Medical information processing apparatus, medical image diagnostic apparatus, method, and program

Abstract

To reduce a burden of interpretation.SOLUTION: A medical information processing apparatus includes an acquisition unit and an estimation unit. The acquisition unit obtains both a first image including a tumor region of a subject and a second image which is obtained by imaging the subject before the first image. The estimation unit estimates a primary lesion of the tumor region based on the first image and the second image.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] An embodiment of the present invention relates to a medical information processing apparatus, a medical image diagnostic apparatus, a method, and a program. [Background technology]

[0002] In PET (Positron Emission Tomography) examinations, doctors (radio-interpreters) interpret PET images by checking the accumulation location of RI (Radio Isotope) tracers (radioactive drugs). However, in recent years, there has been a shortage of nuclear medicine specialists, and the number of cases in which doctors are required to interpret images of the entire body of a subject has increased. In addition, when diagnosing tumors (cancer), doctors must estimate the primary focus, identify the extent of tumor metastasis, and determine the tumor stage, which increases the burden of interpreting images on doctors. For this reason, it is desirable to reduce the increasing workload of doctors in interpreting images. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-203077 [Patent Document 2] Japanese Patent Application Laid-Open No. 2016-187452 Summary of the Invention [Problem to be solved by the invention]

[0004] The problem to be solved by the present invention is to reduce the load of image interpretation. [Means for solving the problem]

[0005] According to an embodiment, a medical image processing apparatus includes an acquisition unit and an estimation unit. The acquisition unit acquires a first image including a tumorous region of a subject and a second image obtained by imaging the subject prior to the first image. The estimation unit estimates a primary focus of the tumorous region based on the first and second images. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of a medical information processing system according to the first embodiment. [Figure 2] FIG. 2 is a flowchart showing an example of the flow of processing executed by the medical image processing apparatus according to the first embodiment. [Figure 3] FIG. 3 is a diagram for explaining the processing shown in FIG. [Figure 4] FIG. 4 is a diagram illustrating an example of a method for generating and using a trained model according to a modification of the first embodiment. [Figure 5] FIG. 5 is a diagram showing an example of the overall configuration of the PET-CT apparatus according to the second embodiment. [Figure 6] FIG. 6 is a block diagram showing an example of the configuration of a console device according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0007] Hereinafter, embodiments of a medical information processing apparatus, a medical image diagnostic apparatus, a method, and a program will be described in detail with reference to the accompanying drawings.

[0008] (First embodiment) In the first embodiment, a medical information processing system 100 including a medical information processing device 30 will be described as an example. For example, as shown in Fig. 1, the medical information processing system 100 includes a PET-CT device 10, a database 20, and the medical information processing device 30. Fig. 1 is a block diagram showing an example of the configuration of the medical information processing system 100 according to the first embodiment.

[0009] 1, a PET-CT (Computed Tomography) device 10, a database 20, and a medical information processing device 30 are connected via a network 90. ​​Here, the network 90 may be configured as a closed local network within a hospital, or may be a network via the Internet. For example, the network 90 includes a LAN (Local Area Network) or a WAN (Wide Area Network).

[0010] The PET-CT device 10 is a device that collects PET images and CT images from a subject. The subject is administered a drug labeled with a positron-emitting nuclide (RI tracer (radiopharmaceutical)). The PET image is a functional image, and the CT image is a morphological image.

[0011] The database 20 is a storage device that stores various data, and is realized by computer equipment such as a server or a workstation. The database 20 may be a server of an information management system such as a Radiology Information System (RIS), a Hospital Information System (HIS), or a Picture Archiving and Communication System (PACS). For example, the database 20 includes an image storage device that stores PET images and CT images acquired by the PET-CT device 10. Although a single database 20 is shown in FIG. 1, the database 20 may be realized by a combination of multiple storage devices.

[0012] The medical information processing device 30 supports a doctor's diagnosis through processing by the processing circuitry 35. In this embodiment, the medical information processing device 30 estimates the primary focus in the region where the tumor is present (tumor region) of the subject from PET images and CT images, and estimates the stage of the primary focus. Then, the medical information processing device 30 presents the estimated primary focus and stage to the doctor. As a result, the burden of image interpretation on the doctor can be reduced.

