Positronium lifetime imaging method and computer device

Abstract

The application relates to a positronium survival time imaging method and a computer device. The method comprises the following steps: acquiring ECT data of an imaging object, acquiring an intermediate image of the imaging object based on the ECT data; the intermediate image comprises at least one of an attenuation image, a positron emission tomography image and a histogram image of positronium survival time of the imaging object; inputting the intermediate image into a target image generation model to obtain a positronium survival time image of the imaging object; and the target image generation model is a trained neural network model. The positronium survival time imaging method provided in the embodiment of the application can reduce the complexity of generating the positronium survival time image and improve the efficiency of generating the positronium survival time image.

Description

Technical Field

[0001] This application relates to the field of imaging technology, and in particular to a time-of-life imaging method and computer device for positron elements. Background Technology

[0002] During positron emission tomography (PET) imaging, a tracer containing a radioactive isotope is injected into the subject. The tracer decays within the subject, producing positrons. These positrons then annihilate electrons within the body. This annihilation reaction generates a temporary intermediate called a positronium. Positroniums are classified by spin into para-positronium (pPs) and ortho-positronium (oPs). In a vacuum, both types of positronium decay into multiphotons at a specific rate; the reciprocal of the decay rate corresponds to the average lifetime of the positronium. In a vacuum, pPs decay into two 511 keV photons with a lifetime of 125 ps, while oPs decay into three photons with a lifetime of 142 ns. However, in a medium, oPs degenerate into pPs due to interactions with surrounding matter (pick-off process and spin exchange), and rapidly undergo two-photon decay. Therefore, the lifetime of oPs in a medium is significantly shorter than its lifetime in a vacuum, and it produces two-photon events with a high probability. Correspondingly, the lifetime of oPs is closely related to the microenvironment of the surrounding tissue. By measuring its specific lifetime, the properties of the surrounding matter can be further inferred, such as tissue molecular density and anaerobicness. These indicators can provide valuable information for cancer staging and treatment planning. Therefore, by performing lifetime imaging at different locations, the properties of the surrounding matter can be inferred.

[0003] Currently, lifetime imaging of positronium is typically achieved through fitting and iterative reconstruction. However, this method of lifetime imaging is highly complex. Summary of the Invention

[0004] Therefore, it is necessary to provide a positron-based time-of-life imaging method and computer device that can reduce the complexity of generating time-of-life images, addressing the aforementioned technical problems.

[0005] In a first aspect, this application provides a survival-time imaging method for positron elements, the method comprising:

[0006] Acquire ECT data of the imaging object;

[0007] Intermediate images of the imaging object are obtained based on ECT data; the intermediate images include at least one of the following: attenuation image of the imaging object, positron emission tomography image, and histogram image of positron survival time;

[0008] The intermediate image is input into the target image generation model to obtain the positron survival time image of the imaging object. The target image generation model is a trained neural network model.

[0009] In one embodiment, the intermediate image is a positron emission tomography (PET) image. The intermediate image of the imaging object is obtained based on ECT data, including:

[0010] Filter the ECT data to obtain double-matching events;

[0011] Image reconstruction was performed on the double coincidence event to obtain positron emission tomography (PET) images.

[0012] In one embodiment, the intermediate image is a histogram image of the positron survival time. The intermediate image of the imaging object is obtained based on ECT data, including:

[0013] Filter the ECT data to obtain triple-match events;

[0014] Multiple positron survival time estimates are calculated based on three coincidence events, and a histogram image of positron survival time is obtained from the multiple positron survival time estimates.

[0015] In one embodiment, the intermediate image is a attenuated image. The intermediate image of the imaging object is obtained based on ECT data, including:

[0016] Acquire tomographic images of the imaging object;

[0017] Obtain the bed code value corresponding to the ECT data;

[0018] Select at least a portion of the computed tomography image based on the bed code value;

[0019] Attenuated images are obtained based on at least a portion of the tomographic scan images.

[0020] In one embodiment, the target image generation model includes two-channel input;

[0021] One channel inputs the attenuated image, and the other channel inputs the positron emission tomography (PET) image; or...

[0022] One channel inputs the decay image, and the other channel inputs a histogram image of the positron survival time; or,

[0023] One channel inputs a positron emission tomography (PET) image, and the other channel inputs a histogram image of the positron survival time.

[0024] In one embodiment, the target image generation model includes three-channel inputs, which are:

[0025] Attenuation images, histogram images of positron survival time, and positron emission tomography (PET) images.

[0026] In one embodiment, the method further includes:

[0027] The target lifetime image is obtained by iterative reconstruction of the positron survival time image. The resolution of the target lifetime image is greater than that of the positron survival time image.

[0028] Secondly, one embodiment of this application provides a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0029] Acquire ECT data of the imaging object;

[0030] Intermediate images of the imaging object are obtained based on ECT data; the intermediate images include at least one of the following: attenuation image of the imaging object, positron emission tomography image, and histogram image of positron survival time;

[0031] The intermediate image is input into a trained neural network model to obtain a positron survival time image of the imaged object.

[0032] In one embodiment, the processor also implements:

[0033] Based on the positron survival time image, the property information of at least one substance is determined.

[0034] In one embodiment, it further includes:

[0035] The display simultaneously shows images of the positron survival time and information about the properties of the substance.

[0036] Thirdly, one embodiment of this application provides a positron-emitting element survival time imaging apparatus, the apparatus comprising:

[0037] The acquisition module is used to acquire ECT data of the imaging object;

[0038] The acquisition module is also used to acquire intermediate images of the imaging object based on ECT data; the intermediate images include at least one of the following: attenuation image of the imaging object, positron emission tomography image, and histogram image of positron survival time;

[0039] The input module is used to input the intermediate image into the target image generation model to obtain the positron survival time image of the imaging object. The target image generation model is a trained neural network model.

[0040] Fourthly, one embodiment of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect above.

[0041] Fifthly, one embodiment of this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method provided in the first aspect.

