Nuclear medicine diagnostic device, data processing method and program

Abstract

To improve usability.SOLUTION: A nuclear medicine diagnosis apparatus includes an acquisition section, a division section, and an identification section. The acquisition section acquires nuclear medicine data. The division section time-divides the nuclear medicine data into at least two or more, first nuclear medicine data and second nuclear medicine data. The identification section identifies a biological accumulation region on the basis of a temporal change in data values included in the first nuclear medicine data and the second nuclear medicine data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The embodiments disclosed in the present specification and drawings relate to a nuclear medicine diagnosis apparatus, a data processing method, and a program. [Background technology]

[0002] FDG (fluorodeoxyglucose)-PET (Positron Emission Tomography) images can show physiological FDG uptake in addition to tumor-related FDG uptake. Physiological uptake in the brain, heart, bladder, tonsils, ovaries during ovulation, and endometrium is relatively consistent in location and morphology and easy to identify. On the other hand, physiological uptake in the digestive system, particularly in the large intestine, can vary in location and morphology from patient to patient. In these cases, image readers rely on their experience to determine whether the uptake is tumor or physiological.

[0003] However, it is desirable that the nuclear medicine imaging device can provide information that supports accurate judgment in the physiological accumulation judgment process that depends on the experience of the radiologist. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2017 / 179256 Summary of the Invention [Problem to be solved by the invention]

[0005] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to improve diagnostic imaging capabilities. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of the configurations shown in the embodiments described below can also be positioned as other problems. [Means for solving the problem]

[0006] A nuclear medicine diagnosis apparatus according to an embodiment includes an acquisition unit, a division unit, and an identification unit. The acquisition unit acquires nuclear medicine data. The division unit time-divides the nuclear medicine data into at least two or more pieces of first nuclear medicine data and second nuclear medicine data. The identification unit identifies a physiological accumulation region based on time changes in data values ​​included in the first nuclear medicine data and the second nuclear medicine data. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram showing an example of a nuclear medicine diagnosis apparatus according to an embodiment. [Figure 2] FIG. 2 is a flowchart illustrating the flow of processing performed by the nuclear medicine diagnosis apparatus according to the first embodiment. [Figure 3] FIG. 3 is a diagram illustrating the processing according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating the processing according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating the processing according to the embodiment. [Figure 6] FIG. 6 is a diagram showing an example of a user interface of the nuclear medicine diagnosis apparatus according to the first embodiment. [Figure 7] FIG. 7 is a diagram showing an example of a user interface of the nuclear medicine diagnosis apparatus according to the fourth embodiment. [Figure 8] FIG. 8 is a diagram showing an example of a user interface for the nuclear medicine diagnosis apparatus according to the modified example of the first embodiment, the fifth embodiment, and the sixth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments of a nuclear medicine diagnosis apparatus, a data processing method, and a program will be described in detail with reference to the drawings.

[0009] (First embodiment) Fig. 1 is a diagram showing the configuration of a PET device 100 as a nuclear medicine diagnosis device according to an embodiment. As shown in Fig. 1, the PET device 100 according to an embodiment includes a gantry device 1 and a console device 2 as a medical image processing device. The gantry device 1 includes a detector 3, a front-end circuit 102, a tabletop 103, a bed 104, and a bed driver 106.

[0010] Detector 3 is a detector that detects radiation by detecting scintillation light (fluorescence), which is light re-emitted when an annihilation gamma ray emitted from a positron in subject P interacts with a light emitter (scintillator) and causes a substance that has become excited and transitions back to the ground state. Detector 3 detects radiation energy information of the annihilation gamma ray emitted from a positron in subject P. Multiple detectors 3 are arranged in a ring shape around subject P, and are made up of, for example, multiple detector blocks.

[0011] One example of a specific configuration of detector 3 is a photon-counting, Anger-type detector, which includes, for example, a scintillator, a photodetector, and a light guide. Another example of a configuration is a non-Anger-type detector in which a scintillator and a photodetector are optically coupled one-to-one. That is, each pixel included in detector 3 includes a scintillator and a photodetector that detects generated scintillation light.

[0012] The scintillator converts incident annihilation gamma rays emitted from positrons in the subject P into scintillation photons (optical photons) and outputs the light. The scintillator is formed of scintillator crystals such as LYSO (Lutetium Yttrium Oxyorthosilicate), LSO (Lutetium Oxyorthosilicate), LGSO (Lutetium Gadolinium Oxyorthosilicate), BGO, etc., and is arranged, for example, two-dimensionally.

[0013] Examples of photodetector elements that can be used include SiPMs (Silicon photomultipliers) and photomultiplier tubes. Photomultiplier tubes have a photocathode that receives scintillation light and generates photoelectrons, multiple dynodes that provide an electric field to accelerate the generated photoelectrons, and an anode through which the electrons flow. They multiply photoelectrons generated by scintillation light output from the scintillator and convert them into an electrical signal.

