JP2010167042A - Medical diagnostic support apparatus and control method of the same and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To reduce an operation load during reading an image, and to provide a mechanism for suggesting the image treated by a suitable tone processing even when the image showing various properties for each case is a diagnosed object. <P>SOLUTION: Past case data is involved in medical images and disease information is obtained by grade setting information and a diagnosis involved in suitable grade processing for observation of the disease condition, and the past case data and the disease information are associated and stored in a case database 150. CPU111 determines a degree of similarity of the diagnosed object case processed by recognition processing and the past case for each kind of disease information and generates the tone processing image by grading the diagnosed object case with grade setting information on the basis of the determined similarity for each kind of disease information. CPU111 computes an accuracy of the disease information in the diagnosed object case and processes in order to suggest the generated grade processing image according to the computed accuracy. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a medical diagnosis support apparatus that supports medical diagnosis using medical images, a control method thereof, and a program for causing a computer to execute the control method.

  In the medical field, a doctor displays a medical image obtained by photographing a patient on a monitor, interprets the displayed medical image, and observes the state of a diseased part of the patient and its change with time. As an apparatus for generating this type of medical image, for example, a CR (Computed Radiography) apparatus, a CT (Computed Tomography) apparatus, an MRI (Magnetic Resonance Imaging) apparatus, an ultrasonic apparatus (US; Ultraound System), and the like can be given.

  For the purpose of reducing the burden on doctors' interpretation, a medical image processing apparatus has been developed that automatically detects a diseased part or the like by digitizing and analyzing a medical image and performing computer-aided diagnosis. Hereinafter, the computer-aided diagnosis is referred to as CAD (Computer-Aided Diagnosis).

  In such CAD, abnormal shadow candidates are automatically detected as disease sites. In this abnormal shadow detection process, an abnormal tumor shadow representing cancer or the like, a high-density microcalcification shadow, or the like is detected by computer processing image data of a medical image that is a radiographic image. By presenting the detection result, it is possible to reduce the burden on the doctor's interpretation and improve the accuracy of the interpretation result.

  Further, among CAD techniques, a technique for automatically diagnosing benign / malignant and disease types from detected abnormal shadow candidates has been developed. As a technique for realizing this, for example, the following Non-Patent Document 1 introduces a technique for estimating the malignancy of breast cancer in mammography using a Bayesian network. Here, the Bayesian network is a probability model in which a qualitative dependency relationship between uncertain events is represented by a graph and a quantitative relationship between individual events is represented by a conditional probability table. By inputting events that can be observed before diagnosis, such as analysis data of medical images and clinical data such as patient attributes and test results, this model can be unobserved before diagnosis such as malignancy of breast cancer. The probability distribution of an event can be calculated.

  The doctor confirms the final image findings after observing in detail the diseased site that he / she has found or has been automatically detected (or automatically differentiated) by such a CAD system. Then, the doctor captures an image of the diseased part as necessary and attaches it to the interpretation report as a disease reference image.

  Here, when observing a diseased part in detail or attaching an image of a diseased part to an interpretation report, it is necessary to adjust the image to a gradation suitable for observing the diseased state. This is a burden for the doctor. Therefore, if the computer can automatically perform appropriate gradation processing, the burden on the doctor can be reduced. In particular, if it is applied when CAD finds a diseased part, it is possible to automate everything from finding a disease to presenting it in an interpretation report without involving a doctor's hand.

  As a technique for realizing appropriate gradation adjustment of such an image, for example, in the following Patent Document 1, a technique for performing contrast correction processing in consideration of disease characteristics when displaying mammography is used. Specifically, in Patent Document 1, the density of a low density region of a mammary gland or a mass that tends to have a small contrast is expanded, and conversely, a density gradation of a fat mass region where there is little possibility that an image of a microcalcified cluster exists. A process of correcting so as to compress is performed.

  Patent Document 2 below introduces a technique for automatically extracting pixels of interest related to a region of interest on a medical image and performing gradation conversion in consideration of the distribution of density values of the extracted group of pixels of interest. ing.

  Further, in Patent Document 3 below, image data on which appropriate gradation processing has been performed is accumulated as a knowledge base, and based on the gradation setting of the image with the most similar image statistical data selected from the knowledge base. Thus, a technique for performing gradation processing of a processing target image has been introduced.

JP 2004-283410 A JP-A-9-94243 JP 2004-54751 A Burnside ES, Rubin DL, Fine JP, Shachter RD, Sisney GA, Leung WK, "Bayesian network to predict breast cancer risk of mammographic microcalcifications and reduce number of benign biopsy results: initial experience", Radiology. 2006 Sep; 240 (3) : 666-73.

  However, although the general characteristics of the disease are considered in the technique described in Patent Document 1, since uniform processing is performed for any case, the characteristics of each case in the same kind of disease Appropriate processing according to the difference is not performed. Therefore, it is necessary to perform gradation processing in consideration of the difference in characteristics for each case.

  Further, in the techniques described in Patent Document 2 and Patent Document 3, both only perform gradation processing based on data obtained by analyzing an image. Processing considering characteristics is not performed. Therefore, multiple cases with different characteristics even though they look similar on the image may be considered, so that in cases where the appropriate gradation setting is different, an image that has been subjected to appropriate processing is not necessarily presented. Absent. Even in such a case, it is necessary to reliably present an image that has been subjected to gradation processing according to the characteristics of the disease desired by the doctor.

  The present invention has been made in view of such problems, and reduces the workload during interpretation, and appropriate gradation processing even when an image showing various characteristics for each case is to be interpreted. An object is to provide a mechanism for presenting an image subjected to.