[0042] The aforementioned positron emission tomography (PET) survival time imaging method and computer device involve acquiring ECT data of the imaging object and obtaining an intermediate image of the imaging object based on the ECT data. The intermediate image includes at least one of a decay image of the imaging object, a positron emission tomography (PET) image, and a histogram image of the positron emission tomography (PET) survival time. The intermediate image is then input into a target image generation model to obtain a PET survival time image of the imaging object. The target image generation model is a trained neural network model. In this embodiment, directly inputting the acquired intermediate image into a pre-trained target image generation model yields the PET survival time image of the imaging object. This method of directly using a trained target image generation model to generate the PET survival time image is fast and efficient in determining the survival time of the positron emission tomography (PET). Attached Figure Description

[0043] Figure 1 This is an application environment diagram of the positron survival time imaging method in one embodiment;

[0044] Figure 2 This is a schematic diagram of the structure of a computer device in one embodiment;

[0045] Figure 3 This is a flowchart illustrating the steps of a positron survival time imaging method in one embodiment;

[0046] Figure 4 This is a flowchart illustrating the steps of a positron survival time imaging method in another embodiment;

[0047] Figure 5 This is a flowchart illustrating the steps of a positron survival time imaging method in another embodiment;

[0048] Figure 6 This is a schematic diagram illustrating the detection of a positronium triple coincidence event in one embodiment;

[0049] Figure 7 This is a flowchart illustrating the steps of a positron survival time imaging method in another embodiment;

[0050] Figure 8 This is a flowchart illustrating the steps of a positron survival time imaging method in another embodiment;

[0051] Figure 9 This is a flowchart illustrating the steps of a positron survival time imaging method in another embodiment;

[0052] Figure 10 This is a flowchart illustrating the steps of a positron survival time imaging method in another embodiment;

[0053] Figure 11 Here is a block diagram of the structure for training an initial image generation model in one embodiment;

[0054] Figure 12 Here is a block diagram of the structure for training the initial image generation model in another embodiment;

[0055] Figure 13 Here is a block diagram of the structure for training the initial image generation model in another embodiment;

[0056] Figure 14 Here is a block diagram of the structure for training the initial image generation model in another embodiment;

[0057] Figure 15 Here is a block diagram of the structure for training the initial image generation model in another embodiment;

[0058] Figure 16 Here is a block diagram of the structure for training the initial image generation model in another embodiment;

[0059] Figure 17 Here is a block diagram of the structure for training the initial image generation model in another embodiment;

[0060] Figure 18 This is a flowchart illustrating the steps of a positron survival time imaging method in another embodiment;

[0061] Figure 19 This is a schematic histogram image of the positron survival time in one embodiment;

[0062] Figure 20 This is a schematic diagram of the spectrum of a positron survival time image in one embodiment;

[0063] Figure 21 This is a schematic diagram of the structure of a positron survival time imaging device in one embodiment. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] The serial numbers assigned to components in this article, such as "first" and "second", are used only to distinguish the objects being described and have no sequential or technical meaning.

[0066] First, before detailing the technical solutions of the embodiments disclosed in this application, the background technology or technological evolution on which the embodiments of this application are based will be introduced. Positron emission tomography (PET) or single-photon emission computed tomography (SPECT) is an important tomographic imaging system in the field of nuclear medicine and has been widely used in medical diagnosis and research. During PET or SPECT imaging, the imaging subject is injected with a tracer containing a radioactive nuclide. The tracer decays within the imaging subject, generating positrons. When these positrons encounter electrons within the biological body, a electron-positron pair annihilation reaction occurs, generating a pair of photons with opposite directions and the same energy. This pair of photons passes through the tissue of the imaging subject, is received by the detector of the PET or SPECT, and undergoes an electronic response, inputting the electronic response signal to a computer device. The computer device then generates an image reflecting the distribution of the tracer within the imaging subject using a corresponding image reconstruction algorithm.

[0067] After electron-positron pair annihilation occurs within the imaged object, a temporary intermediate called positronium is generated. Positronium is classified into para-positronium (pPs) and ortho-positronium (oPs) based on its spin. In a vacuum, both types of positronium decay into multiphotons at a certain decay rate; the reciprocal of the decay rate corresponds to the average lifetime of the positronium. In a vacuum, pPs decay into two 511 keV photons with a lifetime of 125 ps, while oPs decay into three photons with a lifetime of 142 ns. However, in a medium, oPs, due to interactions with surrounding matter (pick-off process and spin exchange), degenerate into pPs and rapidly undergo two-photon decay. Therefore, the lifetime of oPs in a medium is significantly shorter than its lifetime in a vacuum, and it is more likely to produce two-photon events. Correspondingly, the lifetime of oPs is closely related to the microenvironment of the surrounding tissue. By measuring their specific lifetime, the properties of surrounding substances can be further inferred, such as tissue molecular density and anaerobicness. These indicators can provide valuable information for cancer staging and treatment planning. Therefore, the properties of surrounding substances can be inferred by performing lifetime imaging at different locations.

[0068] Currently, positronium lifetime imaging typically involves first fitting the lifetime spectrum to obtain the lifetime, and then generating a lifetime image through iterative reconstruction. The horizontal axis of the spectrum represents the time difference between the generation of the transient gamma ray and the decay of the positronium, while the vertical axis represents the number of triple coincidence events corresponding to that time difference. The specific fitting process includes determining the lifetime curve based on the spectral envelope, and fitting this curve to determine the accurate lifetime. However, the method of lifetime imaging through fitting and iterative reconstruction is complex and time-consuming. Therefore, this application provides a positronium lifetime imaging method that reduces the complexity of generating lifetime images.