[0014] Furthermore, the gantry device 1 generates counting information from the output signal of the detector 3 using the front-end circuit 102, and stores the generated counting information in the memory unit 130 of the console device 2. The detector 3 is divided into multiple blocks and includes the front-end circuit 102.

[0015] The front-end circuit 102 converts the output signal of the detector 3 into digital data and generates counting information. This counting information includes the detection position, energy value, and detection time of the annihilation gamma ray. For example, the front-end circuit 102 identifies multiple photodetector elements that simultaneously converted scintillation light into electrical signals. The front-end circuit 102 then identifies a scintillator number (P) indicating the position of the scintillator onto which the annihilation gamma ray was incident. The position of the scintillator onto which the annihilation gamma ray was incident may be identified by performing a center of gravity calculation based on the position of each photodetector element and the intensity of the electrical signal. Furthermore, when the element sizes of the scintillators and the photodetector elements correspond to each other, the scintillator corresponding to the photodetector element from which the output was obtained may be identified as the scintillator position onto which the annihilation gamma ray was incident.

[0016] Furthermore, the front-end circuit 102 identifies the energy value (E) of the annihilation gamma ray incident on the detector 3 by integrating the intensity of the electrical signal output from each photodetector element. The front-end circuit 102 also identifies the detection time (T) at which the detector 3 detects scintillation light due to the annihilation gamma ray. The detection time (T) may be an absolute time or the elapsed time from the start of imaging. In this way, the front-end circuit 102 generates counting information including the scintillator number (P), the energy value (E), and the detection time (T).

[0017] The front-end circuit 102 is realized by a circuit such as a CPU (Central Processing Unit), a GPU (Graphical Processing Unit), an Application Specific Integrated Circuit (ASIC), or a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)). The front-end circuit 102 is an example of a front-end unit.

[0018] The top board 103 is a bed on which the subject P is placed, and is placed on the bed 104. The bed driving unit 106 moves the top board 103 under the control of the control function 105f of the processing circuit 150. For example, the bed driving unit 106 moves the top board 103 to move the subject P into the imaging opening of the gantry device 1.

[0019] The console device 2 accepts operations of the PET device 100 by an operator, controls the capturing of PET images, and reconstructs the PET images using the counting information collected by the gantry device 1. As shown in FIG. 1, the console device 2 includes a processing circuit 150, an input device 110, a display 120, and a storage unit 130. The various units included in the console device 2 are connected via a bus. Details of the processing circuit 150 will be described later.

[0020] The input device 110 is a mouse, keyboard, or the like used by the operator of the PET device 100 to input various instructions and settings, and transfers the input instructions and settings to the processing circuitry 150. For example, the input device 110 is used to input an instruction to start imaging.

[0021] The display 120 is a monitor or the like that is viewed by the operator, and under the control of the processing circuit 150, displays the subject's respiratory waveform and PET images, and displays a GUI (Graphical User Interface) for receiving various instructions and settings from the operator.

[0022] The storage unit 130 stores various data used in the PET device 100. The storage unit 130 is configured with, for example, a memory, and is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, a hard disk, an optical disk, etc. The storage unit 130 stores counting information, which is information in which a scintillator number (P), an energy value (E), and a detection time (T) are associated with each other, coincidence information in which a set of counting information is associated with a coincidence number, which is a serial number of the coincidence information, a reconstructed PET image, etc.

[0023] The processing circuitry 150 has an acquisition function 150a, a division function 150b, a specification function 150c, a reconstruction function 150d, a system control function 150e, a control function 150f, a reception function 150g, an image generation function 150h, a display control function 150i, and a learning function 150j. Note that each function other than the system control function 150j and the bed control function 150k will be explained in detail later.

[0024] In the embodiment, each processing function performed by the acquisition function 150a, division function 150b, identification function 150c, reconstruction function 150d, system control function 150e, control function 150f, reception function 150g, image generation function 150h, display control function 150i, and learning function 150j is stored in the storage unit 130 in the form of a program executable by a computer. The processing circuitry 150 is a processor that realizes the function corresponding to each program by reading and executing the program from the storage unit 130. In other words, the processing circuitry 150 in a state in which each program has been read has each function shown in the processing circuitry 150 of FIG. 1.

[0025] 1 illustrates a single processing circuit 150 that implements the processing functions performed by the acquisition function 150a, division function 150b, identification function 150c, reconstruction function 150d, system control function 150e, control function 150f, reception function 150g, image generation function 150h, display control function 150i, and learning function 150j. However, the processing circuit 150 may be configured by combining multiple independent processors, and each processor may execute a program to implement the function. In other words, each of the above functions may be configured as a program, and one processing circuit 150 may execute each program. As another example, a specific function may be implemented in a dedicated, independent program execution circuit.

[0026] The term "processor" used in the above description refers to circuits such as a CPU (Central Processing Unit), a GPU (Graphical Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)). The processor realizes its functions by reading and executing programs stored in the memory unit 130.