  A medical diagnosis support apparatus according to the present invention is a medical diagnosis support apparatus that supports medical diagnosis using a medical image, and is intended for a past case including a medical image that has been diagnosed for a disease. Past case accumulation means for accumulating case data, gradation setting information relating to gradation setting appropriately performed for observing a disease state, and disease information obtained by the diagnosis, and the medical image The interpretation target case recognizing means for performing the process of recognizing the case data of the interpretation target case including the case data of the interpretation target case and the case data of the past case for each type of the disease information, Similarity determination means for determining the similarity between the target case and the past case, and for each type of the disease information, the reading using the gradation setting information based on the similarity determined by the similarity determination means. Gradation processing image generation means for gradation-processing a target case to generate a gradation processed image, accuracy calculation means for calculating the accuracy of disease information in the interpretation target case, and accuracy calculated by the accuracy calculation means And a gradation processed image presenting means for performing a process of presenting the gradation processed image generated by the gradation processed image generating means.

  The control method of the medical diagnosis support apparatus of the present invention is a control method of a medical diagnosis support apparatus that supports medical diagnosis using a medical image, and targets past cases including the medical image that have been diagnosed with a disease. As a past case accumulation step of associating and accumulating case data of the past case, gradation setting information relating to gradation setting appropriately performed for observing a disease state, and disease information obtained by the diagnosis And an interpretation target case recognition step for recognizing the case data of the interpretation target case including the medical image, and the case data of the interpretation target case and the case data of the past case for each type of the disease information. In comparison, the similarity determination step for determining the similarity between the interpretation target case and the past case, and the similarity determined in the similarity determination step for each type of the disease information A gradation processing image generation step of generating a gradation processed image by gradation processing of the interpretation target case using the gradation setting information, and a probability calculation step of calculating the accuracy of the disease information in the interpretation target case And a gradation processing image presentation step for performing a process of presenting the gradation processing image generated in the gradation processing image generation step according to the accuracy calculated in the accuracy calculation step.

  The program of the present invention is a program for causing a computer to execute a control method of a medical diagnosis support apparatus that supports medical diagnosis using a medical image, the past case including the medical image in which a diagnosis of a disease has been made In the past, the case data of the past case, the gradation setting information relating to the gradation setting appropriately applied for observing the disease state, and the past case that accumulates the disease information obtained by the diagnosis in association with each other An accumulation step, an interpretation target case recognition step for performing processing for recognizing case data of an interpretation target case including the medical image, and case data of the interpretation target case and case data of the past case for each type of the disease information And the similarity determination step for determining the similarity between the interpretation target case and the past case, and the similarity determination step for each type of the disease information. A gradation processing image generation step of generating a gradation processing image by gradation processing of the interpretation target case using the gradation setting information based on the similarity determined in the step, and a disease in the interpretation target case An accuracy calculation step for calculating the accuracy of information, and a gradation processing image presentation for performing processing for presenting the gradation processing image generated in the gradation processing image generation step according to the accuracy calculated in the accuracy calculation step And causing the computer to execute the steps.

  According to the present invention, it is possible to reduce the work load at the time of interpretation, and to present an image on which appropriate gradation processing has been performed even when an image showing various characteristics for each case is an interpretation target.

  The best mode (embodiment) for carrying out the present invention will be described below with reference to the drawings. The embodiment described below is only an example, and the present invention is not limited to the illustrated configuration.

(First embodiment)
First, a first embodiment of the present invention will be described.
FIG. 1 is a schematic diagram illustrating an example of a schematic configuration of a medical diagnosis support system according to the first embodiment of the present invention.

  As shown in FIG. 1, the medical diagnosis support system according to the present embodiment includes a medical diagnosis support apparatus 100, a medical image photographing apparatus 200, a medical image database 300, a medical document database 400, and a local area network (LAN). 500. That is, the medical diagnosis support system shown in FIG. 1 is configured such that the medical diagnosis support apparatus 100 is connected to the medical image capturing apparatus 200, the medical image database 300, and the medical document database 400 via the LAN 500.

  The medical diagnosis support apparatus 100 is an apparatus that supports medical diagnosis using a medical image, and includes a control unit 110, a monitor 120, a mouse 130, a keyboard 140, and a case database 150.

  The control unit 110 controls the operation of the medical diagnosis support apparatus 100, and includes a central processing unit (CPU) 111, a main memory 112, a magnetic disk 113, a display memory 114, and a bus 115. Has been. Then, the CPU 111 executes a program stored in the main memory 112, for example, to communicate with the medical image capturing apparatus 200, the medical image database 300, and the medical document database 400, and to control the entire medical diagnosis support apparatus 100. Various controls are executed.

  The CPU 111 mainly controls the operation of each component of the medical diagnosis support apparatus 100 and controls the operation of the medical diagnosis support apparatus 100 in an integrated manner.

  The main memory 112 stores a control program executed by the CPU 111 and provides a work area when the CPU 111 executes the program.

  The magnetic disk 113 stores (stores) an operating system (OS), device drivers for peripheral devices, various application software, and the like.

  The display memory 114 temporarily stores display data to be displayed on the monitor 120.

  The bus 115 connects the components of the medical diagnosis support apparatus 100 so that they can communicate with each other, and connects the medical diagnosis support apparatus 100 and the LAN 500 so that they can communicate with each other.

  The monitor 120 is composed of, for example, a CRT monitor or a liquid crystal monitor, and displays an image or the like based on display data in the display memory 114 under the control of the CPU 111.

  The mouse 130 and the keyboard 140 are used for a pointing input and a character input by the user, respectively.

  In the case database 150, the case data of the past cases in which the diagnosis of the disease has been made, the gradation setting information appropriately applied for the observation of the disease state, and the disease information obtained by the diagnosis are the case data. It is accumulated in association with.

