model, a diffusion model, and the like. Exemplarily, the CNN model may include a V-Net model, a U-Net model, a Link Net model, and the like, or any combination thereof. According to some embodiments, the attenuation map generation model may be used to generate a first attenuation map of the subject, which may greatly reduce radiation to the subject. In addition, since the attenuation map generation model may learn the best mechanism for generating attenuation maps based on a large amount of data, the first attenuation map generated using the attenuation map generation mode may be relatively accurate.

[0078] In some embodiments, the processing device 140 may obtain the attenuation map generation model from one or more components (e.g., storage device 150, terminal device 130) of the PET system 100 or an external source through a network (e.g., network 120). For example, the attenuation map generation model may be pre-trained by a computing device (e.g., processing device 140) and stored in a storage device (e.g., storage device 150) of the PET system 100. The processing device 140 may access the storage device and retrieve the attenuation map generation model. In some embodiments, the attenuation map generation model may be generated according to process 400.

[0079] In step 340 , for each of the plurality of physiological phases, the processing device 140 (eg, the third generating module 240 ) may generate an attenuation-corrected gated PET image corresponding to the physiological phase based on the first attenuation map and a portion of the PET data corresponding to the physiological phase.

[0080] In some embodiments, for each of the plurality of physiological phases, the processing device 140 may reconstruct an attenuation-corrected gated PET image corresponding to the physiological phase based on the first attenuation map and the gated PET data set corresponding to the physiological phase using a reconstruction algorithm described elsewhere in the present disclosure. Since the reconstruction in step 340 is performed using the first attenuation map, the reconstructed image generated in step 340 may be considered an attenuation-corrected gated PET image.

[0081] In step 350 , the processing device 140 (eg, the fourth generating module 250 ) may generate a target PET image corresponding to a reference physiological phase among the multiple physiological phases based on the attenuation-corrected gated PET images corresponding to the multiple physiological phases.

[0082] In some embodiments, the processing device 140 or the user may select a physiological phase from a plurality of physiological phases as a reference physiological phase. For example, the processing device 140 randomly selects a physiological phase from a plurality of physiological phases as a reference physiological phase. As another example, the user may select the end-expiratory phase as the reference physiological phase. For simplicity, the first attenuation map corresponding to the reference physiological phase is referred to as the reference attenuation map.

[0083] In some embodiments, the processing device 140 can acquire a second attenuation map of the subject based on a computed tomography (CT) scan of the subject. The CT scan can be performed before or after the PET scan. The field of view (FOV) of the CT scan and the PET scan can cover at least the same ROI of the subject. For example, if the ROI of the subject is the subject's chest, a CT scan is first performed on the subject's chest, and a PET scan can be performed on the subject's chest while the subject maintains substantially the same patient position. In some embodiments, the processing device 140 can acquire CT data collected by a CT scan of the subject from a PET system 100 (e.g., a PET-CT scanner) and generate a second attenuation map of the subject generated based on the CT data.

[0084] In addition, the processing device 140 may determine the reference physiological phase based on the similarity between each of the second attenuation map and the first attenuation map. For example, the processing device 140 may select a reference attenuation map having the highest similarity to the second attenuation map from the first attenuation map, and determine the physiological phase corresponding to the reference attenuation map as the reference physiological phase.

[0085] The similarity between the second attenuation map and the first attenuation map may be represented by mutual information (MI), normalized mutual information (NMI), mean square error (MSE), structural similarity (SSIM), etc. between the two maps. In some embodiments, the processing device 140 may use a similarity algorithm to determine the similarity between the second attenuation map and the first attenuation map. Exemplary similarity algorithms may include a histogram-based algorithm, an algorithm based on Euclidean distance, an algorithm based on Pearson's correlation coefficient, an algorithm on cosine similarity, a hashing algorithm, etc. In this way, the reference physiological phase may have a minimum phase difference with the physiological phase of the CT scan.

[0086] In some embodiments, the processing device 140 may determine a first region corresponding to the target region of the subject in the first attenuation map and a second region corresponding to the target region of the subject in the second attenuation map. The processing device 140 may determine the similarity between the first region and the second region, and designate the similarity between the first region and the second region as the similarity between the first attenuation map and the second attenuation map. In this way, the efficiency of determining the reference physiological phase may be improved by reducing the amount of data processing.