[0027] In FIG. 1, the acquisition function 150a, division function 150b, identification function 150c, reconstruction function 150d, system control function 150e, control function 150f, reception function 150g, image generation function 150h, display control function 150i, and learning function 150j are examples of an acquisition unit, division unit, identification unit, reconstruction unit, system control unit, control unit, reception unit, image generation unit, display control unit, and learning unit, respectively.

[0028] The processing circuitry 150 controls the gantry device 1 and the console device 2 using a system control function 150e, thereby performing overall control of the PET device 100. For example, the processing circuitry 150 controls imaging in the PET device 100 using a system control unit 150e.

[0029] The processing circuitry 105 controls the bed driving unit 106 by means of a control function 150f.

[0030] Next, the background of the embodiment will be briefly described.

[0031] FDG (fluorodeoxyglucose)-PET (Positron Emission Tomography) images can show physiological FDG uptake in addition to tumor-related FDG uptake. Physiological uptake in the brain, heart, bladder, tonsils, ovaries during ovulation, and endometrium is relatively consistent in location and morphology and easy to identify. On the other hand, physiological uptake in the digestive system, particularly in the large intestine, can vary in location and morphology from patient to patient. In these cases, image readers rely on their experience to determine whether the uptake is tumor or physiological.

[0032] However, it is desirable that the PET device 100 can provide information that supports accurate judgment in the physiological accumulation judgment process that depends on the experience of the radiologist.

[0033] In view of this background, the nuclear medicine diagnosis apparatus 100 according to the embodiment includes a processing circuit 150. The processing circuit 150 acquires nuclear medicine data using an acquisition function 150a, divides the nuclear medicine data into at least two or more pieces of first nuclear medicine data and second nuclear medicine data using a division function 150b, and identifies physiological accumulation regions based on time changes in data values ​​included in the first nuclear medicine data and the second nuclear medicine data using an identification function 150c.

[0034] Next, this processing will be explained using Fig. 2 to Fig. 6. Fig. 2 is a flowchart explaining the flow of processing performed by the nuclear medicine diagnosis apparatus according to the first embodiment.

[0035] First, in step S100, the processing circuitry 150 acquires nuclear medicine data by the acquisition function 150a from the front-end circuitry 102. Here, the nuclear medicine data acquired by the processing circuitry 150 from the front-end circuitry 102 by the acquisition function 150a includes, for example, raw data, that is, counting information including, for example, a scintillator number (P), an energy value (E), and a detection time (T).

[0036] As another example, the nuclear medicine data acquired by the processing circuitry 150 using the acquisition function 150a is a reconstructed image obtained by performing reconstruction processing on the count information, which is the raw data.

[0037] Next, in step S110, the processing circuitry 150 time-divides the nuclear medicine data into at least two or more pieces, and divides the data into first nuclear medicine data and second nuclear medicine data. This situation is shown in FIG. 3. In FIG. 3, nuclear medicine data 10a, 10b, 10c, and 10d represent nuclear medicine data corresponding to a first time, a second time, a third time, and a fourth time, respectively, when the processing circuitry 150 performs time-division processing on a series of nuclear medicine data acquired by the acquisition function 150a. In the example of FIG. 3, for example, the nuclear medicine data 10a and the nuclear medicine data 10b are examples of the first nuclear medicine data, and the nuclear medicine data 10c and the nuclear medicine data 10d are examples of the second nuclear medicine data. As another example, for example, the nuclear medicine data 10a may be the first nuclear medicine data, and the nuclear medicine data 10b may be the second nuclear medicine data.

[0038] Subsequently, in step S120, the processing circuitry 150 uses the identification function 150c to identify a physiological accumulation region based on the time change of the data values ​​included in the first nuclear medicine data and the second nuclear medicine data.

[0039] This processing will be explained using Figures 3 to 5. In the following, in Figure 3, the nuclear medicine data 10a relating to a first time point has a tumor accumulation 11a and a physiological accumulation 12a, and the nuclear medicine data 10b relating to a second time point, the nuclear medicine data 10c relating to a third time point, and the nuclear medicine data 10d relating to a fourth time point have the tumor accumulation 11b and the physiological accumulation 12b, the tumor accumulation 11c and the physiological accumulation 12c, and the tumor accumulation 11d and the physiological accumulation 12d, respectively.

[0040] The difference between tumor accumulation and physiological accumulation will now be explained using Figures 4 and 5. In Figure 4, curve 11 shows the time change in SUV (Standard Uptake Value) of the tumor accumulation area in Figure 3. In Figure 5, curve 12 shows the time change in SUV of the physiological accumulation area in Figure 3.

[0041] Comparing Figures 4 and 5, tumor accumulation shows slower changes in signal value compared to physiological accumulation, and signal values ​​change over a longer time scale, as shown in Figure 4. For example, in tumor accumulation, the rate of change in pixel value at the time-varying site can be explained by the rate of change due to the decay of the drug-labeled isotope.