  The medical diagnosis support apparatus 100 according to the present embodiment can read various types of medical image data from the medical image database 300 via the LAN 500. For example, an external storage device such as an FDD, CD-RW drive, MO drive, ZIP drive, or the like may be connected to the medical diagnosis support apparatus 100, and medical image data may be read from these drives. Alternatively, medical image data may be acquired directly from the medical image photographing apparatus 200 via the LAN 500.

  Similarly, the medical diagnosis support apparatus 100 can read medical document data from the medical document database 400 via the LAN 500. For example, an external storage device such as an FDD, CD-RW drive, MO drive, ZIP drive, or the like may be connected to the medical diagnosis support apparatus 100, and medical document data may be read from these drives. Specifically, the medical document data stored in the medical document database 400 corresponds to, for example, an electronic medical record or interpretation report of a patient who is a subject to be imaged.

  Furthermore, the medical diagnosis support apparatus 100 can store (store) data read from the medical image capturing apparatus 200, the medical image database 300, and the medical document database 400 or the analysis result thereof in the case database 150. Here, as the analysis result, for example, image statistical data obtained by analyzing the image data and information on each item such as the age and sex of the patient described in the electronic medical record can be stored.

  The medical image photographing apparatus 200 photographs a patient that is a subject to be photographed and acquires medical image data related to the patient. The medical image capturing apparatus 200 can perform, for example, the control of the CPU 111 of the medical diagnosis support apparatus 100 when capturing an image of a patient who is a subject to be imaged. Medical image data acquired by the medical image photographing apparatus 200 is stored (stored) in the medical image database 300 via the LAN 500 as necessary. For example, examples of the medical imaging apparatus 200 include an X-ray CT apparatus, an MRI apparatus, a US apparatus, an X-ray apparatus, and a nuclear medicine apparatus.

  The medical image database 300 stores medical image data obtained by, for example, photographing by the medical image photographing device 200. The medical diagnosis support apparatus 100 is connected to the medical image database 300 via the LAN 500, and acquires necessary medical image data therefrom.

  The medical document database 400 stores medical document data including information necessary for diagnosis support processing. The medical diagnosis support apparatus 100 is connected to the medical document database 400 via the LAN 500, and acquires necessary medical document data therefrom.

  The LAN 500 connects the medical diagnosis support apparatus 100, the medical image photographing apparatus 200, the medical image database 300, and the medical document database 400 so that they can communicate with each other.

  Next, a processing procedure in the control method of the medical diagnosis support apparatus 100 according to the first embodiment will be described.

  FIG. 2 is a flowchart illustrating an example of a processing procedure in the control method of the medical diagnosis support apparatus 100 according to the first embodiment of the present invention. Specifically, the flowchart shown in FIG. 2 is realized by the CPU 111 executing a program stored in the main memory 112.

  In the following processing, the user (doctor) inputs various commands (instructions / commands) to the medical diagnosis support apparatus 100 by operating the mouse 130 and the keyboard 140. In the following processing, the execution status and execution result of the program executed by the CPU 111 are displayed on the monitor 120 as necessary. Then, the user (doctor) gives an instruction while viewing the information displayed on the monitor 120.

  First, in step S101 of FIG. 2, the CPU 111 reads medical image data and medical document data of a patient to be examined as desired medical examination data in accordance with a command input by the user using the mouse 130 or the keyboard 140. Specifically, the CPU 111 performs a process of inputting medical image data of the patient to be examined from the medical image database 300 and inputting medical document data of the patient to be examined from the medical document database 400. Note that the CPU 111 may input these data from various storage media such as a storage device connected to the medical diagnosis support apparatus 100, such as an FDD, a CD-RW drive, an MO drive, and a ZIP drive.

  Hereinafter, the desired medical examination data input in step S101 is referred to as “interpretation target case”, and the medical image data thereof is referred to as “interpretation target image data”. Further, the CPU 111 inputs, as medical document data, an electronic medical record of a patient (hereinafter referred to as “interpretation target patient”) that is a target (examination target) for image interpretation.

  Subsequently, in step S <b> 102, the CPU 111 performs processing for displaying an interpretation target image (medical image) based on the interpretation target image data input to the medical diagnosis support apparatus 100 in step S <b> 101 on the monitor 120.

  Thereafter, after the user (doctor) finds the diseased part on the image to be interpreted displayed on the monitor 120, the diseased part region is designated by the user (doctor). Subsequently, in step S103, the CPU 111 Recognize the disease region. Here, this recognition processing is referred to as “interpretation target case recognition processing”. Specifically, when a doctor surrounds a region sufficiently including a diseased part on the image to be interpreted displayed on the monitor 120 using the mouse 130, the CPU 111 defines the region as a diseased part ROI (Region of Interest). ). Thereafter, the CPU 111 performs processing for reading image data of the diseased part ROI, which is a recognition processing result, into the main memory 112.

  Subsequently, in step S104, the CPU 111 analyzes the image data of the diseased part ROI read into the main memory 112 in step S103, and performs image statistical data extraction processing. Specifically, after segmenting the boundary of the diseased part from the image data of the diseased part ROI, the CPU 111 extracts, for example, the shape feature value of the diseased part, the feature value of the density distribution, and the feature value of the texture pattern as the image statistical data. To do. Thereafter, the CPU 111 performs processing for reading the extracted image statistical data into the main memory 112.

  When the processing of step S101 is completed, subsequently, in step S105, the CPU 111 performs clinical data extraction processing from the medical document data (electronic medical record) of the interpretation target patient input in step S101. Here, as clinical data, for example, data such as age, sex, past history, smoking history, tumor / inflammation marker, etc. of the patient to be interpreted are extracted from the electronic medical record as medical document data. Thereafter, the CPU 111 performs processing for reading the extracted clinical data into the main memory 112.