[0087] In some embodiments, the processing device 140 may determine, from the attenuation-corrected gated PET image, a first attenuation-corrected gated PET image corresponding to a reference physiological phase and one or more second attenuation-corrected gated PET images corresponding to physiological phases other than the reference physiological phase. In addition, for each of the one or more second attenuation-corrected gated PET images, the processing device 140 may transform the second attenuation-corrected gated PET image to generate a transformed gated PET image corresponding to the reference physiological phase. The processing device 140 may then generate a target PET image based on the first attenuation-corrected gated PET image and the one or more transformed gated PET images. More description of generating a target PET image based on the first attenuation-corrected gated PET image and the one or more transformed gated PET images may be found elsewhere in the present disclosure (e.g., Figure 5 and its description).

[0088] In some embodiments, the processing device 140 may designate the target PET image as a final PET image of the subject for use in clinical examination or disease diagnosis, etc.

[0089] In some embodiments, the processing device 120 may generate a fused image including functional information and anatomical information of the subject by directly combining the target PET image and the CT image generated based on the CT data.

[0090] In some embodiments, the processing device 140 may also perform physiological motion correction on the target PET image relative to the CT image at step 360 to obtain a fused image of the subject.

[0091] In step 360 , the processing device 140 (eg, the fifth generation module 260 ) may generate a physiological phase-matched PET image based on the target PET image.

[0092] The physiological phase matched PET image may have a physiological phase that matches the CT image (eg, the same physiological phase or substantially the same physiological phase).

[0093] In some embodiments, the processing device 140 may determine a motion field between the second attenuation map corresponding to the reference physiological phase (i.e., the reference attenuation map) and the first attenuation map. In some embodiments, the processing device 140 may determine the motion field between the second attenuation map and the reference attenuation map in a manner similar to how the motion field between the second attenuation-corrected gated PET image and the first attenuation-corrected gated PET image is determined as described in step 520, and the description thereof will not be repeated here.

[0094] The processing device 140 may then generate a physiological phase-matched PET image based on the motion field and the target PET image. For example, the processing device 140 may transform (or distort) the target PET image based on the motion field between the second attenuation map and the reference attenuation map to generate a physiological phase-matched PET image. In some embodiments, the processing device 140 may transform the target PET image to generate a physiological phase-matched PET image in a manner similar to the manner in which the second attenuation-corrected gated PET image is transformed to generate the transformed gated PET image described in step 520, and its description is not repeated here.

[0095] The processing device 140 may combine the physiological phase-matched PET image and the CT image into a final PET image of the subject.

[0096] As described elsewhere in the present disclosure, conventional physiological motion correction methods typically use a subject attenuation map generated based on a CT scan of the subject to perform attenuation correction on a gated PET image of the subject, thereby acquiring a target PET image with low accuracy. Compared to conventional physiological motion correction methods, according to some embodiments of the present disclosure, the processing device 140 can generate an attenuation-corrected gated PET image with an improved attenuation correction effect by using a first attenuation map of the subject at a physiological phase that matches the gated PET data set, thereby improving the image quality of the target PET image. In addition, in some embodiments, the processing device 140 can determine a reference physiological phase having a minimum phase difference with the physiological phase of the CT scan based on the similarity between the second attenuation map and the first attenuation map, thereby improving the accuracy of the subject fusion image acquired by combining the target PET image and the CT image, thereby improving the imaging quality of PET imaging.

[0097] In addition, according to some embodiments, the processing device 140 can generate a physiological phase-matched PET image corresponding to the CT scan by performing physiological motion correction on the target PET image relative to the CT image, which can further improve the accuracy of the subject's fusion image, thereby further improving the imaging quality of PET imaging.

[0098] It should be noted that the above description of process 300 is for illustrative purposes only and is not intended to limit the scope of the present disclosure. For those of ordinary skill in the art, various changes and modifications can be made under the teachings of the present disclosure. However, these changes and modifications do not depart from the scope of the present disclosure. In some embodiments, process 300 can be implemented by one or more additional operations not described and / or without one or more of the above operations. For example, the processing device 140 can send the attenuation-corrected gated PET image, the target PET image, and the physiological phase-matched PET image to a terminal device (e.g., the terminal device 130) for display.