[0042] On the other hand, as shown in Figure 5, physiological accumulation, compared to tumor accumulation, exhibits rapid changes in signal values, changes over a short time scale, and the change tends to be irregular. Therefore, the rate of change in pixel values ​​at time-varying sites in physiological accumulation cannot be explained solely by the rate of change due to the decay of the drug-labeling isotope, and results in, for example, short-term or irregular changes. Furthermore, from a spatial perspective, in the case of tumor accumulation, signal values ​​continue to appear in relatively the same area, whereas in the case of physiological accumulation, the spatial area in which signal values ​​appear tends to change irregularly over time. Therefore, the processing circuit 150, using the specific function 150c, can distinguish between tumor accumulation and physiological accumulation by utilizing the difference in the behavior of the change in signal values ​​between tumor accumulation and physiological accumulation.

[0043] As an example, the processing circuit 150 may use the specific function 150c to compare the decay time or increase time of the data values ​​included in the first nuclear medicine data and the second nuclear medicine data with a threshold value. The physiological accumulation region is identified by the identification function 150c. For example, the processing circuit 150 identifies a data value as relating to the physiological accumulation region when the time scale of the decay time or increase time of the data value is shorter than a predetermined threshold defined as the time scale for tumor accumulation, and identifies the data value as relating to tumor accumulation when the time scale of the decay time or increase time of the data value is longer than the threshold. As another example, the processing circuit 150 identifies a data value as relating to physiological accumulation when the rate of change of the data value exhibits behavior that cannot be explained solely by the rate of change due to the decay of the drug-labeling isotope, by the identification function 150c.

[0044] As another example, the processing circuitry 150 uses the identification function 150c to identify a physiological accumulation region by comparing the degree of agreement between the data values ​​included in the first nuclear medicine data and the second nuclear medicine data and a model waveform with a threshold. As an example, the processing circuitry 150 uses the identification function 150c to identify a data value as relating to a physiological accumulation region when the degree of agreement between the data value and a model waveform assuming tumor accumulation is below a threshold. Furthermore, the processing circuitry 150 uses the identification function 150c to identify a data value as representing tumor accumulation when the degree of agreement between the data value and the model waveform exceeds a threshold.

[0045] Processing circuitry 150 may also use identification function 150c to calculate, for each accumulation included in the region of interest, a probability value that the accumulation is a physiological accumulation. Processing circuitry 150 may also use identification function 150c to calculate, for each accumulation included in the region of interest, a probability value that the accumulation is a tumor accumulation.

[0046] Next, in step S130, processing circuitry 150 causes display control function 150i to display the identified physiological accumulation region on display 120 as a display unit. As an example, processing circuitry 150 marks the identified physiological accumulation region and tumor accumulation region in different colors and displays them on display 120 as a display unit.

[0047] An example of such a user interface is shown in Fig. 6. As shown in Fig. 6, processing circuitry 150, using display control function 150i, extracts physiological accumulation regions 12a, 12b, and 12c identified in step S120 and tumor accumulation regions 11a, 11b, and 11c identified in step S120 for each time phase and displays them on display 120 as a display unit. As an example, processing circuitry 150, using display control function 150i, displays physiological accumulation regions 12a, 12b, and 12c identified in step S120 and tumor accumulation regions 11a, 11b, and 11c identified in step S120 for each time phase while marking them in different colors on display 120 as a display unit.

[0048] As described above, in the nuclear medicine diagnosis apparatus according to the first embodiment, the processing circuitry 150 identifies physiological accumulation regions based on time-shared nuclear medicine data and, if necessary, displays the identified physiological accumulation regions distinguished from other regions. This allows the user to easily visually identify physiological accumulation regions and tumor accumulation regions, improving usability.

[0049] (Modification of the first embodiment) As a modified example of this embodiment, for example, in a step between step S110 and step S120, processing circuit 150 may receive an input of a region selection from the user using reception function 150g, and when processing circuit 150 receives an input of a region selection from the user using reception function 150g, in step S130, processing circuit 150 may identify a physiological accumulation region included in the selected region using identification function 150c.

[0050] An example of such a user interface is shown in FIG. 8. In the example of FIG. 8, processing circuitry 150, through display control function 150i, causes display 120 to display image 31 for accepting a user's setting of region of interest 32 on display screen 30. Image 31 for accepting a user's setting of region of interest 32 may be, for example, a still image, an image at a predetermined time phase, or a composite image generated from images at multiple time phases. Processing circuitry 150 also uses reception function 150g to accept changes to the setting of region of interest 32 via buttons 33a, 33b, 33c, and 33d. When the user selects button 34, processing circuitry 150 uses identification function 150c to identify physiological accumulation regions and tumor accumulation regions included in the region of interest 32 currently set, and then uses display control function 150c to display on display 120 the physiological accumulation regions and tumor accumulation regions identified using, for example, the user interface described in FIG. 6.

