JP6948966B2 - Diagnostic support system, diagnostic support method, and program - Google Patents

Description

The present disclosure relates to diagnostic support systems, diagnostic support methods, and programs.

Conventionally, in order to realize diagnostic support for multiple organs and multiple diseases, a common platform having a mechanism for sharing and using a diagnostic support algorithm has been proposed (see Non-Patent Document 1).

Yukitaka Nimura, Daisuke Deguchi, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga, "PLUTO: Common Platform for Medical Imaging Diagnosis Support", MEDICAL IMAGING TECHNOLOGY Vol.26 No.3, P.187-191, May 2008

However, although Non-Patent Document 1 describes that it provides a common platform for realizing diagnostic support for multiple organs and multiple diseases, observation of an observation-required area for diagnosis is performed. There is no mention of how to assign a medical image to a person.

The present disclosure has been made in view of the above circumstances, and an object of the present disclosure is to provide a diagnostic support system, a diagnostic support method, and a program capable of appropriately diagnosing a disease from medical images.

In order to achieve the above object, the diagnostic support system of the first aspect of the present disclosure has an acquisition unit for acquiring a medical image and an extraction for extracting an organ region in which an organ is drawn from the medical image acquired by the acquisition unit. A unit, a derivation unit that derives the organ information of the organ region extracted by the extraction unit, a detection unit that detects an observation-required region based on the organ information derived by the derivation unit, and a detection unit. When multiple observation areas are detected, when one observer makes an observation, refer to the information about one observer making an observation for each combination of a plurality of observation areas, and make a plurality of important points. assign the observation area to one observer, a determination unit for determining the assignment of a plurality of main observation area should be assigned to a plurality of observers, if the determination in determination section assigns to one of the observers, one person When a plurality of areas requiring observation are assigned to one observer and the judgment of the judgment unit is assigned to a plurality of observers based on the information about the observer making an observation, each of the plurality of observers and a plurality of observers are assigned. It includes information indicating the correspondence with each of the observation-required areas, and an allocation unit that allocates a plurality of observation-requiring areas to each of the plurality of observers based on the judgment result of the judgment unit.

The diagnostic support system of the second aspect is the diagnostic support system of the first aspect, in which the allocation unit is an expert for each of a plurality of types of organs, an expert for each type of disease, and an expert for each level of disease. A plurality of observation-required areas are assigned to each of the plurality of observers who are any of the above.

The diagnostic support system of the third aspect is the diagnostic support system of the first aspect or the second aspect , and the detection unit is the first organ region extracted from the first medical image acquired by the acquisition unit. Based on the derived index value based on the derived first organ information and the second organ information derived for the second organ region extracted from the second medical image acquired by the acquisition unit. Detect the area requiring observation.

In the diagnostic support system of the fourth aspect, in the diagnostic support system of the third aspect, the second medical image is the same image as the first medical image, and includes a plurality of organ regions in the image.

In the diagnostic support system of the fifth aspect, in the diagnostic support system of the third aspect or the fourth aspect, the derivation unit derives the first organ information from the organ region extracted from at least the first medical image. ..

The diagnostic support system of the sixth aspect is the diagnostic support system of any one of the third to fifth aspects, after the extraction unit extracts the organ region of the entire organ existing in the medical image. A part of the extracted organ region is further extracted, the derivation unit derives some organ information from a part of the region, and the detection unit is the first organ region extracted from the first medical image. In the first partial organ information derived for a part of the region and the second partial organ information derived for a part of the second organ region extracted from the second medical image. Based on this, the index value is derived.

The diagnostic support system of the seventh aspect is the same organ region as the first organ region and the second organ region in the diagnostic support system of the sixth aspect.

The diagnostic support system of the eighth aspect is the diagnostic support system of any one of the third to seventh aspects, and the extraction unit is present in the first medical image and the first medical image. An organ region is extracted from a medical image including an organ and a medical image other than the first medical image.

In the diagnostic support system of the ninth aspect, in the diagnostic support system of the eighth aspect, the first medical image and the medical images other than the first medical image are different images in the same examination.

The diagnostic support system of the tenth aspect is a medical image obtained by taking a medical image other than the first medical image in the diagnostic support system of the eighth aspect in the past than the first medical image. ..

In the diagnostic support system of the eleventh aspect, in the diagnostic support system of the eighth aspect, the first medical image and the medical images other than the first medical image are medical images obtained by imaging by different imaging methods. be.

The diagnostic support system of the twelfth aspect is the diagnostic support system of any one of the third to eleventh aspects, in which the index value is information representing the degree of disease progression and the area to be evaluated for the disease. Includes at least one.