[0099] Figure 4 is a flowchart of an exemplary process for generating an attenuation map generation model according to some embodiments of the present disclosure.

[0100] In step 410 , the processing device 140 (eg, the second generating module 230 ) may obtain a plurality of training samples.

[0101] In some embodiments, each training sample may include a sample gated PET image and a ground truth attenuation map of a sample subject. The sample gated PET image and the ground truth attenuation map correspond to the same physiological phase of the sample subject.

[0102] In some embodiments, the processing device 140 may generate training samples based on sample PET data and sample CT data collected from a sample PET scan and a sample CT scan of a sample subject. For example, the processing device 140 may determine a sample reference physiological phase of the sample CT scan based on the sample CT data. In addition, the processing device 140 or a user may determine a set of sample gated PET data corresponding to the sample reference physiology. The processing device 140 may generate a sample gated PET image based on the sample gated PET data set. As another example, the processing device 140 may generate a plurality of initial sample gated PET images based on the sample PET data, and generate a sample CT image based on the sample CT data. In addition, the processing device 140 may determine an initial sample gated PET image having the same or substantially the same physiological phase as the sample CT image from the plurality of initial sample gated PET images, and designate the initial sample gated PET image as the sample gated PET image. The processing device 140 may generate a sample attenuation map of the sample subject based on the sample CT data, and designate the sample attenuation map of the sample subject as the ground truth attenuation map of the sample subject.

[0103] In some embodiments, a plurality of training samples may be pre-collected and stored in a storage device (eg, storage device 150 or an external source). Processing device 140 may retrieve the plurality of training samples directly from the storage device.

[0104] In step 420 , the processing device 140 (eg, the second generation module 230 ) may generate an attenuation map generation model by training a preliminary model using a plurality of training samples.

[0105] The preliminary model refers to the model to be trained. The preliminary model can be as described elsewhere in this disclosure (e.g., Figure 3 The preliminary model may include a plurality of model parameters. Before training, the model parameters of the preliminary model may have their respective initial values.

[0106] In the training of the preliminary model, the values ​​of the model parameters may be iteratively updated until a termination condition is met. By way of example only, in the current iteration, the processing device 140 may obtain a predicted attenuation map of a sampled subject for each training sample by inputting a sample gated PET image of the training sample into the preliminary model of the current iteration. A value of a loss function may be determined to measure the difference between the predicted attenuation map of the training sample and the ground truth attenuation map. If the value of the loss function is less than a threshold, the termination condition may be met and the preliminary model may be designated as an attenuation map generation model. Otherwise, the model parameters of the preliminary model may be updated based on the value of the loss function until the termination condition is met.

[0107] Other exemplary termination conditions may include the difference between the value of the loss function obtained in the previous iteration and the current iteration (or between the loss function values ​​within a certain number or count of consecutive iterations) being less than a certain threshold, a maximum number of iterations (or count) having been executed, etc., or any combination thereof.

[0108] In some embodiments, the attenuation map generation model may be generated by a computing device other than the processing device 140 , such as a computing device of a supplier of the attenuation map generation model.

[0109] Figure 5 is a flowchart of an exemplary process for generating a target PET image by performing physiological motion correction according to some embodiments of the present disclosure.

[0110] In step 510, the processing device 140 (eg, the fourth generation module 250) may determine, from the attenuation-corrected gated PET images, a first attenuation-corrected gated PET image corresponding to a reference physiological phase and one or more second attenuation-corrected gated PET images corresponding to physiological phases other than the reference physiological phase.

[0111] At step 520 , for each of the one or more second attenuation-corrected gated PET images, the processing device 140 (eg, the fourth generation module 250 ) may transform the second attenuation-corrected gated PET image to generate a transformed gated PET image corresponding to a reference physiological phase.