[0013] For example, as shown in FIG. 1, the medical information processing device 30 includes a communication interface 31, an input interface 32, a display 33, a memory , and a processing circuit .

[0014] The communication interface 31 is configured by, for example, a network card such as a LAN card, a network adapter, etc. The communication interface 31 transmits and receives various information to and from devices connected via the network 90 under the control of the processing circuit 35.

[0015] The input interface 32 accepts various input operations from the user, converts the accepted input operations into electrical signals, and outputs the electrical signals to the processing circuit 35. For example, the input interface 32 may be implemented by a mouse, keyboard, trackball, switch, button, joystick, a touchpad that allows input operations by touching the operation surface, a touchscreen that integrates a display screen and a touchpad, a non-contact input circuit using an optical sensor, a voice input circuit, etc. The input interface 32 may also be configured as a tablet terminal or the like that can wirelessly communicate with the medical information processing device 30. The input interface 32 may also be a circuit that accepts input operations from the user using motion capture. For example, the input interface 32 can accept the user's body movements, gaze, etc. as input operations by processing signals acquired via a tracker and images collected about the user. The input interface 32 is not limited to those that include physical operating components such as a mouse and keyboard. For example, an example of the input interface 32 also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the medical information processing device 30 and outputs this electrical signal to the processing circuit 35.

[0016] The display 33 displays various types of information and images. For example, the display 33 displays PET images and CT images captured by the PET-CT device 10 under the control of the processing circuitry 35. Furthermore, for example, the display 33 displays a GUI (Graphical User Interface) for receiving various instructions, settings, etc. from a user via the input interface 32. For example, the display 33 is a liquid crystal display or a CRT (Cathode Ray Tube) display. The display 33 may be a desktop type, or may be configured as a tablet terminal or the like capable of wireless communication with the main body of the medical information processing device 30. The display 33 is an example of a display unit.

[0017] The medical information processing device 30 may include a projector instead of or in addition to the display 33. The projector can project onto a screen, wall, floor, etc. under the control of the processing circuitry 35. For example, the projector can project onto any plane, object, space, etc. by projection mapping. Such a projector is an example of a display unit.

[0018] The memory 34 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, a hard disk, an optical disk, etc. For example, the memory 34 stores various data (image data) such as PET images and CT images. The memory 34 also stores programs that enable circuits included in the medical information processing device 30 to realize various functions. The memory 34 may also be realized by a group of servers (cloud) connected to the medical information processing device 30 via a network 90.

[0019] The processing circuit 35 includes an acquisition function 351, an estimation function 352, and a display control function 353. The acquisition function 351 is, for example, an example of an acquisition unit. The estimation function 352 is, for example, an example of an estimation unit. The display control function 353 is, for example, an example of a display control unit.

[0020] 1, each processing function is stored in the form of a computer-executable program in a memory 34. The processing circuitry 35 is a processor that realizes the function corresponding to each program by reading and executing each program from the memory 34. In other words, the processing circuitry 35 in a state in which a program has been read has various functions corresponding to the read program.

[0021] 1, the acquisition function 351, the estimation function 352, and the display control function 353 are realized by a single processing circuit 35. However, the processing circuit 35 may be configured by combining a plurality of independent processors, and each processor may execute a program to realize the functions. Furthermore, each processing function of the processing circuit 35 may be realized by being distributed or integrated as appropriate in a single or multiple processing circuits.

[0022] The processing circuitry 35 may also realize its functions by using a processor in an external device connected via the network 90. ​​For example, the processing circuitry 35 reads and executes a program corresponding to each function from the memory 34, and realizes each function shown in Fig. 1 by using a group of servers (cloud) connected to the medical information processing device 30 via the network 90 as a computational resource.

[0023] FIG. 2 is a flowchart showing an example of the flow of processing executed by the medical information processing apparatus 30 according to the first embodiment. FIG. 3 is a diagram for explaining the processing shown in FIG. 2. As shown in FIGS. 2 and 3, the acquisition function 351 acquires a PET image 60 obtained by imaging a subject to be examined from the PET-CT apparatus 10 or the database 20 (step S101). The PET image 60 is, for example, a three-dimensional image, but may also be a two-dimensional image. In this embodiment, the PET image 60 is a functional image including a tumor region 60a of the subject. The PET image 60 is, for example, an example of a first image.