[0051] According to the modified example of the first embodiment, the user can freely set a region of interest, and physiological accumulation regions can be automatically extracted for the set region of interest, thereby further improving usability, reducing diagnostic effort, and improving diagnostic accuracy.

[0052] (Second embodiment) In the first embodiment, a case has been described in which a physiological accumulation region is identified in step S120 based on a temporal change in data values ​​included in the first nuclear medicine data and the second nuclear medicine data, which are image data after image reconstruction processing has been performed, but the embodiment is not limited to the above example. In the second embodiment, in step S120, a physiological accumulation region is identified based on a temporal change in data values ​​included in the first nuclear medicine data and the second nuclear medicine data, which are raw data (data before image reconstruction processing has been performed). Here, an example of the raw data is, for example, counting information including a scintillator number (P), an energy value (E), and a detection time (T), which the processing circuitry 150 acquires from the front-end circuitry 102 using the acquisition function 150a.

[0053] In the second embodiment, for example, in step S100, the processing circuit 150 acquires raw data, such as a plurality of counting information pieces including a scintillator number (P), an energy value (E), and a detection time (T), from the front-end circuit 102 using the acquisition function 150a. Subsequently, in step S110, the processing circuit 150 performs time-phase division on the counting information pieces, which are raw data, using the division function 150b to generate first and second nuclear medicine data. Subsequently, in step S120, the processing circuit 150 identifies a physiological accumulation region based on time changes in data values ​​included in the first and second nuclear medicine data using the identification function 150c. As an example, the processing circuit 150 calculates difference data between the first and second nuclear medicine data using the identification function 150c, and identifies the physiological accumulation region based on the magnitude of the difference data. In the first embodiment, the difference between the first nuclear medicine data and the second nuclear medicine data is a pixel value, whereas in the second embodiment, the difference between the first nuclear medicine data and the second nuclear medicine data is merely difference data that is not a pixel value. However, by comparing the decay time or increase time of the difference data with a predetermined threshold, a physiological accumulation region can be identified, as in the first embodiment.

[0054] (Third embodiment) The embodiments are not limited to the above examples. In a third embodiment, a case will be described in which, as a method for identifying physiological accumulation, a trained model obtained by machine learning using a neural network is used to perform the process of identifying physiological accumulation in step S120 of Fig. 2. That is, in the third embodiment, in step S120, the processing circuit 150, using the identification function 150c, inputs the first nuclear medicine data and the second nuclear medicine data obtained by time division into a trained model generated by learning using a group of clinical images linked to the presence or absence of physiological accumulation, thereby identifying a physiological accumulation region.

[0055] Here, for example, a group of clinical images classified by a radiologist into the presence or absence of physiological accumulation and the location are used as training data for the neural network. That is, the processing circuitry 150 uses, as training data for the neural network, data linking a clinical image, information representing the location of the clinical image, and information indicating whether the clinical image contains physiological accumulation, as data for training data. For example, a single piece of training data used for training is information linking a clinical image location "large intestine," data of the clinical image of the large intestine at multiple time phases, and a flag "1" indicating that the clinical image contains physiological accumulation. However, the format of the training data used for training according to the embodiment is not limited to the above example. As another example, a single piece of training data may be information linking a clinical image location "large intestine," clinical image of the large intestine at one time phase, and a flag "1" indicating that the clinical image contains physiological accumulation. As another example, the learning data may not include information about the site, and a single piece of learning data used for learning may be, for example, information linking data of clinical images at multiple time phases with information indicating whether the clinical images contain physiological accumulation.In addition, instead of information on whether the clinical images contain physiological accumulation, information indicating the type of accumulation contained in the clinical images, for example, information that is "1" for physiological accumulation and "2" for tumor accumulation, may be used as learning data.

[0056] As described above, when executing learning, the processing circuit 150 performs machine learning in the learning function 150j by inputting multiple pieces of data linked to, for example, data at multiple time phases of a clinical image, information representing the location of the clinical image, and information on whether the clinical image contains physiological accumulation, into a neural network, thereby generating a learned model.

[0057] Next, in step S120, during execution of the trained model, the processing circuitry 150 inputs the first nuclear medicine data and the second medical data obtained by time division into the trained model using the identification function 150c, thereby determining whether or not a physiological accumulation exists in the image to be interpreted and the location of the physiological accumulation. For example, if the trained model outputs a value of "1" representing the presence or absence of a physiological accumulation, the processing circuitry 150 determines using the identification function 150c that the image to be interpreted has a physiological accumulation. Also, for example, if the trained model outputs a real number between 0 and 1 representing the probability that a physiological accumulation is included in the region of interest, the processing circuitry 150 determines using the identification function 150c that the probability that the image to be interpreted has a physiological accumulation is the real number. As another example, if the learning model outputs 0, 1, or 2, the processing circuit 150 determines, using the specific function 150c, that if the output result is 0, no accumulation is present, if the output result is 1, physiological correction is present, and if the output result is 2, tumor accumulation is present.