[0112] In some embodiments, for the second attenuation-corrected gated PET image, the processing device 140 may determine a motion field between the second attenuation-corrected gated PET image and the first attenuation-corrected gated PET image by registering the second attenuation-corrected gated PET image with the first attenuation-corrected gated PET image. For example, the processing device 140 may register the second attenuation-corrected gated PET image with the first attenuation-corrected gated PET image based on a registration algorithm. Exemplary registration algorithms may include a point-based registration algorithm (e.g., an anatomical landmark-based registration algorithm), a curve-based registration algorithm, a surface-based registration algorithm (e.g., a surface contour based on a surface contour), a spatial alignment registration algorithm, a mutual correlation registration algorithm, a mutual information-based registration algorithm, a sequence similarity detection algorithm (SSDA), a nonlinear transformation registration algorithm, an optical flow algorithm, a B-spline registration algorithm, etc., or any combination thereof. In some embodiments, the registration may be performed based on a rigid transformation, an affine transformation, a projective transformation, a nonlinear transformation, an optical flow-based registration, a similarity measure, etc., or any combination thereof. The motion field may include a plurality of motion vectors corresponding to a plurality of physical points of the subject. The motion vector of the physical point can be used to describe the movement between the point corresponding to the physical point in the second attenuation-corrected gated PET image and the point corresponding to the physical point in the first attenuation-corrected gated PET image (i.e., the movement of the physical point between the physiological phase corresponding to the second attenuation-corrected gated PET image and the reference physiological phase).

[0113] In addition, the processing device 140 may transform the second attenuation-corrected gated PET image based on the motion field to generate a transformed gated PET image corresponding to the reference physiological phase. For example, the processing device 140 may transform the position of the voxel in the second attenuation-corrected gated PET image according to the motion field to generate a transformed gated PET image corresponding to the reference physiological phase.

[0114] In some embodiments, for each of the one or more second attenuation-corrected gated PET images, the processing device 140 may determine a motion field between a first region of the first attenuation-corrected gated PET image corresponding to the target region and a second region of the second attenuation-corrected gated PET image corresponding to the target region. In addition, the processing device 140 may transform the second region in the second attenuation-corrected gated PET image based on the motion field between the first region and the second region to generate a transformed gated PET image corresponding to a reference physiological phase. Specifically, the processing device 140 may transform the positions of voxels in the second region according to the motion field between the first region and the second region, and voxels outside the second region in the second attenuation-corrected gated PET image may not be transformed. In this way, the generation efficiency of the transformed gated PET image may be improved by reducing data processing, and the accuracy of generating the transformed gated PET image may be improved by performing physiological motion correction only on the second region corresponding to the target region, thereby avoiding erroneous correction of other regions that are not affected by the physiological motion of the subject.

[0115] In step 530 , the processing device 140 (eg, the fourth generation module 250 ) may generate a target PET image based on the first attenuation-corrected gated PET image and the one or more transformed gated PET images.

[0116] In some embodiments, the processing device 140 may combine the first attenuation-corrected gated PET image and the one or more transform-gated PET images into a target PET image.

[0117] Figure 6 is a schematic diagram of an exemplary process of PET imaging according to some embodiments of the present disclosure. Figure 6 As shown, PET data 601 and physiological signals 602 may be acquired. In some embodiments, the physiological signals 602 may be generated based on the PET data 601, as described in step 310. A plurality of gated PET images 603 may be generated based on the PET data 601 and the physiological signals 602. In addition, a plurality of first attenuation maps 604 may be generated based on the plurality of gated PET images 603 using an attenuation map generation model, and a plurality of attenuation-corrected gated PET images 605 may be generated based on the plurality of first attenuation maps 604 and the PET data 601.

[0118] A reference physiological phase 608 may be determined. In some embodiments, a second attenuation map 607 may be generated based on the CT data 606, and a reference physiological phase 608 may be determined based on the second attenuation map 607 and the plurality of first attenuation maps 604. Then, a first attenuation-corrected gated PET image 609 and one or more second attenuation-corrected gated PET images 610 corresponding to the reference physiological phase may be determined from the plurality of attenuation-corrected gated PET images 605. A motion field 611 between the first attenuation-corrected gated PET image 609 and the second attenuation-corrected gated PET image 610 may be determined by performing image registration between the first attenuation-corrected gated PET image 609 and the second attenuation-corrected gated PET image 610. Furthermore, one or more transformed gated PET images 612 may be generated by transforming the one or more second attenuation-corrected gated PET images 610 based on the motion field 611. A target PET image 613 may be generated by combining the one or more transformed gated PET images 612 and the first attenuation-corrected gated PET image 609.