[0024] Then, the estimation function 352 uses the PET image 60 to extract a tumor region 60a included in the PET image 60 (step S102). The tumor region 60a includes multiple tumors 60b. In the example of FIG. 3, the tumor region 60a includes five tumors 60b. For example, the estimation function 352 extracts the tumor region 60a from the PET image 60 using the PET image 60 and a trained model (not shown) stored in the memory 34. The trained model is configured to output the tumor region included in the input PET image when the PET image is input. The estimation function 352 inputs the PET image 60 to the trained model and obtains the tumor region 60a output from the trained model, thereby extracting the tumor region 60a from the PET image 60. Note that the estimation function 352 may extract the tumor region 60a from the PET image 60 by performing predetermined image processing on the PET image 60 without using the trained model.

[0025] Next, the acquisition function 351 acquires one or more past PET images (time-lapse PET images) 61 obtained by imaging the subject to be examined from the PET-CT device 10 or the database 20 (step S103). For example, the multiple PET images 61 are multiple time-lapse PET images (multiple PET images arranged in time series). The PET image 61 is an image acquired before the PET image 60 and is a three-dimensional image. Note that the PET image 61 may also be a two-dimensional image. In this way, the acquisition function 351 acquires the PET image 61 obtained by imaging the subject before the PET image 60. The PET image 61 is a functional image including a tumor region 61a of the subject. The PET image 61 is, for example, an example of a second image.

[0026] The example in Fig. 3 shows a case where the acquisition function 351 acquires multiple PET images 61. In Fig. 3, the PET image 61 on the left side was captured earlier in the time series than the PET image 61 on the right side. The tumor region 61a in the PET image 61 on the right side includes four tumors 61b. The tumor region 61a in the PET image 61 on the left side includes three tumors 61b.

[0027] Then, the estimation function 352 uses the PET image 61 to determine one or more primary focus candidates 60c from among the multiple tumors 60b in the tumor region 60a of the PET image 60 (step S104). That is, the estimation function 352 determines one or more primary focus candidates 60c based on the PET images 60 and 61. For example, of the two PET images 61 shown in FIG. 3, the PET image captured at the earliest timing is the left PET image 61. Therefore, it is considered that one of the three tumors 61b included in the tumor region 61a of the left PET image 61 is the primary focus. Therefore, as shown in FIG. 3, the estimation function 352 determines three tumor regions 60b (tumor regions indicated by black circles) 60b corresponding to the three tumors 61b included in the tumor region 61a of the left PET image 61 as primary focus candidates 60c from among the multiple tumors 60b in the tumor region 60a.

[0028] If the number of primary focus candidates 60c determined in step S104 is one, the estimation function 352 estimates the primary focus candidate 60c determined in step S104 as the primary focus 60d. That is, the estimation function 352 estimates the primary focus 60d in the tumor region 60a based on the PET images 60 and 61. In this way, the estimation function 352 estimates the primary focus 60d from the PET images 60 and 61 without using a CT image 70, which will be described later. If the primary focus 60d is estimated in step S104, the processing circuitry 35 executes the processes of steps S111 and S112, which will be described later, without executing the processes of steps S105 to S110.

[0029] The acquisition function 351 also acquires a CT image 70 obtained by imaging the subject to be examined from the PET-CT device 10 or the database 20 (step S105). The CT image 70 is, for example, a three-dimensional image, but may also be a two-dimensional image. Here, the subject depicted in the PET image 60 acquired in step S101 is the same as the subject depicted in the CT image 70 acquired in step S105. The CT image 70 is a morphological image including a tumor region of the subject. The CT image 70 is, for example, an example of a third image.

[0030] The acquisition function 351 then acquires the region information 71 by generating it using the CT image 70 using known technology (step S106). The region information 71 is, for example, information indicating the range of various regions or information indicating the positions of anatomical landmarks of various regions. When the region information 71 indicates the positions of anatomical landmarks of various regions, a predetermined range including the positions of the landmarks indicated by the region information 71 is treated as the region range. Therefore, the region information 71, regardless of the information, is information that can identify the position of the region.