[0069] The positron survival imaging method provided in this application can be applied to medical imaging systems, such as... Figure 1As shown, the medical imaging system includes an imaging device 11 and a computer device 12, which are connected to the imaging device 11 via a network. The imaging device 11 scans the object to be imaged, obtains scan data, and transmits the scan data to the computer device 12. The computer device 12 performs image reconstruction based on the received scan data to obtain a reconstructed image. The imaging device can be PET, computed tomography (CT), or magnetic resonance imaging (MRI). The computer device can be, but is not limited to, an industrial computer, a laptop computer, or a tablet computer. The internal structure of the computer device can be as follows: Figure 2 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a positron emission tomography (PET) time-of-life imaging method. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0070] Those skilled in the art will understand that Figure 2 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0071] In one embodiment, such as Figure 3 As shown, a survival time imaging method for positron-emitting elements is provided. This embodiment illustrates the application of this method to a computer device in a medical imaging system. In this embodiment, the method includes the following steps:

[0072] Step 300: Obtain ECT data of the imaging object.

[0073] Emission Computed Tomography (ECT) data refers to data obtained by scanning an object using an imaging device, specifically an emission computed tomography (ECT) device. ECT data is a type of PET data.

[0074] The computer device can acquire ECT data from the post-processing workstation of the image equipment, or from a server such as a Picture Archiving and Communication Systems (PACS). Alternatively, the ECT data can be pre-stored in the computer device's memory, and the computer device can retrieve it directly from the memory when needed. This embodiment does not limit the specific method of acquiring ECT data, as long as the function can be achieved.

[0075] Step 310: Obtain intermediate images of the imaging object based on ECT data; the intermediate images include at least one of the following: attenuation image of the imaging object, positron emission tomography (PET) image, and histogram image of positron survival time.

[0076] An attenuated image of an imaging object can be obtained by a computer sending a control signal to an imaging device to control the imaging device to emit scanning rays towards the imaging object. The scanning rays attenuate after passing through the imaging object, the detector receives the attenuated scanning signal, and transmits the scanning signal to the computer. The computer then performs image reconstruction processing based on the scanning signal to obtain the attenuated image. A positron emission tomography (PET) image can be obtained by a computer sending a control signal to the PET in the imaging device to control the PET to scan the imaging object. A histogram of positron survival time can be obtained as a lower-quality survival time image determined by the scan data obtained by a computer sending a control signal to the PET to control the PET to scan the imaging object. An intermediate image can include any one of the attenuated image, PET image, and positron survival time histogram image; an intermediate image can also include any combination of any two of the attenuated image, PET image, and positron survival time histogram image, such as a combination of an attenuated image and a PET image, a combination of an attenuated image and a positron survival time histogram image, or a combination of a PET image and a positron survival time histogram image; an intermediate image can also be a combination of an attenuated image, a PET image, and a positron survival time histogram image.

[0077] Step 320: Input the intermediate image into the target image generation model to obtain the positron survival time image of the imaging object. The target image generation model is a trained neural network model.

[0078] The target image generation model can be a neural network model. This embodiment does not limit the type or structure of the target image generation model, as long as it can achieve its function. The target image generation model can be obtained by training an initial image generation model using training samples. The training samples correspond to intermediate images. That is, if the training samples used when training the initial image generation model include PET image samples and histogram image samples of positron survival time, then when using the target image generation model to obtain the positron survival time image of the imaging object, the obtained intermediate image of the imaging object includes the PET image and the histogram image of positron survival time; if the training samples used include PET image samples, histogram image samples of positron survival time, and attenuation image samples, then the obtained intermediate image of the imaging object includes the PET image, the histogram image of positron survival time, and the attenuation image; if the training samples used include attenuation image samples and histogram image samples of positron survival time, then the obtained intermediate image of the imaging object includes the attenuation image and the histogram image of positron survival time. The target image generation model can be pre-trained by a computer device and stored in the computer device's memory.

[0079] After acquiring the intermediate image, the computer device inputs the intermediate image into the target image generation model to obtain the positron survival time image of the imaging object.

[0080] In an optional embodiment, the computer device stores multiple different candidate image generation models trained with different training samples in its storage module. After acquiring an intermediate image of the imaging object, the computer device selects a candidate image generation model corresponding to the type of the intermediate image from among the multiple candidate image generation models, and determines the candidate image generation model as the target image generation model.

[0081] In an optional embodiment, after obtaining a positron-emitting cell lifetime image of the imaging object, the computer device can analyze the positron-emitting cell lifetime image to determine the properties of the tissue included in the target region of the imaging object, thereby assisting medical personnel in diagnosis and treatment based on the tissue properties. The tissue properties may include anaerobic properties and tissue density properties, etc.

[0082] The positron emission tomography (PET) survival time imaging method provided in this application acquires ECT data of the imaging object and obtains an intermediate image of the imaging object based on the ECT data. The intermediate image includes at least one of the following: an attenuation image of the imaging object, a positron emission tomography (PET) image, and a histogram image of the positron emission tomography survival time. The intermediate image is input into a target image generation model to obtain the positron emission tomography survival time image of the imaging object. The target image generation model is a trained neural network model. In this embodiment, the acquired intermediate image is directly input into the pre-trained target image generation model to obtain the positron emission tomography survival time image of the imaging object. This method of directly using the trained target image generation model to generate the positron emission tomography survival time image is fast and can improve the efficiency of determining the positron emission tomography survival time image. In addition, the positron emission tomography survival time imaging method provided in this application can remove noise from the generated positron emission tomography survival time image, thereby improving the quality of the generated positron emission tomography survival time image.

[0083] In one embodiment, when the intermediate image of the imaging object acquired based on ECT data is a positron emission tomography (PET) image, such as Figure 4 As shown, this relates to an implementation method for acquiring intermediate images of an imaging object based on ECT data. The steps of this implementation method include:

[0084] Step 400: Filter the ECT data to obtain data on double-matching events.

[0085] A double coincidence event refers to an event in which two photons are generated simultaneously within a certain time window during PET imaging.

[0086] Computer equipment filters the acquired ECT data to obtain data on double-matching events.