[0058] In this way, in the third embodiment, a neural network is used to determine physiological accumulation, which improves the accuracy of identifying physiological accumulation and further improves usability.

[0059] (Fourth embodiment) The embodiments are not limited to the above examples. In the fourth embodiment, a case will be described in which, in response to a request from a user, the processing circuitry 150 causes the display control function 150i to additionally display on the display 120, information that serves as a basis or a basis for determining whether or not a region that may be a physiological accumulation region is a physiological accumulation region. As an example, the processing circuitry 150 uses the reception function 150g to receive an input of a region selection from the user, and uses the display control function 150i to display data for a plurality of time phases related to the region on the display 120 as a display unit.

[0060] An example of such a user interface is shown in FIG. 7. Processing circuitry 150, using display control function 150i, causes display 120 to display image 20 on display screen 19 for accepting settings of regions of interest 21, 22, etc. from the user. The image 20 for accepting settings of region of interest 21, etc. from the user may be, for example, a still image, an image of a predetermined time phase, or a composite image generated from images of multiple time phases. Processing circuitry 150 also uses reception function 150g to accept changes to the setting of region of interest 21 via buttons 23a, 23b, 23c, and 23d. Similarly, processing circuitry 150 also uses reception function 150g to accept changes to the setting of region of interest 22 via buttons 24a, 24b, 24c, and 24d.

[0061] Here, when the user clicks on the region of interest 21, for example, the processing circuitry 150 causes the display control function 150i to display auxiliary information 25 on the display 120 serving as a display unit. As an example, when the user clicks on the region of interest 21, the processing circuitry 150 causes the display control function 150i to display data of multiple time phases related to the region of interest 21 as auxiliary information 25 on the display 120 serving as a display unit. Here, the data of multiple time phases related to the region of interest 21 may be data representing average values ​​of signal values ​​within the region of interest 21 at each of multiple times, or may be data representing signal values ​​at a certain point within the region of interest 21 at each of multiple times.

[0062] Furthermore, the processing circuit 150 may use the display control function 150i to cause the display 120, which serves as a display unit, to display information regarding whether or not the signal present in the region of interest 21 is due to physiological accumulation as auxiliary information 25. For example, in step S120, if the processing circuit 150 uses the identification function 150c to determine that the region of interest 21 is highly likely to be physiological accumulation, the processing circuit 150 uses the display control function 150i to cause the display 120, which serves as a display unit, to display a message indicating that the data present in the region of interest is highly likely to be physiological accumulation as auxiliary information 25. Also, in step S120, if the processing circuit 150 uses the identification function 150c to determine that the region of interest 21 is highly likely to be tumor accumulation, the processing circuit 150 uses the display control function 150i to cause the display 120, which serves as a display unit, to display a message indicating that the data present in the region of interest is highly likely to be tumor accumulation as auxiliary information 25.

[0063] Furthermore, in step S120, if the processing circuit 150 calculates the probability that the signal present in the region of interest is a tumor accumulation or a physiological accumulation using the display control function 150i, the processing circuit 150 may cause the display control function 150i to display the probability as auxiliary information 25 on the display 120 serving as a display unit.

[0064] Similarly, when the user clicks on the region of interest 22, the processing circuitry 150 causes the display control function 150i to display data on multiple time phases related to the region of interest 22 as auxiliary information 26 on the display 120 as a display unit.

[0065] As described above, in the fourth embodiment, when a user selects regions of interest 21, 22, processing circuitry 150 causes display control function 150i to display auxiliary information 25, 26, which are used to determine whether the region of interest is physiological accumulation or tumor accumulation, on display 120 as a display unit. This allows the user to more accurately determine whether the signal value related to the region of interest is due to physiological accumulation or tumor accumulation, improving usability and enabling further reduction in diagnostic effort and improvement in diagnostic accuracy.

[0066] (Fifth embodiment) In the fifth embodiment, when a physiological accumulation is identified based on the embodiments described above, a corrected image in which the physiological accumulation has been removed from the image is provided to the user. That is, the processing circuitry 150 generates third nuclear medicine data using the image generation function 150h, based on the physiological accumulation region identified by the identification function 150c, by correcting the pixel values ​​of the region determined to be a physiological accumulation region. Here, correcting the pixel values ​​of the region determined to be a physiological accumulation region means, for example, setting the pixel values ​​of the region determined to be a physiological accumulation region to 0 or replacing them with the average pixel values ​​of the surrounding pixels.