Diagnosis support system of the thirteenth aspect, in the diagnosis support system according to any one aspect of the twelfth embodiment of the first aspect, the organ information, the size of the organ region, the signal value of each pixel in the image of the organ region, And at least one of the values calculated using the signal values of each pixel.

The diagnostic support system according to the fourteenth aspect is the diagnostic support system according to any one of the first to thirteenth aspects. , Notify information about assignments.

The diagnostic support system according to the fifteenth aspect is the diagnostic support system according to any one of the third to thirteenth aspects. Notify the pre-determined contacts of the observer who has been assigned the assignment with information about the assignment.

The diagnostic support system according to the sixteenth aspect is the diagnostic support system according to any one of the first to fifteenth aspects, wherein the observation-required area allocated by each of the plurality of observers assigned by the allocation unit. A reception unit that receives an instruction to perform observation, and a display control unit that controls the display unit to display an image indicating an observation area assigned to the observer who has given the instruction when the reception unit receives the instruction. Was further prepared.
In the diagnosis support system of the seventeenth aspect, in the diagnosis support system of the sixteenth aspect, the display control unit controls to display a medical image in a state where the observation required area is emphasized as an image indicating the observation required area. ..

On the other hand, in order to achieve the above object, the diagnostic support method of the eighteenth aspect acquires a medical image, extracts an organ region in which an organ is drawn from the acquired medical image, and an organ in the extracted organ region. Information is derived, and based on the derived organ information, observation-requiring areas are detected. When multiple observation-requiring areas are detected, when one observer observes multiple observation-requiring areas, Refer to a predetermined information about observation by one observer for each combination, and assign a plurality of observation-requiring areas to one observer, a plurality of observers, or a division of a plurality of observation- requiring areas . Ri is determined for abutting, to assign to one of the observer, based on the information on the one of the observer to observe, it allocates a plurality of main viewing area to one observer, and assigned to a plurality of observers In the case, the process is diagnosed by allocating the plurality of observation-requiring areas to each of the plurality of observers based on the information indicating the correspondence between each of the plurality of observers and each of the plurality of observation-requiring areas and the judgment result. This is a diagnostic support method executed by the support system.

Further, in order to achieve the above object, the program of the nineteenth aspect acquires a medical image, extracts an organ region in which an organ is drawn from the acquired medical image, and obtains organ information of the extracted organ region. Derived, based on the derived organ information, the area requiring observation is detected, and when multiple areas requiring observation are detected, for each combination of multiple areas requiring observation for one observer observing advance one observer defined refers to the information regarding to observe, assign a plurality of main viewing area to one observer, assigns a plurality of main observation area should be assigned to a plurality of observers in determination for, if assigned to one of the observer, based on the information on the one of the observer to observe, allocates a plurality of main viewing area to one observer, and when assigning the plurality of observers , Assigns a plurality of observation-requiring areas to each of the plurality of observers based on the information indicating the correspondence between each of the plurality of observers and each of the plurality of observation-requiring areas, and the judgment result, and executes the process on the computer. It is a program to make it.

According to the present disclosure, a disease can be evaluated from a combination of a plurality of organ information.

It is a block diagram which shows an example of the structure of the diagnosis support system of embodiment. It is a block diagram which shows an example of the hardware configuration of the diagnostic support apparatus of embodiment. It is a figure which shows an example of the allocation table of an embodiment. It is a block diagram which shows an example of the functional structure of the diagnostic support apparatus of embodiment. It is a figure which shows an example of the organ region extracted from the medical image of an embodiment. It is a flowchart which shows an example of the diagnosis support processing of embodiment. It is a figure which shows an example of the region of the spine extracted from the medical image of an embodiment. It is a figure which shows an example of the region of the psoas major muscle extracted from the medical image of an embodiment. It is a figure which shows an example of the index value display screen of an embodiment.

Hereinafter, examples of embodiments for carrying out the technique of the present disclosure will be described in detail with reference to the drawings.

First, the configuration of the diagnostic support system 10 of the present embodiment will be described with reference to FIG. As shown in FIG. 1, the diagnostic support system 10 includes an image management device 12 and a diagnostic support device 14. The image management device 12 and the diagnosis support device 14 are each connected to the network N, and communication via the network N is possible. The image management device 12 stores medical image data indicating a medical image obtained by imaging with an imaging device that captures a medical image such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging). An example of the image management device 12 is a PACS (Picture Archiving and Communication System). The diagnosis support device 14 supports diagnosis by using the medical image data stored in the image management device 12. Examples of the diagnostic support device 14 include information processing devices such as personal computers and server computers.