[0087] In an optional embodiment, a first filter is pre-configured in the computer device. Inputting ECT data into the first filter yields double-coincidence event data from the ECT data. The first filter can be a pre-configured logic program that implements the filtering function. Specifically, the ECT data includes energy information, time information, the index of the acquisition crystal in the detector, and the acquired data information. When the ECT data is input into the first filter, the first filter, based on the energy information, acquisition time information, and acquired data information of the ECT data, can determine two data points with a time difference within a preset time difference range as double-coincidence events within a preset energy range.

[0088] In another alternative embodiment, a pre-trained classification network is pre-configured in the computer device. By inputting ECT data into the classification network, data on double coincidence events in the ECT data can be obtained.

[0089] Step 410: Perform image reconstruction on the data of the double coincidence event to obtain a positron emission tomography (PET) image.

[0090] After acquiring data from a double coincidence event, the computer device performs image reconstruction on the data to obtain a PET image. This embodiment does not limit the specific method of image reconstruction, as long as the function can be achieved.

[0091] In this embodiment, a PET image can be obtained by reconstructing images from double coincidence event data obtained by filtering ECT data. This method of determining PET images is quick and easy to implement, and can improve the efficiency of determining the positron-emitting time-of-life image of the imaging object.

[0092] In one embodiment, when the intermediate image of the imaging object acquired based on ECT data is a histogram image of the positron survival time, such as Figure 5 As shown, this relates to an implementation method for acquiring intermediate images of an imaging object based on ECT data. This implementation method includes:

[0093] Step 500: Filter the ECT data to obtain data on triple-matching events.

[0094] A triple coincidence event refers to an event during PET imaging where a prompt gamma ray and two photons are generated within a certain time window. Specifically, triple coincidence events include the generation of nuclides (such as those in the tracer injected into the imaging subject) within a specific time window. 22 The decay of Na produces a prompt gamma and the decay of a positron produces a pair of back-to-back emitted photons.

[0095] After acquiring ECT data, computer equipment can filter the ECT data to obtain data on triple-matching events.

[0096] In an optional embodiment, a second filter is pre-configured in the computer device. Inputting ECT data into the second filter yields triple coincidence event data from the ECT data. The second filter can be a pre-configured logic program that implements the filtering function. Specifically, when ECT data is input into the second filter, the second filter can filter out triple coincidence event data from the ECT data based on the energy information, acquisition time information, acquisition crystal index, and acquired data information.

[0097] In another alternative embodiment, a pre-trained classification network is pre-configured in the computer device. By inputting ECT data into the classification network, the data of the three coincidence events in the ECT data can be obtained.

[0098] In another optional embodiment, a further implementation of determining the data for double-coinciding events and triple-coinciding events using a first filter and a second filter includes: inputting ECT data into a first filter, which, based on the energy information, time information, and acquired data information of the ECT data, filters out two data points whose time difference between acquisition times falls within a first preset time difference range, and uses these as the initial double-coinciding event data; inputting the initial double-coinciding event data into a second filter, which, based on the received initial double-coinciding event data and the time information of each data point, filters out three data points whose time difference between acquisition times falls within a second preset time difference range, and uses these as the triple-coinciding event data. The remaining initial double-coinciding event data, excluding the filtered triple-coinciding event data, is then determined as the double-coinciding event data.

[0099] In another optional embodiment, the computer device is equipped with a pre-trained classification network. By inputting ECT data into the classification network, data on double-matching events and triple-matching events in the ECT data can be obtained.

[0100] Step 510: Calculate multiple positron survival time estimates based on the data of the three coincidence events, and obtain a histogram image of the positron survival time based on the multiple positron survival time estimates.

[0101] Typically, in triple coincidence events, the generation of prompt gamma and positrons occurs almost simultaneously. After interacting with surrounding tissue in the imaging target, the positron generates positronium. Compared to the decay time of positronium, the interaction time between the positron and the surrounding tissue is on the order of picoseconds and can be ignored. Therefore, in practice, it is assumed that positronium and prompt gamma are generated almost simultaneously, and the survival time of positronium can be determined using the generation time of prompt gamma. In other words, the histogram image of positronium survival time can be determined using the generation time of prompt gamma. In this case, the data screening for triple coincidence events differs from that for ordinary triple events, mainly because the detection energy window of prompt gamma is not within the conventional two-photon detection energy window. 22 Taking Na as an example, its prompt gamma energy peak is at 1.26 MeV, while the energy of a single photon in a two-photon pair is 511 keV (the detection energy window is in the range of approximately 430-650 keV).

[0102] For example, a method for detecting a positronium triple coincidence event is as follows: Figure 6 As shown. Figure 6 In this diagram, P represents the prompt gamma detected by the PET detector, and E1 and E2 represent two photons emitted back-to-back by the PET detector. The annihilation reaction occurs at position A on the ine-of-response (LOR) line defined by E1 and E2.

[0103] After acquiring data from the triple coincidence event, the computer device calculates multiple positron survival time estimates based on the triple coincidence event data.

[0104] In an optional embodiment, such as Figure 7 As shown, an implementation method for calculating multiple positron survival time estimates based on data from three coincidence events is described, and the steps of this implementation method include:

[0105] Step 700: Determine multiple detection locations and corresponding detection time differences for the three-match events detected at different times based on the data of the three-match events.

[0106] Multiple triple coincidence events are generated during PET imaging. The triple coincidence event data includes relevant data from triple coincidence events occurring at different times and locations. After acquiring the triple coincidence event data, the computer equipment determines multiple detection locations of the triple coincidence events detected by the detector at different times, as well as the detection time difference corresponding to each detection location. In other words, the detector can detect triple coincidence events at multiple detection locations, and for the same detection location, multiple triple coincidence events can be detected at different times. An example of detecting a triple coincidence event at a certain detection location at the current time is... Figure 6 As shown, the detection location of the detected triple coincidence event can be represented as: The detection time difference can be expressed as (Δt, Δt) p1 ,Δt p2 ), where the detector detects two photons at times t and t', respectively. E1 and t E2 The time for the detector to detect prompt gamm is t. p Δt=t E1 -t E2 For the detector to detect the time difference between two photons (E1 and E2), Δt p1 =t p -t E1 For the detector to detect the time difference between prompt gamma and photon E1, Δt p2 =t p -t E2The detector detects the time difference between prompt gamma and photon E1.