When the processing of step S104 and step S105 ends, the process proceeds to step S106.
In step S <b> 106, the CPU 111 performs a process of setting the disease information to be initially processed for the disease information stored in the case database 150. Here, the disease number for specifying the disease information is set as i (i = 1 in the case of the first process), and the number of types of the disease information in the case database 150 is set as n.

  At this time, the disease information in the present embodiment is represented by a combination of the type of the disease and its location. This is because the appropriate gradation setting may differ depending not only on the type of disease but also on the location of the disease. In the case of `` diffuse lung disease '' in the lung field, if the shadow is distributed in the central part of the lung field, it is necessary to set the gradation so that the inside of the lung field can be easily observed. When distributed in the marginal part, it is necessary to set the gradation so that both the lung field and the structure around the lung field can be easily observed.

  FIG. 3 is a schematic diagram showing an example of a list of disease information used in step S106 of FIG. FIG. 3 shows a list of disease information expressed by disease types and their locations. Then, it is assumed that disease information is stored in the case database 150 as in the list shown in FIG. In this processing, when the total (number of types) of types of disease information is n, the disease information ID to be processed is set as the disease number i, and i = 1 is set as the first disease number.

  Subsequently, in step S107, the CPU 111 performs a process of selecting from the case database 150 a past case group in which the disease number i set in step S106 matches the disease information. Specifically, a case of past case data whose disease information item matches disease number i is selected (selected) from case data (past case data) of many past cases stored in the case database 150. Perform the process.

  Although the description is mixed, the CPU 111 performs a process of storing in the case database 150 cases (past cases) whose disease names have been determined in advance by past diagnosis. This process is referred to as “past case accumulation process”. Here, the process in which the CPU 111 accumulates past cases in advance will be described in detail with reference to the flowchart of FIG.

  FIG. 4 is a flowchart showing an example of a processing procedure of past case accumulation processing for accumulating past cases in the case database 150 in the medical diagnosis support apparatus 100 according to the first embodiment of the present invention. Specifically, the flowchart shown in FIG. 4 is realized by the CPU 111 executing a program stored in the main memory 112. In the following description, the steps performing the same processing as in the flowchart of FIG. 2 describe which steps in FIG. 2 are the same, and detailed description thereof is omitted.

  In FIG. 4, the processing from step S201 to step S205 is the same as the processing from step S101 to step S105 in FIG.

  Thereafter, when the user (doctor) performs detailed observation of the diseased part and appropriately sets the gradation when attaching the slice image in which the diseased part is reflected as a reference image to the interpretation report, subsequently, in step S206, the CPU 111 Performs recognition processing of the gradation setting information. Specifically, two values of a window width (Window Width; hereinafter referred to as “WW”) and a window level (Window Level; hereinafter referred to as “WL”) adjusted for the image are recognized. To do. Thereafter, the CPU 111 performs processing for reading the gradation setting information, which is the recognition processing result, into the main memory 112.

  Subsequently, in step S207, the CPU 111 performs a process of recognizing disease information obtained by a user (doctor) as a result of diagnosis. Specifically, a disease impression item and a disease position information item in image diagnosis are recognized as disease information. Such information (disease information) may be in the form of recognizing information input by a doctor in a dedicated input form at the time of interpretation, or in the form of extracting and recognizing information from the created interpretation report. However, if a definitive diagnosis of the disease is not made in the image diagnosis, an electronic medical chart of the corresponding patient is obtained from the medical document database 400 at a stage where a definitive diagnosis is made later based on the result of biopsy, etc. Recognize by extracting information.

  In step S208, the CPU 111 performs processing for associating the data extracted in steps S204 and S205 with the information recognized in steps S206 and S207 and storing them in the case database 150. Here, the image statistical data extracted in step S204 and the clinical data extracted in step S205 are combined to obtain case data regarding the case. In step S208, the gradation setting information of the image recognized in step S206 and the disease information recognized in step S207 are stored in the case database 150 in association with the case data.

FIG. 5 shows the first embodiment of the present invention, when gradation setting information, disease information, and case data (image statistical data and clinical data) are stored in the case database 150 in association with one case. It is a schematic diagram which shows an example of this data item.
In FIG. 5, a case ID for specifying one case shown in FIG. 5 is set, and gradation setting information, disease information, and case data (image statistical data and clinical data) are related to the one case. Is set. FIG. 5 shows an example of data items and data contents for each gradation setting information, disease information, and case data (image statistical data and clinical data).

  Through the processes from step S201 to step S208, the past case data is stored in the case database 150 in association with the gradation setting information and the disease information.

Here, it returns to description of FIG. 2 again.
In step S107 of FIG. 2, specifically, the disease number i and the data item of disease information (disease information ID) match from the case database 150 in which past case data and the like are stored by the method shown in FIG. All case IDs of past cases to be selected are selected.

  Subsequently, in step S108, the CPU 111 compares the case data with respect to the interpretation target case and all the past cases belonging to the disease number i selected in step S107, and determines the similarity of the past case to the interpretation target case. Process.

  Here, the process in which the CPU 111 determines the similarity of the past case with respect to the interpretation target case (that is, the process in step S108 in FIG. 2) will be described in detail with reference to the flowchart in FIG.

  FIG. 6 is a flowchart illustrating an example of a detailed processing procedure of the similarity determination process in step S108 of FIG.

  First, when the process of step S108 in FIG. 2 is started, in step S301 in FIG. 6, the CPU 111 sets a past case to be processed first from the past cases selected in step S107 in FIG. Process. Specifically, in this process, the total number of selected past cases is set as m, and the case ID of the past case to be processed is set as a case number j (j = 1 in the case of the first process).