Next, the hardware configuration of the diagnostic support device 14 of the present embodiment will be described with reference to FIG. As shown in FIG. 2, the diagnostic support device 14 includes a CPU (Central Processing Unit) 20, a memory 21 as a temporary storage area, and a non-volatile storage unit 22. Further, the diagnostic support device 14 includes a display unit 23 such as a liquid crystal display, an input unit 24 such as a keyboard and a mouse, and a network I / F (InterFace) 25 connected to the network N. The CPU 20, the memory 21, the storage unit 22, the display unit 23, the input unit 24, and the network I / F 25 are connected to the bus 26.

The storage unit 22 is realized by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, or the like. The diagnosis support program 30 is stored in the storage unit 22 as a storage medium. The CPU 20 reads the diagnostic support program 30 from the storage unit 22, expands it into the memory 21, and executes the expanded diagnostic support program 30.

Further, the allocation table 32 is stored in the storage unit 22. FIG. 3 shows an example of the allocation table 32. As shown in FIG. 3, the allocation table 32 of the present embodiment provides information in which each of a plurality of types of organs, a doctor in charge of observing the organs, and contact information of the doctor in charge of observation are associated with each other. Is. The doctor in charge of observing an organ may be, for example, a specialist in the organ or a specialist in a disease related to the organ, and an appropriate person for observing may be determined in advance. .. The contact information is not particularly limited as long as it can contact the doctor in charge of observation, and examples thereof include a telephone number of a mobile phone and the like, and an e-mail address. The physician of this embodiment is an example of an observer of the present disclosure. Further, the allocation table 32 of the present embodiment is an example of information representing the correspondence relationship of the present disclosure.

Next, the functional configuration of the diagnostic support device 14 of the present embodiment will be described with reference to FIG. As shown in FIG. 4, the diagnosis support device 14 includes an acquisition unit 40, an extraction unit 42, a derivation unit 44, a detection unit 46, a judgment unit 48, an allocation unit 50, a reception unit 52, and a display control unit 54. When the CPU 20 executes the diagnosis support program 30, it functions as an acquisition unit 40, an extraction unit 42, a derivation unit 44, a detection unit 46, a determination unit 48, an allocation unit 50, a reception unit 52, and a display control unit 54.

The acquisition unit 40 acquires the medical image data stored in the image management device 12 from the image management device 12 via the network N. In the present embodiment, the acquisition unit 40 acquires a plurality of medical image data indicating each of a plurality of medical images in the same examination, such as a plurality of medical images obtained by one CT imaging.

The extraction unit 42 extracts an organ region in which an organ is drawn from a plurality of medical images indicated by a plurality of medical image data acquired by the acquisition unit 40. The extraction unit 42 may extract a plurality of organ regions from each of a plurality of different medical images.

For example, AI (Artificial Intelligence) technology can be applied to the extraction process of the organ region by the extraction unit 42. Specifically, for example, a deep neural network is created by inputting medical image data and outputting the extracted organ region. Next, the trained model obtained by training the created deep neural network using the medical image data and the teacher data including the organ region in the medical image indicated by the medical image data is stored in the storage unit 22 in advance. I will do it. The extraction unit 42 inputs a plurality of medical image data acquired by the acquisition unit 40 into the trained model, acquires the organ region output from the trained model, and extracts the organ region from the medical image. FIG. 5 shows an example of the organ region extracted by the extraction unit 42. The extraction unit 42 may extract a region input by the user via the input unit 24 as an organ region.

The derivation unit 44 derives organ information obtained from an image of each organ region for a plurality of organ regions extracted by the extraction unit 42. Examples of organ information include the size of the organ region such as area and volume, and the signal value (for example, pixel value) of each pixel of the image of the organ region. Further, examples of the organ information include values calculated from the signal values of each pixel of the image of the organ region (for example, maximum value, minimum value, average value, variance, standard deviation, etc.).

For example, AI technology can be applied to the process of deriving the organ information by the deriving unit 44. Specifically, for example, a deep neural network is created by inputting image data showing an image of an organ region and outputting organ information. Next, a trained model obtained by training the created deep neural network using image data showing an image of an organ region and teacher data including organ information corresponding to the image data is stored in the storage unit 22 in advance. Remember. The derivation unit 44 was extracted by the extraction unit 42 by inputting image data showing an image of the organ region extracted by the extraction unit 42 into the trained model and acquiring the organ information output from the trained model. Derivation of organ information in the organ region.