[0119] In some embodiments, a motion field 614 between the second attenuation map and the first attenuation map corresponding to the reference physiological phase 608 (i.e., the reference attenuation map) can be determined by performing image registration. Finally, a physiological phase-matched PET image 615 can be generated by transforming the target PET image 613 based on the motion field 614.

[0120] For those skilled in the art, various changes and modifications may be made to the present application without departing from the spirit and scope of the present application. In this way, if the modifications and changes of the present application are within the scope of the appended claims and their equivalents, the present application may be intended to include these modifications and changes. For example, the steps of the processes 300, 400 and 500 shown are intended to be illustrated. In some embodiments, the processes 300, 400 and 500 may be implemented by one or more additional steps not described and / or one or more steps not discussed. In addition, the order of steps of the processes 300, 400 and 500 and the related descriptions are not meant to be restrictive.

[0121] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0122] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0123] In addition, it will be appreciated by those skilled in the art that various aspects of the present application may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product, or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software, generally referred to herein as "modules," "units," "components," "devices," or "systems." In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, the product including computer-readable program code.

[0124] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0125] The computer program coding required for the operation of each part of the application 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 language, VisualBasic, Fortran2003, Perl, COBOL2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program coding can be run completely on the user's computer, or run on the user's computer as an independent software package, or run partly on the user's computer and partly on the remote computer, or run completely on the remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (for example, by using the Internet of an Internet service provider), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0126] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing processing device or mobile device.

[0127] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0128] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "approximately", "approximately" or "substantially" in some examples. Unless otherwise specified, "approximately", "approximately" or "substantially" may represent a certain change in the value described (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 change according to the required features of individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of general digit retention. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range. In some embodiments, for illustrative purposes, classification conditions for classification or determination are provided and modified according to different situations. For example, the classification condition of "value greater than a threshold value" may further include or exclude the condition of "probability value equal to a threshold value".

Claims

1. A system for positron emission tomography (PET) imaging, comprising: at least one storage device including a set of instructions; as well as at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to instruct the system to perform operations comprising: acquiring PET data of the subject collected by performing a PET scan on the subject and a physiological signal associated with physiological movement of the subject during the PET scan; generating a plurality of gated PET images corresponding to a plurality of physiological phases of the subject based on the PET data and the physiological signal; For each of the plurality of physiological phases, generating a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase; For each of the plurality of physiological phases, generating an attenuation-corrected gated PET image corresponding to the physiological phase based on the first attenuation map and a portion of the PET data corresponding to the physiological phase; and Based on the attenuation-corrected gated PET images corresponding to the multiple physiological phases, a target PET image corresponding to a reference physiological phase among the multiple physiological phases is generated.

2. The system according to claim 1, wherein: The acquiring of physiological signals associated with the physiological motion of the subject during the PET scan comprises: determining a target area of ​​the subject affected by the subject's physiological movement; determining a time activity curve (TAC) corresponding to the target region based on the PET data; and The physiological signal of the subject is generated based on the TAC.

3. The system according to claim 1, wherein: The acquiring of physiological signals associated with the physiological motion of the subject during the PET scan comprises: Determining a target area of ​​the subject affected by the physiological movement; for each time point during the PET scan, determining a center of mass distribution (COD) of coincident events at the time point in the target region based on the PET data; The physiological signal of the subject is generated based on the COD corresponding to each time point.

4. The system according to any one of claims 1 to 3, wherein: For each of the plurality of physiological phases, generating a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase comprises: For each of the multiple physiological phases, the gated PET image corresponding to the physiological phase is processed by using an attenuation map generation model to generate the first attenuation map of the subject corresponding to the physiological phase, and the attenuation map generation model is a trained machine learning model.

5. The system according to claim 4, wherein: The attenuation map generation model is generated according to a model training process, including: Acquire a plurality of training samples, each training sample comprising a sample gated PET image and a ground truth attenuation map of a sample subject, the sample gated PET image and the ground truth attenuation map corresponding to the same physiological phase of the sample subject; and The attenuation map generation model is generated by training a preliminary model using multiple training samples.