[0107] Step 710: For each detection position at the current time, determine the annihilation position where the annihilation reaction occurs based on the detection position and the corresponding detection event difference; and determine the estimated value of the positron survival time based on the annihilation position, the detection position and the corresponding detection time difference.

[0108] After determining multiple detection locations and corresponding time differences for triple-coincidence events detected at different times, the computer device, for each detection location at the current time, can determine the annihilation location corresponding to that detection location based on the detection location and the corresponding time difference. The current time can be any time from different times within the triple-coincidence event data. The computer device can determine the annihilation location corresponding to the detection location based on the time difference. and The annihilation location is determined by the corresponding detection time difference Δt. Specifically, computer equipment can be based on the formula The annihilation location was calculated. Where c represents the speed of light.

[0109] After obtaining the annihilation location, the computer equipment can determine the target time difference between the prompt gamma generation time and the positronium decay time in a triple coincidence event, i.e., the positron survival time estimate, based on the annihilation location, the detection location, and the corresponding detection time difference. At an annihilation location, the computer equipment can first estimate the flight time of the prompt gamma based on the annihilation location and the detection location, thereby inferring the prompt gamma generation time, and then use the Δt in the detection time difference to determine the target time difference. p1 and Δt p2 Calculate the target time difference based on any information in the time difference. Specifically, if Δt is detected... p1 The target time difference can be calculated using the following formula (1). Similarly, if the time difference Δt is detected... p2 The formula for the target time difference can be expressed as follows: Using the same method, the target time difference at different times at the annihilation location can be determined, thus obtaining multiple positron survival time estimates.

[0110]

[0111] In this embodiment, the method of determining the positron survival time estimate based on the detection positions and corresponding detection time differences of the triple coincidence events detected by the detector at different times is fast and easy to implement, and can improve the efficiency of obtaining positron survival time images using the positron survival time imaging method.

[0112] After obtaining multiple positron survival time estimates, the computer device can generate a histogram image of the positron survival time based on these estimates.

[0113] In an optional embodiment, such as Figure 8 As shown, an implementation of a histogram image for determining the positron survival time based on multiple positron survival time estimates is provided, the steps of which include:

[0114] Step 800: For each annihilation location, determine the first survival image based on the estimated positron survival time at different times corresponding to the annihilation location.

[0115] After obtaining the estimated positron survival time for each annihilation location, the computer device can determine the first survival image based on each annihilation location and the corresponding survival time estimate. The first survival image is a three-dimensional image, where each pixel represents an annihilation location and the sum of the cumulative survival time estimates at that annihilation location, i.e., the sum of the estimated positron survival times at all times corresponding to that annihilation location.

[0116] Step 810: Determine the second survival image based on each annihilation location and the number of ternary coincidence events generated at each annihilation location.

[0117] After determining the number of triplet events generated at each annihilation location, the computer device can determine the second survival image based on each annihilation location and the number of triplet events generated at each annihilation location. The second survival image is a three-dimensional image, where each pixel represents an annihilation location and the number of triplet events generated at that annihilation location, i.e., the number of annihilation reactions.

[0118] Step 820: Determine the histogram image of the positron survival time based on the first survival image and the second survival image.

[0119] After determining the first survival image and the second survival image, the computer device can determine a histogram image of the positron survival time by determining the ratio of the first generated image and the second survival image. Each pixel in the histogram image of the positron survival time represents the average survival time at that annihilation location.

[0120] In this embodiment, a first survival image can be determined based on the estimated positron survival time at different times at each annihilation location, and a second survival image can be determined based on the annihilation location and the number of triple coincidence events generated at the annihilation location. In this way, the histogram image of the positron survival time can be determined by the two determined survival images, which can improve the efficiency of determining the histogram image of the positron survival time.

[0121] The above embodiment obtains triple coincidence event data by filtering ECT data; multiple positron survival time estimates are calculated based on the triple coincidence event data; and a histogram image of positron survival time can be obtained based on the multiple positron survival time estimates. This method of determining the histogram image of positron survival time is fast and easy to implement, and can improve the efficiency of determining the histogram image of positron survival time.

[0122] In one embodiment, when the intermediate image of the imaging object acquired based on ECT data is a attenuated image, such as Figure 9 As shown, this relates to an implementation method for acquiring intermediate images of an imaging object based on ECT data. This implementation method includes:

[0123] Step 900: Obtain the tomographic scan image of the imaging object.

[0124] The computer sends control signals to the imaging device to control the imaging device to scan the object, generating a tomographic scan signal, and then sends the tomographic scan signal back to the computer. Upon receiving the tomographic scan signal, the computer reconstructs the image to obtain a tomographic image. The imaging device can be a CT scanner or an MRI scanner. The resulting tomographic image can be either a CT image or an MRI image.

[0125] Step 910: Obtain the bed code value corresponding to the ECT data.

[0126] Based on the acquired ECT data, the computer equipment can determine the corresponding bed code value, which is the position of the imaging object on the scanning bed when the imaging equipment scans the object. Specifically, the bed code value corresponding to the ECT data refers to the center bed code value of the position of the imaging object on the scanning bed.

[0127] Step 920: Select at least a portion of the tomographic scan image based on the bed code value.

[0128] Computed tomographic images are typically overall images of the object being imaged, with different portions of the image corresponding to different bed code values. After determining the bed code value corresponding to the ECT data, the computer equipment searches for at least the portion of the image corresponding to that bed code value within the computed tomographic image.

[0129] Step 930: Obtain attenuated images based on at least a portion of the tomographic scan images.