The detection unit 46 detects an observation-requiring region that needs to be observed by a doctor from a medical image based on each organ information derived from each of the plurality of organ regions by the derivation unit 44. In the present embodiment, as an example of the method in which the detection unit 46 detects the observation-required region, the index value is derived based on each organ information derived for each of the plurality of organ regions by the out-licensing unit 44, and the derived index value is used. Based on this, the area requiring observation is detected from the organ area. In this embodiment, as an example of the index value used for deriving the observation-required region, the index value related to the evaluation of the disease or the like is used. The number of organ information may be two or three or more.

For example, AI technology can be applied to the index value derivation process by the detection unit 46. Specifically, for example, a deep neural network is created in which information on a plurality of organs is input and index values related to disease evaluation are output. Next, a trained model obtained by training a created deep neural network using teacher data including a plurality of organ information and index values related to evaluation of a disease corresponding to the organ information is stored in the storage unit 22 in advance. Remember. The detection unit 46 inputs the organ information derived by the derivation unit 44 for a plurality of organ regions into the trained model, and acquires the index value related to the disease evaluation output from the trained model, thereby relating to the disease evaluation. Derived the index value. The detection unit 46 may derive an index value related to the evaluation of the disease according to a predetermined rule instead of using the AI technique.

When the detection unit 46 detects a plurality of observation-requiring areas, the determination unit 48 determines the allocation of the plurality of observation-requiring areas to a plurality of doctors.

Based on the determination result of the determination unit 48, the allocation unit 50 allocates a doctor who observes each observation-requiring area to each of the plurality of observation-requiring areas. Specifically, the allocation unit 50 refers to the allocation table 32 and allocates a doctor (specialist) specializing in the organ region to the organ region corresponding to the observation-required region.

In addition, the allocation unit 50 of the present embodiment notifies the contact associated with the assigned doctor of information indicating that the observation of the observation-required area has been assigned. Specifically, the allocation unit 50 refers to the allocation table 32, acquires the contact associated with the doctor who has allocated the observation area, and supplies the acquired contact in advance via the network I / F25. Give the prescribed notification. The specific content of the notification to be performed here is not particularly limited, and may be, for example, only information indicating that the observation required area has been allocated, information regarding the index value derived by the detection unit 46, or the like. Information that accompanies the observation of the area requiring observation may also be included.

The reception unit 52 receives an instruction (hereinafter, referred to as “observation execution instruction”) to observe the observation-requiring area by the doctor assigned the observation-requiring area. The reception unit 52 may receive the observation execution instruction via the input unit 24, or may receive the observation execution instruction from another terminal device or the like used by the doctor via the network I / F25. May be good.

When the reception unit 52 receives the observation execution instruction, the display control unit 54 indicates the observation required area assigned to the doctor who has given the observation execution instruction to the display unit of the device to which the observation execution instruction has been given by the doctor. Controls the display of images. Specifically, when the reception unit 52 receives the observation execution instruction via the input unit 24, the display control unit 54 controls the display unit 23 to display an image representing the observation required area. The image representing the observation-requiring area is, for example, a medical image to be extracted from the observation-requiring area, and the display control unit 54 of the present embodiment marks the detected observation-requiring area on the medical image as an example. It is displayed on the display unit in a state of being emphasized. Further, the reception unit 52 controls to display the index value derived by the detection unit 46 on the display unit together with the observation required area.

Next, the operation of the diagnostic support device 14 of the present embodiment will be described with reference to FIG. When the CPU 20 executes the diagnosis support program 30, the diagnosis support process shown in FIG. 6 is executed. Further, the diagnosis support process shown in FIG. 6 is executed when, for example, the user inputs an execution instruction of the diagnosis support program 30 via the input unit 24.

In step S10 of FIG. 6, as described above, the acquisition unit 40 acquires the medical image data stored in the image management device 12 from the image management device 12 via the network N. In the next step S12, the extraction unit 42 extracts a plurality of organ regions in which the organ is drawn from the plurality of medical images indicated by the plurality of medical image data acquired by the process of step S10.

In the next step S14, as described above, the derivation unit 44 derives the organ information obtained from the image of each organ region for the plurality of organ regions extracted by the process of step S12.

In the next step S16, as described above, the detection unit 46 derives an index value for detecting the observation-required region based on the plurality of organ information derived for each of the plurality of organ regions by the process of step S14. do.

In the next step S18, as described above, the detection unit 46 detects the observation-required region from the medical image based on the index value derived by the process of step S16.

In the next step S20, as described above, when a plurality of observation-requiring areas are detected by the process of step S18, the determination unit 48 determines the allocation of the plurality of observation-requiring areas to the plurality of observers. , It is determined whether or not to assign to each of a plurality of doctors for each observation area. For example, even when a plurality of observation-requiring regions are detected, it may be preferable for one doctor to perform observation, for example, when the fields specializing in the organ region corresponding to the observation-requiring region are close to each other. In the diagnostic support device 14 of the present embodiment, even when a plurality of observation-requiring regions are detected in this way, when it is preferable for one doctor to perform observation, each combination of the plurality of observation-requiring regions is performed in advance. The information about the observation by one doctor is stored in the storage unit 22 in advance (not shown).