  Subsequently, in step S302, the CPU 111 performs a process of comparing the case data of the interpretation target case with the case data of the past case of the case number j. Here, the case data to be compared are specifically image analysis data extracted from the diseased region and clinical data acquired from the electronic medical record. Further, as a comparison method, specifically, a feature space having feature values of image analysis data and clinical data is constructed, and each data is mapped to a feature point in the feature space to compare spatial positional relationships. .

  Subsequently, in step S303, the CPU 111 performs determination by calculating the similarity of the past case of the case number j with respect to the interpretation target case based on the comparison result in step S302. Specifically, the similarity is obtained by obtaining the Euclidean distance with respect to the feature point representing the case data of the interpretation target case mapped to the feature space in step S302 and the feature point representing the case data of the past case with the case number j. Is calculated.

  Subsequently, in step S304, the CPU 111 performs a process of incrementing the value of the case number j indicating the past case to be processed by one.

  Subsequently, in step S305, the CPU 111 compares the current case number j with the total number m of the selected past cases, and whether or not the current case number j is less than or equal to the total number m of the selected past cases. Determine whether.

  As a result of the determination in step S305, if the current case number j is less than or equal to the total number m of the selected past cases (S305 / YES), the process returns to step S302, and the processes after step S302 are performed again.

  On the other hand, as a result of the determination in step S305, if the current case number j is not less than the total number m of selected past cases (S305 / NO), the processing of the flowchart shown in FIG.

  By performing the processes from step S301 to step S305, the similarity determination process for each past case in step S108 in FIG. 2 is performed.

Here, it returns to description of FIG. 2 again.
When the process of step S108 ends, subsequently, in step S109, the CPU 111 selects a past case with a high similarity based on the similarity for each past case determined in step S108, and gradation setting information regarding the past case Process to get. Specifically, the gradation setting information in the selected past case having a high similarity is acquired from the case database 150.

  At this time, in addition to the method of selecting the past case having the highest similarity, for example, a method of selecting a plurality of past cases in descending order of the similarity and acquiring the respective gradation setting information is also applicable. Further, there may be a case where a plurality of appropriate gradation settings are given in the selected past case. For example, in the case of a “neoplastic disease”, a gradation setting that narrows the WW value to the soft tissue concentration and the anatomical structure of the margin of the diseased part are observed so that the anatomical structure inside the tumor can be observed In order to make it easier, it is conceivable that a gradation setting with a wide WW value is given. In this case, the gradation setting information is acquired for the number set in the past case.

  Subsequently, in step S110, the CPU 111 performs gradation processing on the image interpretation target image data based on the gradation setting information of the similar past case acquired in step S109, and generates gradation processed image data. I do. This is referred to as “gradation processed image generation processing”. In the present embodiment, the gradation setting information of the similar past case is directly applied as the gradation setting information in the interpretation target image data during the gradation processing image generation processing. In step S110, gradation-processed image data is generated by performing gradation processing on the image data to be interpreted as many times as the number of gradation setting information acquired in step S109.

  Subsequently, in step S111, the CPU 111 performs a process of increasing the value of the disease number i indicating the disease information to be processed by one.

  Subsequently, in step S112, the CPU 111 compares the current disease number i with the number n of types of disease information set in step S106, and the current disease number i is equal to or less than the number n of types of disease information. Determine whether or not.

  As a result of the determination in step S112, if the current disease number i is less than or equal to the number n of types of disease information (S112 / YES), the process returns to step S107, and the processes after step S107 are performed again.

On the other hand, if it is determined in step S112 that the current disease number i is not less than or equal to the number of types of disease information (S112 / NO), the process proceeds to step S113.
When the processing proceeds to step S113, the CPU 111 performs a probability calculation process for calculating the probability of being diagnosed as the disease information for each disease information regarding the interpretation target case. Specifically, a method of calculating the accuracy is applied based on the past case similarity information calculated for each disease information corresponding to the disease number i in step S108. Hereinafter, the accuracy calculation processing in step S113 will be described in detail.

First, for each disease information corresponding to the disease number i, m past cases are selected in descending order of similarity, and an average value (average value shown in the following equation (1)) of the m degrees of similarity is selected. calculate. However, in the equation (1), S _{i, j} represents the degree of similarity regarding the jth case belonging to the disease information of the disease number i.

  Then, according to the magnitude | size of the average value of similarity, accuracy (accuracy shown to the following (2) formula) is provided for every disease information corresponding to the disease number i.

  As this method, for example, the following equation (3) can be applied. In equation (3), for all disease numbers (total n), after calculating the average value of similarities given in equation (1) and obtaining the total value, the similarity corresponding to disease number i The accuracy is calculated by dividing the average value by the total value.

  In this way, the higher the average value of the similarity, the higher the accuracy is because the past cases with higher similarity of the case data including the clinical data in addition to the image analysis data, the cases to be interpreted and the disease information This is because there is a high possibility that

  Subsequently, in step S114, the CPU 111 obtains a gradation processed image (interpretation target image after gradation processing) based on the gradation processed image data generated for each disease information in step S110 in the disease information calculated in step S113. Processing to present according to the accuracy is performed. This process is referred to as “gradation processed image presentation process”. Here, as a presentation method, specifically, there is a method of displaying a list of diseased part slice images showing a diseased part on the monitor 120 in descending order of accuracy of disease information.

FIG. 7 is a schematic diagram illustrating a presentation example of a gradation processed image (an image to be interpreted after gradation processing) according to the accuracy for each disease information in step S114 of FIG.
Specifically, FIG. 7 shows a gradation based on the gradation setting set in the similar past case for each set disease information regarding the case presenting the “ground glass shadow” in the chest CT image that is the image to be interpreted. It is the example which displayed the diseased part slice image which performed the process as a list in order of accuracy.

  Then, when the process of step S114 ends, the process of the flowchart shown in FIG. 2 ends.