[0130] After selecting at least a portion of a tomographic image, the computer device determines an attenuated image based on that portion of the image.

[0131] In an optional embodiment, the computer device may perform a bilinear transformation on at least a portion of the selected tomographic images to obtain an attenuated image of the imaging object.

[0132] In this embodiment, a tomographic image of the imaging object is acquired; the bed code value corresponding to the ECT data is acquired; at least a portion of the tomographic image is selected based on the bed code value; and an attenuation image is acquired based on the at least portion of the tomographic image. By selecting at least a portion of the image corresponding to the ECT data from the tomographic image, a more accurate attenuation image can be determined based on the selected at least portion of the image.

[0133] In one embodiment, such as Figure 10 As shown, the training process of the target image generation model includes:

[0134] Step 1001: Obtain training samples, which include at least one of attenuation image samples, positron emission tomography image samples, and histogram image samples of positron survival time, as well as standard survival time images.

[0135] The training samples may include at least one of attenuation image samples, PET image samples, and histogram image samples of positron survival time. The descriptions of the attenuation image samples, PET image samples, and histogram image samples of positron survival time can be found in the specific descriptions of the attenuation images, PET images, and histogram images of positron survival time in the above embodiments, and will not be repeated here. The training samples also include standard survival time images, i.e., survival time images of higher quality.

[0136] In an alternative embodiment, the standard survival time image may be generated in advance using an iterative reconstruction and fitting method.

[0137] The computer device can obtain training samples from the image processing workstation or from servers such as PACS. Alternatively, the training samples can be pre-stored in the computer device's memory, and the computer device can directly retrieve them from memory when it needs to train the target image generation model. This embodiment does not limit the method of obtaining training samples, as long as it can achieve its function.

[0138] Step 1002: Train the initial image generation model using training samples to obtain the target image generation model.

[0139] The description of the initial image generation model can be found in the detailed description of the target image generation model in the above embodiments, and will not be repeated here. After acquiring training samples, the computer device inputs the training samples into the initial image generation model to train the initial image generation model, thereby obtaining the target image generation model. Specifically, the initial image generation model generates an initial survival time image by processing at least one of the input attenuation image samples, PET image samples, and histogram image samples of positron survival time; a loss function is determined based on the initial survival time image and the standard survival time image; and the network parameters of the initial image generation model are updated according to the loss function to obtain the target image generation model.

[0140] In this embodiment, the initial image generation model is trained using training samples to obtain the target image generation model. This method of determining the target image generation model is quick and easy to implement.

[0141] In one embodiment, the target image generation model includes two input channels: one channel for an attenuated image and the other channel for a positron emission tomography (PET) image. That is, the intermediate image of the imaging object acquired based on ECT data includes both an attenuated image and a PET image, which are then input into the target image generation model.

[0142] In this case, training the initial image generation model yields the structural block diagram of the target image generation model, as shown below. Figure 11 As shown. PET data samples are acquired, and the first filter is used to filter the PET data samples to obtain data on double coincidence events. Image reconstruction is performed on the data on double coincidence events to obtain PET image samples. Attenuated image samples are determined based on computed tomography (CT) images. The PET image samples and attenuated image samples are input into the initial image generation model, and the initial image generation model is trained by combining it with standard survival time images to obtain the target image generation model.

[0143] The second scenario involves inputting the attenuation image through one channel and the histogram image of the positron survival time through the other channel. In other words, the intermediate image of the imaging object acquired based on ECT data includes both the attenuation image and the histogram image of the positron survival time, which are then input into the target image generation model.

[0144] In this case, training the initial image generation model yields the structural block diagram of the target image generation model, as shown below. Figure 12As shown, PET data samples are obtained, and the second filter is used to filter the PET data samples to obtain data on triple coincidence events. Based on the data on triple coincidence events and the Direct Time of Flight (DTOF) method, histogram image samples of positron survival time are obtained. Attenuation image samples are determined based on tomographic scan images (CT images). The histogram image samples of positron survival time and the attenuation image samples are input into the initial image generation model. Combined with standard survival time images, the initial image generation model is trained to obtain the target image generation model.

[0145] The third scenario involves one channel inputting a positron emission tomography (PET) image and the other channel inputting a histogram image of positron survival time. In other words, the intermediate image of the imaging object acquired based on ECT data includes both a PET image and a histogram image of positron survival time. These two images are then input into the target image survival model.

[0146] In this case, training the initial image generation model yields the structural block diagram of the target image generation model, as shown below. Figure 13 As shown. PET data samples are acquired and filtered using a first and second filter to obtain data on double-coincidence events and triple-coincidence events. Image reconstruction is performed on the double-coincidence event data to obtain PET image samples. Based on the triple-coincidence event data and the Direct Time of Flight (DTOF) method, histogram image samples of positron survival time are obtained. The PET image samples and the histogram image samples of positron survival time are input into the initial image generation model. Combined with standard survival time images, the initial image generation model is trained to obtain the target image generation model.

[0147] The above embodiments provide different scenarios for the data that can be input to the two channels of the target image generation model when the target image generation model has two input channels. Users can set the input data of the target image generation model according to their actual application needs.

[0148] In one embodiment, the target image generation model includes three input channels: an attenuation image, a histogram image of positron emission tomography (PET) survival time, and a positron emission tomography (PET) image. That is, the intermediate image of the imaging object acquired based on ECT data includes an attenuation image, a PET image, and a histogram image of positron emission tomography (PET) survival time; these three images are then input into the target image survival model.

[0149] In this case, training the initial image generation model yields the structural block diagram of the target image generation model, as shown below. Figure 14 As shown. The descriptions of the attenuation image samples, PET image samples, and histogram image samples of positron survival time can be found in the specific descriptions in the above embodiments, and will not be repeated here.

[0150] In this embodiment, the PET image, the histogram image of the positron survival time, and the decay image are input into the target image generation model. In this way, the target image generation model can obtain rich information and obtain a more accurate positron survival time image.