6. The system according to any one of claims 1 to 5, wherein: Generating a target PET image corresponding to a reference physiological phase among the multiple physiological phases based on the attenuation-corrected gated PET images corresponding to the multiple physiological phases comprises: Determining, from the attenuation-corrected gated PET images, a first attenuation-corrected gated PET image corresponding to the reference physiological phase and one or more second attenuation-corrected gated PET images corresponding to physiological phases other than the reference physiological phase; for each of the one or more second attenuation-corrected gated PET images, transforming the second attenuation-corrected gated PET image to generate a transformed gated PET image corresponding to the reference physiological phase; and The target PET image is generated based on the first attenuation-corrected gated PET image and the one or more transform-gated PET images.

7. The system according to claim 6, wherein: The operations further include: obtaining a second attenuation map of the subject generated based on a computed tomography (CT) scan of the subject; selecting a reference attenuation map having the highest similarity to the second attenuation map from among the first attenuation maps corresponding to the plurality of physiological phases; The physiological phase corresponding to the reference attenuation map is determined as the reference physiological phase.

8. The system according to claim 6, wherein: For each of the one or more second attenuation-corrected gated PET images, transforming the second attenuation-corrected gated PET image to generate a transformed gated PET image corresponding to the reference physiological phase comprises: determining a target area affected by the physiological movement of the subject; For each of the one or more second attenuation-corrected gated PET images, determining a motion field between a first region of the first attenuation-corrected gated PET image corresponding to the target region and a second region of the second attenuation-corrected gated PET image corresponding to the target region; and The second region in the second attenuation-corrected gated PET image is transformed based on the motion field to generate the transformed gated PET image corresponding to the reference physiological phase.

9. The system according to claim 1, wherein: The operations further include: acquiring a second attenuation map of the subject generated based on a computed tomography (CT) scan of the subject; determining a motion field between the second attenuation map and the first attenuation map corresponding to the reference physiological phase; and Based on the motion field and the target PET image, a physiological phase-matched PET image corresponding to the CT scan is generated.

10. The system according to any one of claims 1 to 9, wherein: The plurality of gated PET images are tissue images.

11. The system according to any one of claims 1 to 10, wherein: The plurality of gated PET images are non-attenuation corrected (NAC) PET images.

12. A method for positron emission tomography (PET) imaging, the method being implemented on a computing device having at least one storage device and at least one processor, the method comprising: acquiring PET data of the subject collected by performing a PET scan on the subject and a physiological signal associated with physiological movement of the subject during the PET scan; generating a plurality of gated PET images corresponding to a plurality of physiological phases of the subject based on the PET data and the physiological signal; For each of the plurality of physiological phases, generating a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase; For each of the plurality of physiological phases, generating an attenuation-corrected gated PET image corresponding to the physiological phase based on the first attenuation map and a portion of the PET data corresponding to the physiological phase; and Based on the attenuation-corrected gated PET images corresponding to the multiple physiological phases, a target PET image corresponding to a reference physiological phase among the multiple physiological phases is generated.

13. The method according to claim 12, wherein: The acquiring of physiological signals associated with the physiological motion of the subject during the PET scan comprises: determining a target area of ​​the subject affected by the subject's physiological movement; determining a time activity curve (TAC) corresponding to the target region based on the PET data; and The physiological signal of the subject is generated based on the TAC.

14. The method according to claim 12, wherein: The acquiring of physiological signals associated with the physiological motion of the subject during the PET scan comprises: Determining a target area of ​​the subject affected by the physiological movement; for each time point during the PET scan, determining a center of mass distribution (COD) of coincident events at the time point in the target region based on the PET data; The physiological signal of the subject is generated based on the COD corresponding to each time point.

15. The method according to any one of claims 12 to 14, wherein for each of the plurality of physiological phases, generating a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase comprises: For each of the multiple physiological phases, the gated PET image corresponding to the physiological phase is processed by using an attenuation map generation model to generate the first attenuation map of the subject corresponding to the physiological phase, and the attenuation map generation model is a trained machine learning model.

16. The method according to claim 15, wherein: The attenuation map generation model is generated according to a model training process, including: Acquire a plurality of training samples, each training sample comprising a sample gated PET image and a ground truth attenuation map of a sample subject, the sample gated PET image and the ground truth attenuation map corresponding to the same physiological phase of the sample subject; and The attenuation map generation model is generated by training a preliminary model using multiple training samples.