[0031] The acquisition function 351 also acquires metastatic site information 80 relating to the metastatic site for each primary focus (step S107). In this embodiment, the metastatic site information 80 is stored in the memory 34, and the acquisition function 351 acquires the metastatic site information 80 from the memory 34. A record is registered in the metastatic site information 80 for each primary focus. Each record in the metastatic site information 80 is associated with the primary focus and the possibility of metastasis from the primary focus to each site. In the example of FIG. 3, a single circle "◯" indicates a high possibility, and a double circle "◎" indicates an extremely high possibility. The topmost record in the metastatic site information 80 in FIG. 3 indicates that, when a lung tumor (lung cancer) is the primary focus, there is an extremely high possibility of metastasis to lymph nodes, and a high possibility of metastasis to the liver (liver), lungs, bones, brain, and adrenal glands. The same applies to the other records.

[0032] The estimation function 352 then narrows down the primary focus candidates 60c using the site information 71 and the metastatic site information 80 (step S108). An example of the processing in step S108 will be described. For example, the coordinate system of the PET image 60 is the same as the coordinate system of the CT image 70. Therefore, the coordinate system of the PET image 60 is the same as the coordinate system used to define the ranges of various sites indicated by the site information 71. Therefore, the site where the tumor 60b is located can be identified from the site information 71. Therefore, in step S108, the estimation function 352 first uses the site information 71 to identify the site where each of the multiple tumors 60b included in the tumor region 60a is located. Below, an example will be described in which the estimation function 352 identifies that, of five tumors 60b, the first tumor 60b is located in the liver, the second tumor 60b is located in the lung, the third tumor 60b is located in the bone, the fourth tumor 60b is located in the brain, and the fifth tumor 60b is located in the adrenal gland. The three primary focus candidates 60c determined in step S104 are the first tumor 60b, the second tumor 60b, and the fourth tumor 60b described above. That is, the three primary focus candidates 60c are present in the liver, lung, and brain.

[0033] Then, the estimation function 352 narrows down the primary focus candidates 60c by excluding the primary focus candidates 60c that do not match the information on the metastatic site for each primary focus indicated by the metastatic site information 80 from the three primary focus candidates 60c determined in step S104 and selecting the primary focus candidates 60c that match the information on the metastatic site for each primary focus. A specific example will be given below. Here, the first primary focus candidate 60c is the first tumor 60b present in the liver, the second primary focus candidate 60c is the second tumor 60b present in the lung, and the third primary focus candidate 60c is the fourth tumor 60b present in the brain.

[0034] The estimation function 352 references the metastatic site information 80 and determines whether the first primary focus candidate 60c and the other four tumors 60b match the information regarding the metastatic site for each primary focus indicated by the metastatic site information 80. Here, the fourth record from the top of the metastatic site information 80 indicates that if a liver tumor (liver cancer) is the primary focus, there is a high possibility that it will metastasize to the lungs, bones, brain, and adrenal glands. Therefore, the estimation function 352 determines that the first primary focus candidate 60c and the other four tumors 60b match the information regarding the metastatic site for each primary focus indicated by the metastatic site information 80.

[0035] The estimation function 352 also references the metastatic site information 80 and determines whether the second primary focus candidate 60c and the other four tumors 60b match the information regarding the metastatic site for each primary focus indicated by the metastatic site information 80. Here, as described above, the topmost record in the metastatic site information 80 indicates that if a lung tumor (lung cancer) is the primary focus, there is a high probability of metastasis to the liver (liver), bone, brain, and adrenal gland. Therefore, the estimation function 352 determines that the second primary focus candidate 60c and the other four tumors 60b match the information regarding the metastatic site for each primary focus indicated by the metastatic site information 80.

[0036] The estimation function 352 also references the metastatic site information 80 and determines whether the third primary focus candidate 60c and the other four tumors 60b match the information on the metastatic site for each primary focus indicated in the metastatic site information 80. Here, no records that specify the brain as the primary focus are registered in the metastatic site information 80. Therefore, the estimation function 352 determines that the third primary focus candidate 60c and the other four tumors 60b do not match the information on the metastatic site for each primary focus indicated in the metastatic site information 80.