[0151] In an optional embodiment, the target image generation model includes a single-channel input, which can be any one of a decay image, a histogram image of positron survival time, and a positron emission tomography (PET) image.

[0152] In this case, if the training samples used to train the initial image generation model include attenuated image samples, the block diagram for training the initial image generation model is as follows: Figure 15 As shown. If the training samples for training the initial image generation model include PET image samples, then the block diagram for training the initial image generation model is as follows. Figure 16 As shown. If the training samples for training the initial image generation model include histogram image samples of positron survival time, then the block diagram for training the initial image generation model is as follows. Figure 17 As shown.

[0153] In one embodiment, after determining the positron-electron survival time image of the imaged object, the method further includes:

[0154] The target lifetime image is obtained by iterative reconstruction of the positron survival time image; the resolution of the target lifetime image is greater than that of the positron survival time image.

[0155] After obtaining a positron survival time image of the object being imaged, the computer equipment can use this positron survival time image as the initial image for iterative reconstruction. By iteratively reconstructing this positron survival time image, the target survival time image can be obtained. The resolution of the target survival time image is greater than that of the positron survival time image; that is, the quality of the target survival time image is superior to that of the positron survival time image.

[0156] This embodiment does not limit the specific method for iterative reconstruction of positron survival time images, as long as the function can be achieved.

[0157] In an optional embodiment, the iterative reconstruction method can be any one of the following: maximum likelihood estimation, conjugate gradient method, wavelet transform-based method, etc.

[0158] In this embodiment, after obtaining the positron survival time image, iterative reconstruction of the positron survival time image can yield a target survival time image of higher quality, thereby improving the practicality and reliability of the positron survival time image imaging method.

[0159] Please see Figure 18 One embodiment of this application provides a survival time imaging method for positron-emitting elements, the method comprising the following steps:

[0160] Step 1801: Obtain training samples and use the training samples to train the initial image generation model to obtain the target image generation model; the training samples include attenuation image samples, PET image samples, histogram image samples of positron survival time, and standard survival time images.

[0161] Step 1802: Obtain ECT data of the imaging object; filter the ECT data to obtain data of double coincidence events and triple coincidence events, and determine the attenuation image of the imaging object based on the ECT data;

[0162] Step 1803: Reconstruct the image based on the data of the double coincidence event to obtain the PET image;

[0163] Step 1804: Calculate multiple positron survival time estimates based on the data of the triple coincidence event, and obtain a histogram image of the positron survival time based on the multiple positron survival time estimates;

[0164] Step 1805: Input the attenuation image, PET image, and histogram image of positron survival time into the target image generation model to obtain the positron survival time image of the imaging object.

[0165] Step 1806: Iteratively reconstruct the positron survival time image to obtain the target survival time image; the resolution of the target survival time image is greater than the resolution of the positron survival time image.

[0166] In an optional embodiment, the histogram image of the positron survival time is as follows: Figure 19 As shown, Figure 19 The black area in the middle of the three images is a histogram of positron survival times in three sections (transverse, coronal, and sagittal) of the imaged object. The spectral diagram of the positron survival time image is shown below. Figure 20 As shown, Figure 20 The horizontal axis represents time, and the unit is nanoseconds (ns).

[0167] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0168] Based on the same inventive concept, this application also provides a time-of-life imaging apparatus for implementing the above-described time-of-life imaging method. The solution provided by this apparatus is similar to the implementation described in the above-described method; therefore, the specific limitations in one or more embodiments of the time-of-life imaging apparatus provided below can be found in the limitations of the time-of-life imaging method described above, and will not be repeated here.

[0169] In one embodiment, such as Figure 21 As shown, a positron-emitting element survival time imaging device 20 is provided, comprising: an acquisition module 21 and an input module 22, wherein:

[0170] Acquisition module 21 is used to acquire ECT data of the imaging object;

[0171] The acquisition module 21 is also used to acquire intermediate images of the imaging object based on ECT data; the intermediate images include at least one of the attenuation image of the imaging object, positron emission tomography image, and histogram image of positron survival time.

[0172] The input module 22 is used to input the intermediate image into the target image generation model to obtain the positron survival time image of the imaging object. The target image generation model is a trained neural network model.

[0173] In one embodiment, the acquisition module 21 includes a first filtering unit and a reconstruction unit. The first filtering unit is used to filter ECT data to obtain data of double coincidence events; the reconstruction unit is used to perform image reconstruction on the data of double coincidence events to obtain positron emission tomography (PET) images.

[0174] In one embodiment, the acquisition module 21 further includes a second filtering unit and a first determining unit. The second filtering unit is used to filter the ECT data to obtain data on triple coincidence events; the first determining unit calculates multiple positron survival time estimates based on the triple coincidence event data, and obtains a histogram image of positron survival time based on the multiple positron survival time estimates.

[0175] In one embodiment, the acquisition module 21 further includes an acquisition unit and a second determination unit. The acquisition unit is used to acquire a tomographic image of the imaging object; the acquisition unit is also used to acquire the bed code value corresponding to the ECT data; the second determination unit is used to select at least a portion of the tomographic image based on the bed code value; the second determination unit is also used to acquire an attenuation image based on at least a portion of the tomographic image.

[0176] In one embodiment, the target image generation model includes two-channel input;

[0177] One channel inputs an attenuation image, and the other channel inputs a positron emission tomography (PET) image; or, one channel inputs an attenuation image, and the other channel inputs a histogram image of positron survival time; or, one channel inputs a positron emission tomography (PET) image, and the other channel inputs a histogram image of positron survival time.

[0178] In one embodiment, the target image generation model includes three-channel inputs, which are:

[0179] Attenuation images, histogram images of positron survival time, and positron emission tomography (PET) images.

[0180] In one embodiment, the positron survival time imaging device 20 further includes a reconstruction module. The reconstruction module is used to iteratively reconstruct the positron survival time image to obtain a target survival time image, wherein the resolution of the target survival time image is greater than the resolution of the positron survival time image.