17. The method according to any one of claims 12 to 16, wherein: Generating a target PET image corresponding to a reference physiological phase among the multiple physiological phases based on the attenuation-corrected gated PET images corresponding to the multiple physiological phases comprises: Determining, from the attenuation-corrected gated PET images, a first attenuation-corrected gated PET image corresponding to the reference physiological phase and one or more second attenuation-corrected gated PET images corresponding to physiological phases other than the reference physiological phase; for each of the one or more second attenuation-corrected gated PET images, transforming the second attenuation-corrected gated PET image to generate a transformed gated PET image corresponding to the reference physiological phase; and The target PET image is generated based on the first attenuation-corrected gated PET image and the one or more transform-gated PET images.

18. The method according to claim 17, wherein: The operations further include: obtaining a second attenuation map of the subject generated based on a computed tomography (CT) scan of the subject; selecting a reference attenuation map having the highest similarity to the second attenuation map from among the first attenuation maps corresponding to the plurality of physiological phases; The physiological phase corresponding to the reference attenuation map is determined as the reference physiological phase.

19. The method according to claim 17, wherein: For each of the one or more second attenuation-corrected gated PET images, transforming the second attenuation-corrected gated PET image to generate a transformed gated PET image corresponding to the reference physiological phase comprises: determining a target area affected by the physiological movement of the subject; For each of the one or more second attenuation-corrected gated PET images, determining a motion field between a first region of the first attenuation-corrected gated PET image corresponding to the target region and a second region of the second attenuation-corrected gated PET image corresponding to the target region; and The second region in the second attenuation-corrected gated PET image is transformed based on the motion field to generate the transformed gated PET image corresponding to the reference physiological phase.

20. The method according to claim 12, wherein: The operations further include: acquiring a second attenuation map of the subject generated based on a computed tomography (CT) scan of the subject; determining a motion field between the second attenuation map and the first attenuation map corresponding to the reference physiological phase; and Based on the motion field and the target PET image, a physiological phase-matched PET image corresponding to the CT scan is generated.

21. The method according to any one of claims 12 to 20, wherein: The plurality of gated PET images are tissue images.

22. The system according to any one of claims 12 to 21, wherein: The plurality of gated PET images are non-attenuation corrected (NAC) PET images.

23. A system for positron emission tomography (PET) imaging, comprising: an acquisition module, configured to acquire PET data of the subject collected by performing a PET scan on the subject and a physiological signal associated with a physiological movement of the subject during the PET scan; A first generating module configured to generate a plurality of gated PET images corresponding to a plurality of physiological phases of the subject based on the PET data and the physiological signal; a second generating module configured to generate, for each of the plurality of physiological phases, a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase; a third generating module configured to generate, for each of the plurality of physiological phases, an attenuation-corrected gated PET image corresponding to the physiological phase based on the first attenuation map and a portion of the PET data corresponding to the physiological phase; as well as The fourth generating module is configured to generate a target PET image corresponding to a reference physiological phase among the multiple physiological phases based on the attenuation-corrected gated PET images corresponding to the multiple physiological phases.

24. A non-transitory computer readable medium comprising at least one set of instructions for positron emission tomography (PET) imaging, wherein when executed by one or more processors of a computing device, the at least one set of instructions causes the computing device to perform a method comprising: acquiring PET data of the subject collected by performing a PET scan on the subject and a physiological signal associated with a physiological movement of the subject during the PET scan; generating a plurality of gated PET images corresponding to a plurality of physiological phases of the subject based on the PET data and the physiological signal; For each of the plurality of physiological phases, generating a first attenuation map of the subject corresponding to the physiological phase based on the gated PET image corresponding to the physiological phase; For each of the plurality of physiological phases, generating an attenuation-corrected gated PET image corresponding to the physiological phase based on the first attenuation map and a portion of the PET data corresponding to the physiological phase; and Based on the attenuation-corrected gated PET images corresponding to the multiple physiological phases, a target PET image corresponding to a reference physiological phase among the multiple physiological phases is generated.

25. A device for positron emission tomography (PET) imaging, comprising at least one processor and at least one storage device for storing a set of instructions, wherein when the set of instructions is executed by the at least one processor, the device performs the method of any one of claims 11-20.

Images