[0037] The estimation function 352 then excludes the third primary focus candidate 60c determined to be a mismatch from the three primary focus candidates 60c and selects the second and third primary focus candidates 60c determined to be a match, thereby narrowing down the primary focus candidates 60c. In the example of Fig. 3, the number of primary focus candidates 60c is narrowed down to two by the processing of step S108. That is, the three primary focus candidates 60c are narrowed down to the second and third primary focus candidates 60c.

[0038] Note that if the number of primary focus candidates 60c narrowed down in step S108 is one, the estimation function 352 estimates the primary focus candidate 60c narrowed down in step S108 as a primary focus 60d. That is, the estimation function 352 narrows down the multiple primary focus candidates 60c to one primary focus candidate 60c based on metastatic site information 80 related to the metastatic site for each primary focus, and estimates the single narrowed primary focus candidate 60c as a primary focus 60d in the tumor region 60a. Furthermore, the estimation function 352 narrows down the multiple primary focus candidates 60c to one primary focus candidate 60c based on metastatic site information 80 and site information 71 related to the site of the subject obtained from the CT image 70, and estimates the single narrowed primary focus candidate 60c as a primary focus 60d in the tumor region 60a. If a primary focus 60d is estimated in step S108, the processing circuitry 35 does not perform the processes of steps S109 to S110, but instead performs the processes of steps S111 and S112, which will be described later.

[0039] Then, the estimation function 352 identifies the accumulation of the RI tracer on the CT image 70 corresponding to the candidate primary focus 60c narrowed down in step S108, and acquires the characteristics of the identified accumulation (step S109). The characteristics of the RI tracer accumulation here are, for example, the size of the RI tracer accumulation.

[0040] The estimation function 352 then identifies the primary focus 60d from among the primary focus candidates 60c narrowed down in step S108 based on the acquired RI tracer accumulation characteristics, thereby estimating the primary focus 60d (step S110). For example, the estimation function 352 identifies the primary focus candidate 60c whose RI tracer accumulation characteristics most closely resemble those of the primary focus as the primary focus 60d from among the primary focus candidates 60c narrowed down in step S108. That is, the estimation function 352 estimates the primary focus 60d in the tumor region 60a based on the PET image 60, the PET image 61, and the CT image 70. Furthermore, in step S110, the estimation function 352 estimates tumors 60b other than the primary focus 60d as metastatic focus 60e. The example of FIG. 3 shows a case in which three metastatic focus 60e are estimated.

[0041] Then, the estimation function 352 estimates the stage of the primary focus 60d based on known guidelines (stage guidelines) for classifying tumor stages (disease stages) (step S111).

[0042] Then, the display control function 353 displays the estimated primary focus 60d and the stage of the primary focus 60d on the display 33 (step S112), and ends the processing shown in Fig. 2. For example, in step S112, the display control function 353 displays the PET image 60 on the display 33, and also displays the character string "Primary focus" on the display 33 in correspondence with the primary focus 60d in the displayed PET image 60. The display control function 353 also displays the character string "Metastatic focus" on the display 33 in correspondence with the metastatic focus 60e in the displayed PET image 60. The display control function 353 also displays the stage of the estimated primary focus 60d on the display 33. This allows the medical information processing device 30 according to this embodiment to assist doctors in various diagnoses, such as estimating a primary focus and determining the stage of a tumor, and reduces the burden of image interpretation on doctors.

[0043] The above has described the first embodiment. As described above, the medical information processing apparatus 30 according to the first embodiment can reduce the load of image interpretation.

[0044] (Modification of the first embodiment) In the first embodiment described above, the medical information processing device 30 executes steps S101 to S110 of the process shown in FIG. 2 to estimate the primary focus 60d in the tumorous region 60a. However, the medical information processing device 30 may also use a trained model to estimate the primary focus 60d in the tumorous region 60a. Therefore, such a modification will be described as a modification of the first embodiment. Below, a description of the same configuration as the first embodiment will be omitted, and differences from the first embodiment will be mainly described.

[0045] FIG. 4 is a diagram illustrating an example of a method for generating and using a trained model 81 according to a modification of the first embodiment. The trained model 81 is a trained machine learning model obtained by having a machine learning model perform machine learning based on input data and teacher data in accordance with a model learning program. The machine learning model is a model such as a convolutional neural network (CNN). The trained model 81 is generated by an external learning device or the medical information processing device 30. Below, a case where the trained model 81 is generated by a learning device will be described, but the trained model 81 may also be generated by the medical information processing device 30 using a method similar to the method described below.