When allocating to each of a plurality of doctors for each observation area, the determination in step S20 becomes an affirmative determination, and the process proceeds to step S22.

In step S22, as described above, the allocation unit 50 refers to the allocation table 32 and allocates a doctor who observes each observation-requiring area to the plurality of observation-requiring areas derived by the process of step S18.

In the next step S24, as described above, the allocation unit 50 determines whether or not to notify the doctor assigned by the process of step S22. In the present embodiment, as an example, when the index value derived by the process of step S16 satisfies a predetermined condition, the assigned doctor is notified of the information indicating that the observation of the observation-required area has been assigned. do. In this embodiment, as predetermined conditions, an index value that can be regarded as having a serious degree of illness and an index value that can be regarded as having a high degree of urgency of illness are adopted. The numerical value can be set as appropriate according to the disease or the like. In addition, the present invention is not limited to this embodiment, and the allocation unit 50 may determine whether or not to notify by referring to information other than the index value. For example, if the patient information associated with the patient or the like that is the subject of the medical image acquired in step S10 can be acquired, the allocation unit 50 may determine whether or not to perform the notification based on the patient information. good. As a specific example, when the information indicating that the patient is in an emergency is associated with the information, the allocation unit 50 determines that the notification is to be performed.

If no notification is given, the determination in step S24 becomes a negative determination, and the process proceeds to step S28. On the other hand, when notifying, the determination in step S24 becomes an affirmative determination, and the process proceeds to step S26.

In step S26, as described above, the allocation unit 50 refers to the allocation table 32 and allocates the observation of the observation required area to the contact associated with the doctor assigned by the process of step S22. The information representing the above is notified, and the process proceeds to step S28.

On the other hand, if the observation area is not assigned to each of the plurality of doctors, the determination in step S20 becomes a negative determination, and the process proceeds to step S28. In the present embodiment, even when there is one observation-required region detected by the process of step S18, the determination of step S20 is a negative determination, and the process proceeds to step S28.

In step S28, the display control unit 54 determines whether or not the reception unit 52 has received the observation execution instruction, as described above. The determination in step S28 is a negative determination until the reception unit 52 receives the observation execution instruction. On the other hand, when the reception unit 52 receives the observation execution instruction, the determination in step S28 becomes an affirmative determination, and the process proceeds to step S30.

In step S30, as described above, the display control unit 54 displays an image representing the observation required area assigned to the doctor who has given the observation execution instruction on the display unit of the device for which the observation execution instruction has been given by the doctor. Control to make it. When the process of step S30 is completed, the diagnosis support process is completed. By executing the process of this step S30, the doctor assigned the observation-requiring area interprets the image representing the observation-requiring area displayed on the display unit and observes the observation-requiring area.

Next, a specific operation example of the diagnosis support device 14 will be described.

For example, when observing fatty liver (when the disease is fatty liver), the region requiring observation is the liver region, and an index value related to the evaluation of fatty liver is used as an index value. For example, when observing lung cancer (when the disease is lung cancer), the areas to be observed are the lung area, the lymph node area, and the lung and other organ areas other than the lymph node, and the evaluation of lung cancer is used as an index value. The evaluation value for is used. Further, for example, when observing sarcopenia (when the disease is sarcopenia), the areas requiring observation are the spinal region and the psoas major muscle region, and the index value related to the index value related to the evaluation of sarcopenia is used as the index value.

In step S12, the extraction unit 42 extracts the spleen region and the liver region from the plurality of medical images. In addition, the extraction unit 42 extracts the lung region, the lymph node region, and the region of other organs other than the lung and the lymph node from the plurality of medical images. Further, the extraction unit 42 extracts a region of the spine and a region of the psoas major muscle from a plurality of medical images. An example of the spinal region extracted by the extraction unit 42 is shown in FIG. 7, and an example of the psoas major muscle region is shown in FIG.