[0067] An example of such a user interface is shown in Fig. 8. In Fig. 8, when a user clicks button 35, processing circuitry 150 causes image generation function 150h to generate third nuclear medicine data in which pixel values ​​of a portion determined to be a physiological accumulation region within region of interest 32 are corrected. For example, processing circuitry 150 causes image generation function 150h to generate third nuclear medicine data in which pixel values ​​of a portion determined to be a physiological accumulation region within region of interest are replaced with 0. Next, processing circuitry 150 causes display control function 150i to display the generated third nuclear medicine data on display 120 as a display unit, for example, as shown on the right side of Fig. 8.

[0068] As described above, in the fifth embodiment, an image in which the physiological accumulation region has been removed is displayed, thereby further reducing the diagnostic effort and improving the diagnostic accuracy.

[0069] (Sixth embodiment) In the sixth embodiment, in order to easily check whether or not a physiological accumulation site includes tumor accumulation, gamma correction is performed on the physiological accumulation site in the reconstructed image.

[0070] Here, gamma correction is a nonlinear transformation characterized by a parameter γ. Specifically, gamma correction converts input pixel values ​​to V in , constant A, output pixel value V out As, V out = AV γ in This is an example of a transformation that can visually highlight differences in pixel values. Therefore, by performing gamma transformation on a reconstructed image, if a physiological accumulation site contains a tumor accumulation, the tumor accumulation can be more easily detected.

[0071] An example of such a user interface is shown in Fig. 8. When the user selects the button 36, the processing circuitry 150 causes the image generation function 150h to generate fourth nuclear medicine data for the physiological accumulation region identified by the identification function 150c, by performing gamma correction characterized by the parameter γ input in the input field 37. The value of the parameter γ can be changed using, for example, the button 38.

[0072] As described above, in the sixth embodiment, input for performing gamma correction is received from the user, which allows the user to easily check whether the physiological accumulation site contains tumor accumulation, thereby further reducing the diagnostic effort and improving the diagnostic accuracy.

[0073] According to at least one of the embodiments described above, usability can be improved.

[0074] With respect to the above embodiment, the following supplementary notes are disclosed as one aspect and optional features of the invention.

[0075] (Appendix 1) A nuclear medicine diagnosis apparatus according to one aspect of the present invention includes an acquisition unit, a division unit, and an identification unit. The acquisition unit acquires nuclear medicine data. The division unit time-divides the nuclear medicine data into at least two or more pieces of first nuclear medicine data and second nuclear medicine data. The identification unit identifies a physiological accumulation region based on time changes in data values ​​included in the first nuclear medicine data and the second nuclear medicine data.

[0076] (Appendix 2) a receiving unit that receives an input of a region selection from a user; The imaging device may further include a display control unit that causes a display unit to display data on a plurality of time phases relating to the region.

[0077] (Appendix 3) further comprising a reception unit that receives an input of a region selection from a user; The identifying unit may identify the physiological accumulation region included in the region when the accepting unit accepts an input of selection of the region from the user.

[0078] (Appendix 4) The apparatus may further include an image generating unit that generates third nuclear medicine data in which pixel values ​​of the area determined to be the physiological accumulation area are corrected based on the physiological accumulation area identified by the identifying unit.

[0079] (Appendix 5) The identification unit may identify the physiological accumulation region by inputting the first nuclear medicine data and the second nuclear medicine data into a trained model generated by learning using a group of clinical images linked to the presence or absence of physiological accumulation.

[0080] (Appendix 6) The imaging device may further include an image generating unit that generates fourth nuclear medicine data obtained by performing gamma correction on the physiological accumulation region identified by the identifying unit.

[0081] (Appendix 7) The identifying unit may identify the physiological accumulation region by comparing a decay time of the data value with a threshold value, or by comparing a degree of agreement between the data value and a model waveform with a threshold value.

[0082] (Appendix 8) The identification unit may identify a data value as relating to a physiological accumulation region if the time scale of the decay time or increase time of the data value is shorter than a predetermined threshold defined as the time scale for tumor accumulation.

[0083] (Appendix 9) The identification unit may identify a data value as being related to physiological accumulation when the rate of change of the data value exhibits behavior that cannot be explained solely by the rate of change due to decay of the drug-labeling isotope.

[0084] (Appendix 10) The identifying unit may identify a data value as relating to a physiological accumulation region when the degree of agreement of the data value with a model waveform assuming tumor accumulation is below a threshold.

[0085] (Appendix 11) One aspect of the present invention provides a data processing method, comprising: Acquire nuclear medicine data, The nuclear medicine data is time-divided into at least two or more parts, and divided into first nuclear medicine data and second nuclear medicine data; A physiological accumulation region is identified based on the time change of data values ​​included in the first nuclear medicine data and the second nuclear medicine data.

[0086] (Appendix 12) One aspect of the present invention provides a data processing method, comprising: On the computer, Acquire nuclear medicine data, The nuclear medicine data is time-divided into at least two or more parts, and divided into first nuclear medicine data and second nuclear medicine data; A process of identifying a physiological accumulation region based on time changes in data values ​​included in the first nuclear medicine data and the second nuclear medicine data is executed.