[0181] Each module in the aforementioned positron survival imaging device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0182] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0183] Acquire ECT data of the imaging object;

[0184] Intermediate images of the imaging object are obtained based on ECT data; the intermediate images include at least one of the following: attenuation image of the imaging object, positron emission tomography image, and histogram image of positron survival time;

[0185] The intermediate image is input into a trained neural network model to obtain a positron survival time image of the imaged object.

[0186] The computer device provided in this embodiment is similar in principle and technical effect to the method embodiment described above, and will not be repeated here.

[0187] In one embodiment, the processor also performs the following when performing computed imaging:

[0188] Based on the positron survival time image, the property information of at least one substance is determined.

[0189] After determining the positron-emitting cell lifetime image, computer equipment can analyze the image to determine the properties of at least one substance in the imaged object. These properties may include anaerobic properties, tissue density, and other characteristics.

[0190] Specifically, survival time is positively correlated with anaerobic conditions, so positron emission tomography (PET) survival time images can be used to determine the anaerobic properties of the imaged object; this anaerobic property information can reflect the therapeutic effect on lesions (tumors) present in the imaged object. Survival time is inversely proportional to tissue density, so positron emission tomography (PET) survival time images can be used to determine the tissue density of the imaged object. Changes in tissue density and surrounding density can determine whether abnormalities exist in the tissue.

[0191] In this embodiment, the processor in the computer device can determine the property information of at least one substance based on the positron survival time image. This allows for the acquisition of property information of at least one substance that reflects whether the imaged object is normal, thus making the computer device more practical.

[0192] In one embodiment, the computer device further includes a display that simultaneously displays a positron survival time image and property information of the substance.

[0193] After determining a positron survival time image and identifying the property information of at least one substance based on that image, the computer device can display both the positron survival time image and the substance's property information on a monitor. The substance's property information can be annotated at the corresponding location in the positron survival time image, or it can be displayed separately from the image. That is, the monitor includes an image display area and an information display area; the image display area shows the positron survival time image, and the information display area shows the substance's property information.

[0194] In this embodiment, the positron survival time image and the property information of the substance are displayed simultaneously on the display of the computer device. This makes it easier for the user to obtain the survival time map of the imaging object and the property information of each substance in the imaging object more clearly.

[0195] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0196] Acquire ECT data of the imaging object;

[0197] Intermediate images of the imaging object are obtained based on ECT data; the intermediate images include at least one of the following: attenuation image of the imaging object, positron emission tomography image, and histogram image of positron survival time;

[0198] The intermediate image is input into a trained neural network model to obtain a positron survival time image of the imaged object.

[0199] The computer device readable storage medium provided in this embodiment is similar in principle and technical effect to the method embodiment described above, and will not be repeated here.

[0200] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0201] Acquire ECT data of the imaging object;

[0202] Intermediate images of the imaging object are obtained based on ECT data; the intermediate images include at least one of the following: attenuation image of the imaging object, positron emission tomography image, and histogram image of positron survival time;

[0203] The intermediate image is input into a trained neural network model to obtain a positron survival time image of the imaged object.

[0204] The computer device program product provided in this embodiment has a similar implementation principle and technical effect to the above method embodiment, and will not be described again here.

[0205] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0206] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0207] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A positronic element lifetime imaging method, characterized by, The method includes: Acquire ECT data of the imaging object; An intermediate image of the imaging object is obtained based on the ECT data; the intermediate image includes at least one of the following: an attenuation image of the imaging object, a positron emission tomography (PET) image, and a histogram image of positron survival time; The intermediate image is input into the target image generation model to obtain the positron survival time image of the imaging object. The target image generation model is a trained neural network model.

2. The method of claim 1, wherein, The intermediate image is a positron emission tomography (PET) image. The process of obtaining the intermediate image of the imaging object based on the ECT data includes: The ECT data is filtered to obtain data on double-matching events; The data from the double coincidence event are used for image reconstruction to obtain the positron emission tomography (PET) image.

3. The method of claim 1, wherein, The intermediate image is a histogram image of the positron survival time. The process of obtaining the intermediate image of the imaging object based on the ECT data includes: The ECT data is filtered to obtain data on triple-matching events; Based on the data from the three coincidence events, multiple positron survival time estimates are calculated, and a histogram image of the positron survival time is obtained based on the multiple positron survival time estimates.

4. The method of claim 1, wherein, The intermediate image is an attenuated image. The process of obtaining the intermediate image of the imaging object based on the ECT data includes: Acquire a tomographic image of the imaging object; Obtain the bed code value corresponding to the ECT data; At least a portion of the computed tomography image is selected based on the bed code value; The attenuation image is obtained based on at least a portion of the tomographic scan image.

5. The method of claim 1, wherein, The target image generation model includes two input channels; One channel receives the attenuation image, and the other channel receives the positron emission tomography (PET) image; or... One channel is used to input the attenuation image, and the other channel is used to input the histogram image of the positron survival time; or, One channel inputs the positron emission tomography (PET) image, and the other channel inputs a histogram image of the positron survival time.

6. The method of claim 1, wherein, The target image generation model includes three-channel input, which are as follows: The attenuation image, the histogram image of the positron survival time, and the positron emission tomography image.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: The positron survival time image is iteratively reconstructed to obtain a target survival time image, wherein the resolution of the target survival time image is greater than the resolution of the positron survival time image.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it performs the following steps: Acquire ECT data of the imaging object; An intermediate image of the imaging object is obtained based on the ECT data; the intermediate image includes at least one of the following: attenuation image of the imaging object, positron emission tomography image, and histogram image of positron survival time; The intermediate image is input into a trained neural network model to obtain a positron survival time image of the imaging object.

9. The computer device of claim 8, wherein, The processor also implements: Based on the positron survival time image, the property information of at least one substance is determined.

10. The computer device of claim 9, wherein, Also includes: The display simultaneously shows the positron survival time image and the property information of the substance.

Images