[0046] The learning device generates a trained model 81 by performing learning (supervised learning) based on input data and training data. Here, the input data is, for example, PET images 82 obtained by imaging each of a plurality of subjects. The PET image 82 is a functional image including a tumor region 82a of the subject. The tumor region 82a is an area including one or more tumors 82b. The training data is a PET image 83 obtained by adding information about a primary focus, information about metastatic focus, and information about the order of tumor metastasis to the PET image 82. In the example of FIG. 4, in the PET image 83, information indicating that one tumor 82b is a primary focus is added to one tumor 82b. In addition, in the PET image 83, information indicating that two tumors 82b are metastatic focus is added to the two tumors 82b. In addition, information indicating a location xxx where a primary focus is located is added to the PET image 83. The trained model 81 is configured to output data (output data) corresponding to the training data when data corresponding to the input data is input during inference.

[0047] A case will be described in which the machine learning model is a CNN. In this case, in the learning device, input data is input to the CNN, which is the machine learning model. The learning device applies the CNN to the input data. As a result, output data is generated in the CNN, and the generated output data is output from the CNN. In the learning device, the output data is input to an evaluation function. In addition, in the learning device, training data is also input to the evaluation function. The learning device uses the evaluation function to evaluate the output data generated by the CNN based on the input data and the training data. For example, the evaluation function compares the generated output data with the training data and corrects the CNN coefficients (network parameters such as weights and biases) using an error backpropagation method. The evaluation by the evaluation function is fed back to the CNN. The learning device repeats this series of supervised learning based on the input data and the training data until, for example, the error between the output data and the training data becomes equal to or less than a predetermined threshold. The learning device can output the trained machine learning model as a trained model 81. In this modification, the trained model 81 generated by the learning device in this manner is stored in memory 34.

[0048] A case will be described in which the medical information processing device 30 estimates a primary focus 60d in a tumor region 60a using a trained model 81. An example of processing executed by the medical information processing device 30 when performing inference using the trained model 81 will be described below. For example, the estimation function 352 inputs a PET image 60 to the trained model 81. Then, the estimation function 352 acquires a PET image (output data) 62 output from the trained model 81. This PET image 62 is an image in which information on the primary focus, information on metastatic focus, and information on the order of tumor metastasis are added to the PET image 60. In the example of FIG. 4, in the PET image 62, information indicating that one tumor 60b is a primary focus is added to one tumor 60b. Furthermore, in the PET image 62, information indicating that these tumors 60b are metastatic focus is added to three tumors 60b. Furthermore, information indicating a location xxx where the primary focus is located is added to the PET image 62.

[0049] The estimation function 352 estimates the primary focus 60d in the tumor region 60a by acquiring the above-described PET image 62. Then, the processing circuitry 35 executes the processes of steps S111 and S112, similarly to the first embodiment.

[0050] The medical information processing device 30 according to the modified example has been described above. As described above, the estimation function 352 estimates the primary focus in the tumor region 60a by inputting the PET image 60 into the trained model 81 obtained by associating and training a PET image 82 including a tumor region 82a of a subject with a PET image 83 obtained by adding information on the primary focus, information on metastatic focus, and information on the order of tumor metastasis to the PET image 82, and acquiring the PET image 62 output from the trained model 81. The PET image 82 is, for example, an example of a third image. The PET image 83 is, for example, an example of a fourth image. The PET image 62 is, for example, an example of a fifth image.

[0051] The above has described a modified example of the first embodiment. According to the medical information processing device 30 according to the modified example, it is possible to reduce the load of image interpretation, similar to the medical information processing device 30 according to the first embodiment.

[0052] (Second embodiment) In the first embodiment, a case has been described in which the medical information processing device 30 executes the processing shown in Fig. 2. However, the PET-CT device 10, which is a medical image diagnostic device, may execute processing similar to the processing shown in Fig. 2 to reduce the burden of image interpretation on a doctor. Therefore, such an embodiment will be described as the second embodiment. In the description of the second embodiment, configurations different from the first embodiment will be mainly described, and a description of configurations similar to the first embodiment may be omitted.