In step S14, the derivation unit 44 derives an average value of pixel values (for example, CT values) in the spleen region as organ information in the spleen region, and also derives an average value of pixel values (for example, CT values) in the spleen region as organ information in the liver region. The pixel value of each pixel in is derived. In addition, the derivation unit 44 derives the size of the tumor and the presence or absence of infiltration in the lung region as organ information in the lung region. In addition, the derivation unit 44 derives the presence or absence of lymph node metastasis as organ information in the lymph node region. In addition, the derivation unit 44 derives the presence or absence of a tumor (that is, distant metastasis) in the other organ as organ information in the region of the other organ. Further, the derivation unit 44 derives the positions of the third lumbar vertebra to the fourth lumbar vertebra as the organ information of the spinal region, and obtains the cross-sectional area of each of the plurality of cross sections of the psoas major muscle as the organ information of the psoas major muscle region. Derived.

In step S16, the detection unit 46 sets the pixel value of each pixel in the liver region to a predetermined value (for example, 10HU (Hounsfield Unit)) as an index value related to the evaluation of fatty liver, rather than the average value of the pixel values in the spleen region. )) And more, and the information representing the region where the pixel value is equal to or less than the threshold value (for example, 40 HU) is derived. The information representing this region in this operation example is an example of the information representing the region to be evaluated for the disease of the present disclosure. In this case, in step S20, the detection unit 46 detects the region from which the information representing the region, which is the index value, has been derived as the observation required region. If the information representing the above region is not derived, it indicates that the region requiring observation regarding fatty liver was not detected.

Further, in step S16, the detection unit 46 evaluates lung cancer based on the size and invasion of the tumor in the lung region derived by the out-licensing unit 44, the presence / absence of lymph node metastasis, and the presence / absence of distant metastasis. As an index value for, the stage as an example of the degree of progression of lung cancer is derived. As a method used for deriving the stage of lung cancer, for example, the method disclosed in Reference 1 below can be applied.

[Reference 1] "Classification of stage", [online], [Search on February 6, 2018], Internet (URL: http://ganclass.jp/kind/lung/stage/stage.php)

In this case, in step S20, the detection unit 46 detects a lung region, a lymph node region, a region in which distant metastasis is observed, or the like as an observation-required region, depending on the stage of lung cancer as an index value. If the stage of lung cancer is not derived, it indicates that the area requiring observation related to lung cancer was not detected.

Further, in step S16, the detection unit 46 derives the cross-sectional area of the psoas major muscle in the 3rd to 4th lumbar vertebrae as an index value for the evaluation of sarcopenia. In this case, in step S20, the detection unit 46 responds to the value of the change over time in the cross-sectional area of the psoas major muscle, which is an index value. The area of the lumbar spine and the area of the psoas major muscle are detected as areas requiring observation. If it can be considered that the cross-sectional area of the psoas major muscle has not changed with time, it indicates that the observation area for sarcopenia was not detected.

In step S20, the determination unit 48 determines whether or not a plurality of observation-requiring regions corresponding to fatty liver, lung cancer, sarcopenia, etc. have been detected as described above, and according to the determination result, the allocation unit 50 in step S22. However, the observation area is allocated.

As described above, the diagnostic support system 10 of the present embodiment includes an acquisition unit 40 that acquires a medical image, and an extraction unit 42 that extracts an organ region in which an organ is drawn from the medical image acquired by the acquisition unit 40. , A derivation unit 44 that derives the organ information of the organ region extracted by the extraction unit 42, a detection unit 46 that detects an observation-required region that requires observation based on the organ information derived by the derivation unit 44, and a detection unit. When a plurality of observation-requiring areas are detected by 46, a determination unit 48 for determining the allocation of the plurality of observation-requiring areas to a plurality of doctors, and a plurality of observation-requiring areas for a plurality of observation-requiring areas based on the determination results of the determination unit 48. It includes an allocation unit 50 assigned to each of the doctors.

Therefore, according to the present embodiment, the disease can be appropriately diagnosed from the medical image by each of the plurality of doctors.

In the present embodiment, the case where each of a plurality of types of organs is assigned to a specialist for each organ has been described, but the present invention is not limited to this. For example, it may be assigned to a specialist for each disease, a specialist for each level of the disease (progression of the disease, etc.), or a combination of these specialists. In these cases, the allocation table 32 corresponding to each expert may be stored in the storage unit 22.

Further, in the present embodiment, a case where a plurality of organ regions are extracted from a plurality of medical images has been described, but the present invention is not limited to this. For example, a plurality of organ regions may be extracted from one medical image.

Further, in the present embodiment, the case of extracting the region of the entire organ such as the liver and the spleen has been described, but the present invention is not limited to this. After the extraction unit 42 extracts the region of the entire organ, a part of the region may be further extracted from the extracted region. In this case, the derivation unit 44 exemplifies a form in which a part of the organ information is derived from the image of a part of the region extracted by the extraction unit 42. Further, in this case, a mode in which the detection unit 46 derives an index value related to disease evaluation based on a plurality of partial organ information derived for each of the plurality of partial regions by the derivation unit 44 is exemplified. Further, in this case, the plurality of partial regions may be partial regions extracted from the same organ region, such as the upper left lobe of the lung and the upper right lobe of the lung, or may be extracted from different organ regions. It may be a part of the area. Further, in this case, the plurality of organ regions used for deriving the index value related to the evaluation of the disease may be a combination of the region of the whole organ and the region of a part of the organ.