  As described above, according to the configuration of the first embodiment described above, by automating the gradation processing of the image to be interpreted, the doctor who is the user can save the trouble of adjusting the gradation of the image to be interpreted. In addition, the doctor who is the user can respond to various cases by presenting the gradation processed images obtained by performing gradation processing on the image to be interpreted based on similar past cases for each disease information in descending order of possibility of the disease information. Thus, it is possible to reliably and easily select a gradation processed image that matches desired disease information.

<Variation 1 of the first embodiment>
Below, the modification 1 of 1st Embodiment is demonstrated.
The similarity determination process between the interpretation target case and each past case in step S108 shown in FIG. 2 may take the following form.

  In the case of a CT image, the image data itself generally has a gradation of 12 bits per pixel. Accordingly, in step S108, image statistical data extracted from image data of 12-bit gradation per pixel is compared in the comparison between the case data of the interpretation target case and the case data of the past case, and the similarity is obtained. It will be.

  On the other hand, after performing gradation processing using the gradation setting information of the past case, image statistical data can be extracted from the interpretation target case and the past case, and the similarity can be obtained by comparing them. . At this time, the image to be interpreted after gradation processing is generally an image in which gradation is narrowed down to 8 bits so that it can be displayed on the monitor 120, but this is as it is when a doctor is browsing a diseased part. It is an image. Therefore, by comparing the case data extracted from the image after gradation processing, the similarity can be calculated under conditions closer to when the doctor actually browses the image.

<Modification 2 of the first embodiment>
Below, the modification 2 of 1st Embodiment is demonstrated.
The gradation processing for the image to be interpreted based on the gradation setting information of the past case having a high degree of similarity in step S110 shown in FIG. 2 may take the following form.

  In general, there is a gradation setting serving as a reference value for each type of disease and its location. Therefore, a method of performing gradation processing on an image to be interpreted based on both a value (referred to as a “preset value”) previously set as a reference value for each disease information and gradation setting information of similar cases Is mentioned. Specifically, for example, the following method can be considered.

The preset values for gradation setting in the corresponding disease information are WW: W _p and WL: L _p , respectively. Moreover, the gradation settings of the similar past cases are set to WW: W _s and WL: L _s , respectively, and the similarity of the similar past cases is set as shown in the following equation (4).

At this time, assuming that the gradation settings based on both are WW: W _ps and WL: L _ps , these can be obtained by the following equations (5) and (6), respectively.

  Both formulas (5) and (6) are calculated by weighting with the similarity S. This is because, when the value of S is large, the reliability of similar past cases is high, so the weight of gradation setting for similar past cases is increased, and conversely, when the value of S is small, the reliability of similar past cases is This is because the weight of the preset value is intended to be increased.

  In this way, by using the preset value for gradation setting in disease information, even if a past case with a high degree of similarity cannot be obtained, gradation setting of a certain level or more can be performed without performing inappropriate gradation processing. Based gradation processing can be performed.

<Modification 3 of the first embodiment>
Below, the modification 3 of 1st Embodiment is demonstrated.
The presentation process of the gradation processed image according to the accuracy for each disease information in step S114 shown in FIG. 2 may take the following form.

  In the display of the image to be interpreted (gradation processed image) after gradation processing, a method of displaying a list of diseased part slice images on the interpretation report for each disease information is conceivable. In this way, by presenting the image after gradation processing on the interpretation report, the user doctor can capture the reference image from the medical image and paste it on the interpretation report. Can be achieved.

<Modification 4 of the first embodiment>
Below, the modification 4 of 1st Embodiment is demonstrated.
The presentation process of the gradation processed image according to the accuracy for each disease information in step S114 shown in FIG. 2 may take the following form.

  In the display of the interpretation target image (gradation processed image) after gradation processing, a diseased part slice image is displayed on the medical image display area used for interpretation with the gradation setting with the highest probability of disease, A method is conceivable in which only the diseased part ROI image is displayed in a list in order of accuracy of the disease information on the region. Here, the diseased part ROI image corresponds to a gradation processed image of an image region obtained by cutting out a diseased part from a medical image. Further, the list display described above may be displayed on the interpretation report as in the above-described third modification. In this way, by displaying only the diseased part ROI image after gradation processing as a list, it is possible to reduce the image display area while leaving the area that the doctor wants to observe. Therefore, the number of images that can be displayed at a time can be increased. Furthermore, when a doctor who is a user selects one of a plurality of diseased part ROI images displayed in a list, a function for displaying a diseased part slice image subjected to gradation processing corresponding to the selected one on a medical image display area is added. May be. As a result, the entire image can be confirmed with a gradation setting desired by the doctor by an easy operation.

(Second Embodiment)
Next, a second embodiment of the present invention will be described.
The configuration of the medical diagnosis support system and the medical diagnosis support device 100 according to the second embodiment is the same as the configuration in the first embodiment, and therefore the configuration shown in FIG. 1 is used. Description is omitted. Moreover, in the following description, a different part from 1st Embodiment is demonstrated.

  FIG. 8 is a flowchart showing an example of a processing procedure in the control method of the medical diagnosis support apparatus 100 according to the second embodiment of the present invention. Specifically, the flowchart shown in FIG. 8 is realized by the CPU 111 executing a program stored in the main memory 112. In FIG. 8, steps performing the same processing as in the flowchart of FIG. 2 in the first embodiment are given the same step numbers, and detailed descriptions thereof are omitted.

  First, in step S101 of FIG. 8, the CPU 111 reads medical image data and medical document data (interpretation target case) of a patient to be examined as desired medical examination data in accordance with a command input by the user.

  Subsequently, in step S401, the CPU 111 performs an automatic detection process of a diseased part region using CAD technology from the image interpretation target image data input in step S101. Here, for example, after the computer performs processing for emphasizing the shadow of the diseased part, the boundary region of the diseased part is segmented, and the region sufficiently surrounding the diseased part is automatically detected as the diseased part ROI. Thereafter, the CPU 111 performs processing for reading image data of the diseased part ROI, which is an automatic detection result, into the main memory 112.