[0053] Fig. 5 is a diagram showing an example of the overall configuration of a PET-CT apparatus 10 according to the second embodiment. As shown in Fig. 5, the PET-CT apparatus 10 includes a PET gantry device 1, a CT gantry device 2, a bed 3, and a console device 4. An RI tracer is administered to a subject P. The PET-CT apparatus 10 is an example of a medical image diagnostic apparatus.

[0054] The PET gantry device 1 is a device that detects pairs of gamma rays (pair annihilation gamma rays) emitted from living tissue that has taken in positron-emitting nuclides, and generates counting information from the gamma ray detection signals, thereby collecting counting information. The counting information is stored in a memory 41 (described later) of the console device 4.

[0055] The CT gantry device 2 is a device that generates X-ray projection data that is the basis of a CT image by detecting X-rays that have passed through the subject P. The CT gantry device 2 can also generate X-ray projection data that is the basis of a two-dimensional or three-dimensional scanogram.

[0056] The bed 3 is a bed on which the subject P rests, and includes a tabletop 36, a support frame 37, and a bed device 38. The bed 3 sequentially moves the subject P to the imaging ports of the CT gantry device 2 and the PET gantry device 1 based on instructions from the operator of the PET-CT device 10 received via the console device 4. That is, the PET-CT device 10 controls the bed 3 to first capture CT images and then capture PET images. Note that while FIG. 5 shows an example in which the CT gantry device 2 is disposed on the bed 3 side, the embodiment is not limited to this, and the PET gantry device 1 may also be disposed on the bed 3 side.

[0057] The bed 3 uses a driving mechanism (not shown) to move the top board 36 and the support frame 37 in the central axis direction of the detector field of view of the CT gantry device 2 and the PET gantry device 1. In other words, the bed 3 moves the top board 36 and the support frame 37 in a direction along the longitudinal direction of the top board 36 and the support frame 37.

[0058] The console device 4 is a device that receives instructions from an operator and controls processing by the PET-CT device 10. FIG. 6 is a diagram showing an example of the configuration of the console device 4 according to the second embodiment. As shown in FIG. 6, the console device 4 has a memory 41, a display 42, an input interface 43, and a processing circuit 44.

[0059] The display 42 displays various images and information under the control of a display control function 444, which will be described later. For example, the display 42 has the same configuration as the display 33 described above.

[0060] The input interface 43 has the same configuration as the input interface 32 described above, and accepts instructions and operations from the user.

[0061] The processing circuitry 44 executes various processes. For example, as shown in FIG. 6, the processing circuitry 44 includes a control function 441, an acquisition function 442, an estimation function 443, and a display control function 444. Here, for example, the processing functions executed by the acquisition function 442, the estimation function 443, and the display control function 444, which are components of the processing circuitry 44 shown in FIG. 6, are recorded in the memory 41 in the form of programs executable by a computer. The processing circuitry 44 is a processor that realizes the functions corresponding to each program by reading and executing each program from the memory 41. In other words, the processing circuitry 44 in a state in which each program has been read has the functions shown in the processing circuitry 44 in FIG. 6.

[0062] The processing circuitry 44 further has a PET image generation function for generating a PET image using counting information collected by the PET gantry device 1, and a CT image generation function for generating a CT image using X-ray projection data generated by the CT gantry device 2. The PET image generation function stores the generated PET image in the memory 41. The CT image generation function also stores the generated CT image in the memory 41.

[0063] The term "processor" refers to a circuit such as a central processing unit (CPU), a graphics processing unit (GPU), 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 function by reading and executing a program stored in the memory 41. Instead of storing the program in the memory 41, the processor may be configured so that the program is directly embedded in its circuit. In this case, the processor realizes its function by reading and executing the program embedded in the circuit. Each processor in this embodiment is not limited to being configured as a single circuit, but may also be configured as a single processor by combining multiple independent circuits.

[0064] The control function 441 controls the operation of the PET-CT device 10. For example, the control function 441 receives instructions from a user via the input interface 43, and controls the PET gantry device 1, the CT gantry device 2, and the bed 3 in accordance with the received instructions to perform various processes such as scanogram collection, scanning (actual imaging), image reconstruction, image generation, and image display. The control function 441 is, for example, an example of a control unit.