Further, in the present embodiment, the case where the organ region is extracted from a plurality of medical images in the same examination has been described, but the present invention is not limited to this. For example, an organ region may be extracted from a plurality of medical images in which the same subject is photographed at different times. Further, for example, an organ region may be extracted from a plurality of medical images obtained by photographing the same subject by different imaging methods. Examples of different imaging methods in this case include imaging with different imaging devices such as CT imaging and MRI imaging. In addition, different imaging methods in this case include, for example, imaging with the same imaging device, but with and without a contrast medium, and normal imaging with mammography and tomosynthesis imaging. Can be mentioned.

In the present embodiment, the case where the index value related to the evaluation of the disease is displayed on the display unit has been described, but the present invention is not limited to this. For example, in addition to the index value related to the evaluation of the disease, each organ information used for deriving the index value and at least one of each organ region corresponding to each organ information may be further displayed on the display unit.

Further, for example, the diagnosis result using the index value related to the evaluation of the disease may be displayed on the display unit. In this case, when the pixel value of each pixel in the liver region is smaller than the average value of the pixel values in the spleen region by a predetermined value or more and the area of the region where the pixel value is equal to or less than the threshold value is the predetermined value or more, the patient. An example is a form in which information indicating that is a fatty liver is displayed on a display unit.

Further, various processors other than the CPU may execute various processes executed by the CPU executing software (program) in the above embodiment. In this case, the processor is a PLD (Programmable Logic Device) whose circuit configuration can be changed after manufacturing an FPGA (Field-Programmable Gate Array) or the like, and an ASIC (Application Specific Integrated Circuit) or the like in order to execute a specific process. An example is a dedicated electric circuit or the like, which is a processor having a circuit configuration designed exclusively for the purpose. Further, the above-mentioned various processes may be executed by one of these various processors, or a combination of two or more processors of the same type or different types (for example, a plurality of FPGAs and a combination of a CPU and an FPGA). Etc.). Further, the hardware structure of these various processors is, more specifically, an electric circuit in which circuit elements such as semiconductor elements are combined.

Further, in the above embodiment, the mode in which the diagnosis support program 30 is stored (installed) in the storage unit 22 in advance has been described, but the present invention is not limited to this. The diagnostic support program 30 is provided in a form recorded on a recording medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), and a USB (Universal Serial Bus) memory. May be good. Further, the diagnosis support program 30 may be downloaded from an external device via a network.

10 Diagnosis support system 12 Image management device 14 Diagnosis support device 20 CPU
21 Memory 22 Storage unit 23 Display unit 24 Input unit 25 Network I / F
26 Bus 30 Diagnosis support program 32 Allocation table 40 Acquisition unit 42 Extraction unit 44 Reception unit 46 Detection unit 48 Judgment unit 50 Assignment unit 52 Reception unit 54 Display control unit N network

Claims (19)