  Subsequently, in step S402, the CPU 111 analyzes the image data of the diseased part ROI read into the main memory 112 in step S401, and performs image statistical data extraction processing.

  Thereafter, processing similar to the processing after step S106 shown in FIG. 2 is sequentially performed.

  As described above, according to the configuration of the second embodiment described above, it is possible to automate processes from discovery of a diseased part in an image to be interpreted to gradation processing of an appropriate image to be interpreted using CAD technology. Thereby, the doctor who is a user can confirm the image of the disease appropriately gradation-processed at the stage of first viewing the image to be interpreted, and can use it as a diagnosis result, thereby reducing the doctor's workload. be able to.

<Modification of Second Embodiment>
The gradation processing image presentation processing according to the accuracy for each disease information in step S114 shown in FIG. 8 may take the following form.

  In the present embodiment, it is possible to generate a gradation-processed image obtained by performing gradation processing appropriate for browsing a diseased part before a doctor browses an image to be interpreted. For this reason, when browsing a volume image such as a CT image, a method of displaying a medical image as a moving image with the most accurate gradation setting of disease information is conceivable so that a doctor can easily grasp the characteristics of the disease. More specifically, when an image including a diseased part is displayed while automatically shifting slice images in order, a method of appropriately changing to an appropriate gradation setting and displaying a moving image can be considered. Thereby, the doctor can confirm the image of the disease with an appropriate gradation setting without adding his / her operation when viewing the volume image.

  Further, in the present embodiment, in the moving image display, the gradation processed image processed by the gradation setting of the most accurate disease information is displayed, but in consideration of the case where the doctor desires different disease information, At the same time, only the diseased part ROI is displayed in a list in order of accuracy of the disease information. Then, when a diseased part ROI of desired disease information is selected from the displayed list, the CPU 111 performs control so that the gradation display in the moving image is switched to the selected setting. Thereby, a doctor who is a user can check an image having a gradation setting that matches desired disease information at any time.

(Third embodiment)
Next, a third embodiment of the present invention will be described.
The configuration of the medical diagnosis support system and the medical diagnosis support device 100 according to the third embodiment adopts the same configuration as the configuration in the first embodiment, and therefore the configuration shown in FIG. 1 is used. Description is omitted. Moreover, in the following description, a different part from 1st Embodiment is demonstrated.

  FIG. 9 is a flowchart illustrating an example of a processing procedure in the control method of the medical diagnosis support apparatus 100 according to the third embodiment of the present invention. Specifically, the flowchart shown in FIG. 9 is realized by the CPU 111 executing a program stored in the main memory 112. Note that, in FIG. 9, steps that perform the same processing as in the flowchart of FIG. 2 in the first embodiment are given the same step numbers, and detailed descriptions thereof are omitted.

  First, as shown in FIG. 9, in the processing in this embodiment, the processing from step S101 to step S105 in FIG. 2 in the first embodiment is performed.

  Subsequently, in step S501, the CPU 111 performs disease information estimation processing and accuracy calculation processing based on the image statistical data and clinical data read into the main memory 112 in step S104 and step S105, respectively. . At this time, when a plurality of pieces of disease information are estimated, accuracy calculation processing is performed for each piece of disease information.

  Here, as one of the means for estimating disease information, for example, the Bayesian network technique described in Non-Patent Document 1 can be applied. Thereby, the probability of the assumed disease information can be calculated by inputting the image statistical data and the clinical data to the nodes in the inference model of the Bayesian network constructed in advance for estimating the disease information. . For example, if image statistical data and clinical data obtained from a case showing an image finding of “ground glass shadow” in the lung field in a chest CT image, a disease that may show the same “ground glass shadow” image finding Information is output. Specifically, for example, “massic disease (center of lung field): 80%” and “sarcoidosis (center of lung field): 20%” are output. At this time, the estimated disease information follows the classification of the list of disease information shown in FIG.

  Thereafter, the CPU 111 performs a process of reading the information obtained as a result of step S501 into the main memory 112.

  Subsequently, in step S502, the CPU 111 assigns identification numbers for the estimated number of diseases to the disease information estimated in step S501, and then performs setting processing of disease information that is the first processing target. Specifically, the number of types of disease information estimated in step S906 is n, and identification numbers (identification numbers shown in the following expression (7)) are assigned in descending order of the accuracy of the disease.

  For example, in the specific example of step S501, n = 2, and “tumorous disease (lung field center)”: identification number 1, “sarcoidosis (lung field center)”: identification number 2.

  In step S502, i = 1 is set as the disease number to be processed. At this time, the disease number i to be processed is set as an identification number k.

  Thereafter, the processing from step S107 to step S112 shown in FIG. 2 is performed.

  If it is determined in step S112 that the current disease number i is not equal to or less than the number n of types of disease information (S112 / NO), the process proceeds to step S114. The process of step S114 shown in FIG. 9 is the same process as step S114 shown in FIG.

  Then, when the process of step S114 ends, the process of the flowchart shown in FIG. 9 ends.

  As described above, in the configuration of the third embodiment described above, in the stage of step S501, possible disease information is estimated and the number is narrowed down. Thereby, it is not necessary to follow the procedure of performing a similarity search for all types of disease information stored in the case database 150 and performing gradation processing based on the result. Therefore, the computational complexity of the computer can be reduced.

(Fourth embodiment)
Next, a fourth embodiment of the present invention will be described.
In the embodiments from the first embodiment to the third embodiment, two types of image statistical data and clinical data are used as case data for calculating case similarity and estimating disease information. . However, in addition to these two types of data, it is also conceivable to use the imaging parameters of the medical image imaging apparatus 200.