[0065] The acquisition function 442 has the same functions as the acquisition function 351. For example, the acquisition function 442 acquires each of the PET image 60, the PET image 61, and the CT image 70 stored in the memory 41, and executes various processes using each of the acquired PET image 60, the PET image 61, and the CT image 70. The estimation function 443 has the same functions as the estimation function 352. The display control function 444 has the same functions as the display control function 353. However, the display control function 444 displays various images and various information on the display 42 instead of the display 33.

[0066] The above has described the second embodiment. The PET-CT apparatus 10 according to the second embodiment can reduce the load of image interpretation, similar to the medical information processing apparatus 30 according to the first embodiment.

[0067] In the above-described embodiments, the case where the PET-CT device 10 is used has been described. However, a PET-MR (Magnetic Resonance) device may be used instead of the PET-CT device 10. In this case, an MR image, which is a morphological image generated by the PET-MR device, is used instead of a CT image.

[0068] The program executed by the processor may be provided by being pre-installed in a ROM (Read Only Memory), a storage unit, etc. The program may be provided by being stored in a computer-readable storage medium such as a CD (Compact Disk)-ROM, a FD (Flexible Disk), a CD-R (Recordable), or a DVD (Digital Versatile Disk) in a format that can be installed or executed by these devices. The program may also be provided or distributed by being stored on a computer connected to a network such as the Internet and downloaded via the network.

[0069] Furthermore, the components of each device illustrated in the above-described embodiments are merely functional concepts and do not necessarily have to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to that illustrated, and all or part of the devices can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

[0070] According to at least one of the embodiments described above, it is possible to reduce the load of image interpretation.

[0071] Although several embodiments of the present invention 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, and modifications 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 described in the claims and their equivalents. [Explanation of symbols]

[0072] 30 Medical information processing device 351 Acquisition Function 352 Estimation Function 353 Display Control Function

Claims

1. an acquisition unit that acquires a first image including a tumorous region of a subject and a second image obtained by imaging the subject at a time prior to the first image; an estimation unit that estimates a primary focus of the tumor region based on the first image and the second image; A medical information processing device comprising:

2. 2. The medical information processing device according to claim 1, wherein the estimation unit determines a plurality of primary focus candidates based on the first image and the second image, narrows down the plurality of primary focus candidates to one primary focus candidate based on metastatic site information regarding a metastatic site for each primary focus, and estimates the one narrowed down primary focus candidate as the primary focus in the tumor region.

3. 2. The medical information processing device according to claim 1, wherein the estimation unit estimates the primary focus of the tumor region by inputting the first image into a trained model obtained by associating a third image including the tumor region of the subject with a fourth image obtained by adding information on the primary focus, information on metastatic focus, and information on the order of tumor metastasis to the third image and training the trained model, and acquiring a fifth image output from the trained model.

4. the first image and the second image are functional images including the tumorous region of the subject; the acquisition unit acquires a third image that is a morphological image including the tumorous region of the subject; The medical image processing device according to claim 1 , wherein the estimation unit estimates the primary focus of the tumor region based on the first image, the second image, and the third image.

5. the acquisition unit acquires a third image that is a morphological image including the tumorous region of the subject; 2. The medical information processing device according to claim 1, wherein the estimation unit determines a plurality of primary focus candidates based on the first image and the second image, narrows down the plurality of primary focus candidates to one primary focus candidate based on metastatic site information on a metastatic site for each primary focus and site information on a site of the subject obtained from the third image, and estimates the one narrowed down primary focus candidate as the primary focus in the tumor region.

6. The medical information processing device according to claim 1 , wherein the estimation unit estimates the stage of the estimated primary focus based on a guideline for classifying tumor stages.

7. an acquisition unit that acquires a first image including a tumorous region of a subject and a second image obtained by imaging the subject at a time prior to the first image; an estimation unit that estimates a primary focus of the tumor region based on the first image and the second image; A medical image diagnostic device comprising:

8. acquiring a first image including a tumorous region of a subject and a second image obtained by imaging the subject at a time prior to the first image; estimating a location of origin of the tumor region based on the first image and the second image.

9. On the computer, acquiring a first image including a tumorous region of a subject and a second image obtained by imaging the subject at a time prior to the first image; A program for executing a process for estimating a primary focus of the tumor region based on the first image and the second image.

Images