The acquisition department that acquires medical images and
An extraction unit that extracts the organ region in which the organ is drawn from the medical image acquired by the acquisition unit, and an extraction unit.
A derivation unit that derives organ information of the organ region extracted by the extraction unit, and a derivation unit.
Based on the organ information derived by the derivation unit, a detection unit that detects an observation-required region that requires observation, and a detection unit.
When a plurality of the observation-requiring regions are detected by the detection unit, information regarding the case where one observer observes is performed by a predetermined observer for each combination of the plurality of observation-requiring regions. reference, a determination unit for determining the assignment of the plurality of whether the main observation area allocated to one of the observers, a plurality of the main observation area should be assigned to a plurality of observers,
When the judgment of the judgment unit is assigned to one observer, a plurality of the observation-required areas are assigned to the one observer based on the information regarding the observation by the one observer, and the judgment unit is assigned. When the determination is assigned to a plurality of observers, the plurality of the above are based on the information representing the correspondence relationship between each of the plurality of observers and each of the plurality of observation-required areas, and the determination result of the determination unit. An allocation unit that allocates an observation area to each of the plurality of observers,
Diagnostic support system equipped with. The allocation unit is a plurality of the observation-required areas for each of the plurality of observers, which is one of a plurality of types of organ-specific specialists, a plurality of types of disease-specific specialists, and a disease-level specialist. Assign,
The diagnostic support system according to claim 1. The detection unit is based on the first organ information derived for the first organ region extracted from the first medical image acquired by the acquisition unit and the second medical image acquired by the acquisition unit. The observation-required region is detected by the second organ information derived for the extracted second organ region and the index value derived based on the second organ information.
The diagnostic support system according to claim 1 or 2. The second medical image is the same image as the first medical image and includes a plurality of organ regions in the image.
The diagnostic support system according to claim 3. The derivation unit derives the first organ information from at least the organ region extracted from the first medical image.
The diagnostic support system according to claim 3 or 4. The extraction unit extracts the organ region of the entire organ existing in the medical image, and then further extracts a part of the extracted organ region.
The derivation unit derives some organ information from the part of the region.
The detection unit has the first partial organ information derived for a part of the first organ region extracted from the first medical image and the second part extracted from the second medical image. The index value is derived based on the second partial organ information derived for a partial region of the organ region of the above.
The diagnostic support system according to any one of claims 3 to 5. The first organ region and the second organ region are the same organ region.
The diagnostic support system according to claim 6. The extraction unit is a medical image including the first medical image and an organ existing in the first medical image, and the organ region is obtained from a medical image other than the first medical image. Extract,
The diagnostic support system according to any one of claims 3 to 7. The first medical image and the medical images other than the first medical image are different images in the same examination.
The diagnostic support system according to claim 8. The medical image other than the first medical image is a medical image obtained by being taken in the past than the first medical image.
The diagnostic support system according to claim 8. The first medical image and the medical images other than the first medical image are medical images obtained by photographing by different imaging methods.
The diagnostic support system according to claim 8. The index value includes at least one of information representing the degree of disease progression and the area to be evaluated for the disease.
The diagnostic support system according to any one of claims 3 to 11. The organ information includes at least one of the size of the organ region, the signal value of each pixel in the image of the organ region, and the value calculated using the signal value of each pixel.
The diagnostic support system according to any one of claims 1 to 12. The allocation unit notifies the predetermined contact of the observer who has allocated the observation area to the information regarding the allocation.
The diagnostic support system according to any one of claims 1 to 13. When the index value satisfies a predetermined condition, the allocation unit notifies the predetermined contact of the observer who has allocated the observation area to the information regarding the allocation.
The diagnostic support system according to any one of claims 3 to 13. A reception unit that receives instructions for observing the allocated observation-required area by each of the plurality of observers assigned by the allocation unit.
When the reception unit receives the instruction, a display control unit that controls the display unit to display an image indicating the observation-required area assigned to the observer who has given the instruction.
With more
The diagnostic support system according to any one of claims 1 to 15. The display control unit controls to display the medical image in a state where the observation-requiring area is emphasized as an image showing the observation-requiring area.
The diagnostic support system according to claim 16. Get a medical image,
Extract the organ area where the organ was drawn from the acquired medical image,
Derived organ information of the extracted organ area,
Based on the derived organ information, the area requiring observation is detected, and the area requiring observation is detected.
When a plurality of the observation-requiring areas are detected, when one observer makes an observation, a plurality of information regarding the observation by one predetermined observer for each combination of the plurality of observation-requiring areas are referred to. wherein either the main viewing area allocated to one of the observers, and determines the assignment of the plurality of the main observation area should be assigned to a plurality of viewer's,
When assigning to one observer, when assigning a plurality of the observation-required areas to the one observer and assigning to a plurality of observers based on the information regarding the observation by the one observer, Based on the information representing the correspondence between each of the plurality of observers and each of the plurality of observation-requiring regions and the judgment result, the plurality of observation-requiring regions are assigned to each of the plurality of observers.
A diagnostic support method in which the diagnostic support system executes processing. Get a medical image,
Extract the organ area where the organ was drawn from the acquired medical image,
Derived organ information of the extracted organ area,
Based on the derived organ information, the area requiring observation is detected, and the area requiring observation is detected.
When a plurality of the observation-requiring areas are detected, when one observer makes an observation, a plurality of information regarding the observation by one predetermined observer for each combination of the plurality of observation-requiring areas are referred to. wherein either the main viewing area allocated to one of the observers, and determines the assignment of the plurality of the main observation area should be assigned to a plurality of viewer's,
When assigning to one observer, when assigning a plurality of the observation-required areas to the one observer and assigning to a plurality of observers based on the information regarding the observation by the one observer, Based on the information representing the correspondence between each of the plurality of observers and each of the plurality of observation-requiring regions and the judgment result, the plurality of observation-requiring regions are assigned to each of the plurality of observers.
A program that lets a computer perform processing.

Images