[0087] Although several embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0088] 150 Processing Circuit 150a Acquisition Function 150b division function 150c specific functions 150d reconfiguration function 150e System Control Functions 150f control function 150g Reception function 150h image generation function 150i display control function 150j Learning Function

Claims

1. an acquisition unit for acquiring nuclear medicine data; a division unit that divides the nuclear medicine data into at least two or more time segments and divides the data into first nuclear medicine data and second nuclear medicine data; an identifying unit that identifies a physiological accumulation region based on time changes in data values ​​included in the first nuclear medicine data and the second nuclear medicine data; an image generating unit that generates corrected third nuclear medicine data by replacing pixel values ​​of a region determined to be the physiological accumulation region with an average value of surrounding pixel values ​​based on the physiological accumulation region identified by the identifying unit; a receiving unit that receives an input of a region selection from a user; a display control unit that displays data of a plurality of time phases relating to the region on a display unit; Equipped with the display control unit causes the display unit to display a probability that the signal present in the region selected by the user is a physiological accumulation, and causes the display unit to display the third nuclear medicine data. Nuclear medicine diagnostic equipment.

2. an acquisition unit for acquiring nuclear medicine data; a division unit that divides the nuclear medicine data into at least two or more time segments and divides the data into first nuclear medicine data and second nuclear medicine data; an identifying unit that identifies a physiological accumulation region based on time changes in data values ​​included in the first nuclear medicine data and the second nuclear medicine data; an image generating unit that generates corrected third nuclear medicine data by replacing pixel values ​​of a region determined to be the physiological accumulation region with an average value of surrounding pixel values ​​based on the physiological accumulation region identified by the identifying unit; a receiving unit that receives an input of a region selection from a user; a display control unit that displays data of a plurality of time phases relating to the region on a display unit; Equipped with the display control unit, when a first region in the image displayed on the display unit is selected by a user, causes the display unit to display a screen relating to the time change of the data values ​​relating to the first region, and when a second region in the image displayed on the display unit is selected by the user, causes the display unit to display a screen relating to the time change of the data values ​​relating to the second region, and causes the display unit to display the third nuclear medicine data.

3. further comprising a reception unit that receives an input of a region selection from a user; The nuclear medicine diagnosis apparatus according to claim 1 , wherein the specifying unit specifies the physiological accumulation region included in the region when the receiving unit receives an input of the region selection from the user.

4. 3. The nuclear medicine diagnosis device according to claim 1, wherein the identification unit identifies the physiological accumulation region by inputting the first nuclear medicine data and the second nuclear medicine data into a trained model generated by learning using a group of clinical images linked to the presence or absence of physiological accumulation.

5. The nuclear medicine diagnosis apparatus according to claim 1 or 2, further comprising an image generating unit that generates fourth nuclear medicine data by performing gamma correction on the physiological accumulation region identified by the identifying unit.

6. 3. The nuclear medicine diagnosis device according to claim 1, wherein the identifying unit identifies the physiological accumulation region by comparing a decay time of the data value with a threshold value or by comparing a degree of agreement between the data value and a model waveform with a threshold value.

7. the display control unit causes the display unit to display a screen for setting an intensity of gamma correction to be performed on the physiological accumulation region identified by the identification unit; 6. The nuclear medicine diagnosis device according to claim 5, wherein the image generation unit performs the gamma correction on the physiological accumulation region identified by the identification unit based on a strength of the gamma correction set by a user via the screen, and generates the fourth nuclear medicine data.

8. Acquire nuclear medicine data, The nuclear medicine data is time-divided into at least two or more parts, and divided into first nuclear medicine data and second nuclear medicine data; identifying a physiological accumulation region based on time changes in data values ​​included in the first nuclear medicine data and the second nuclear medicine data; generating corrected third nuclear medicine data by replacing pixel values ​​of a region determined to be the physiological accumulation region with an average value of surrounding pixel values ​​based on the identified physiological accumulation region; Accepting an input from a user to select an area; Displaying data of a plurality of time phases relating to the region on a display unit, and displaying on the display unit a probability that the signal present in the region selected by the user is a physiological accumulation; displaying the third nuclear medicine data on the display unit; Data processing methods.

9. On the computer, Acquire nuclear medicine data, The nuclear medicine data is time-divided into at least two or more parts, and divided into first nuclear medicine data and second nuclear medicine data; identifying a physiological accumulation region based on time changes in data values ​​included in the first nuclear medicine data and the second nuclear medicine data; generating corrected third nuclear medicine data by replacing pixel values ​​of a region determined to be the physiological accumulation region with an average value of surrounding pixel values ​​based on the identified physiological accumulation region; Accepting an input from a user to select an area; Displaying data of a plurality of time phases relating to the region on a display unit, and displaying on the display unit a probability that the signal present in the region selected by the user is a physiological accumulation; a program for causing the display unit to display the third nuclear medicine data and for executing processing;

Images