  As the imaging parameters, specifically, in the case of MRI (magnetic resonance imaging), the type of imaging procedure (pulse sequence), the echo time TE, the repetition time TR, the width of the RF pulse in the imaging procedure, Amplitude, gradient magnetic field pulse width, amplitude and the like are included. These imaging parameters can be used by storing them in the case database 150 via the LAN 500 when a medical image is captured by the medical image capturing apparatus 200.

  As described above, in the configuration of the fourth embodiment described above, processing including imaging parameters is performed. Thereby, even when medical image data captured by a plurality of medical image capturing devices is included in the case database 150, gradation processing suitable for the characteristics of the imaging parameters of the image to be interpreted can be performed.

  In each of the above-described embodiments of the present invention, the case data includes image statistical data and clinical data (further, imaging parameters). However, the present invention is not limited to this. Absent. For example, the case data may include at least one of image statistical data, clinical data, and imaging parameters.

  According to each of the embodiments of the present invention described above, it is possible to reduce the workload of a doctor at the time of interpretation, and even when an image showing various characteristics for each case is targeted, an appropriate matching with desired disease information is performed. An image that has been subjected to gradation processing can be presented.

(Other embodiments)
2, 4, 6, 8, and 9 showing the control method of the medical diagnosis support apparatus 100 according to each embodiment of the present invention described above, the CPU (111) of the computer performs the storage medium (112 This can be realized by executing the program stored in (). This program and a computer-readable recording medium storing the program are included in the present invention.

  In addition, the present invention can be implemented as, for example, a system, apparatus, method, program, storage medium, or the like. Specifically, the present invention may be applied to a system including a plurality of devices. You may apply to the apparatus which consists of one apparatus.

  In the present invention, a software program (in the embodiment, a program corresponding to the flowcharts shown in FIGS. 2, 4, 6, 8, and 9) that realizes the functions of the above-described embodiments is stored in a system or apparatus. Includes those that are supplied directly or remotely. The present invention also includes a case where the system or the computer of the apparatus is achieved by reading and executing the supplied program code.

  Accordingly, since the functions of the present invention are implemented by computer, the program code installed in the computer also implements the present invention. In other words, the present invention includes a computer program itself for realizing the functional processing of the present invention.

  In that case, as long as it has the function of a program, it may be in the form of object code, a program executed by an interpreter, script data supplied to the OS, and the like.

  Examples of the recording medium for supplying the program include a flexible disk, hard disk, optical disk, magneto-optical disk, MO, CD-ROM, CD-R, and CD-RW. In addition, there are magnetic tape, nonvolatile memory card, ROM, DVD (DVD-ROM, DVD-R), and the like.

  As another program supply method, a browser on a client computer is used to connect to an Internet home page. The computer program itself of the present invention or a compressed file including an automatic installation function can be downloaded from the homepage by downloading it to a recording medium such as a hard disk.

  It can also be realized by dividing the program code constituting the program of the present invention into a plurality of files and downloading each file from a different homepage. That is, the present invention includes a WWW server that allows a plurality of users to download a program file for realizing the functional processing of the present invention on a computer.

  In addition, the program of the present invention is encrypted, stored in a storage medium such as a CD-ROM, distributed to users, and key information for decryption is downloaded from a homepage via the Internet to users who have cleared predetermined conditions. Let It is also possible to execute the encrypted program by using the downloaded key information and install the program on a computer.

  Further, the functions of the above-described embodiments are realized by the computer executing the read program. In addition, based on the instructions of the program, an OS or the like running on the computer performs part or all of the actual processing, and the functions of the above-described embodiments can also be realized by the processing.

  Further, the program read from the recording medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer. Thereafter, the CPU of the function expansion board or function expansion unit performs part or all of the actual processing based on the instructions of the program, and the functions of the above-described embodiments are realized by the processing.

  Note that each of the above-described embodiments is merely a specific example for carrying out the present invention, and the technical scope of the present invention should not be construed as being limited thereto. . That is, the present invention can be implemented in various forms without departing from the technical idea or the main features thereof.

1 is a schematic diagram illustrating an example of a schematic configuration of a medical diagnosis support system according to a first embodiment of the present invention. It is a flowchart which shows an example of the process sequence in the control method of the medical diagnosis assistance apparatus which concerns on the 1st Embodiment of this invention. It is a schematic diagram which shows an example of the list | wrist of the disease information used by step S106 of FIG. 6 is a flowchart showing an example of a processing procedure of past case accumulation processing for accumulating past cases in a case database in the medical diagnosis support apparatus according to the first embodiment of the present invention. An example of a data item when the gradation setting information and disease information and case data (image statistical data and clinical data) are associated with each other and stored in the case database for one case according to the first embodiment of the present invention. It is a schematic diagram which shows. It is a flowchart which shows an example of the detailed process sequence of the similarity determination process in FIG.2 S108. It is a schematic diagram which shows the example of presentation of the gradation process image (interpretation target image after a gradation process) according to the accuracy for every disease information in step S114 of FIG. It is a flowchart which shows an example of the process sequence in the control method of the medical diagnosis assistance apparatus which concerns on the 2nd Embodiment of this invention. It is a flowchart which shows an example of the process sequence in the control method of the medical diagnosis assistance apparatus which concerns on the 3rd Embodiment of this invention.

100 Medical Diagnosis Support Device 110 Control Unit 111 CPU (Central Processing Unit)
112 Main memory 113 Magnetic disk 114 Display memory 115 Bus 120 Monitor 130 Mouse 140 Keyboard 150 Case database 200 Medical imaging apparatus 300 Medical image database 400 Medical document database 500 LAN (local area network)

Claims (14)

A medical diagnosis support apparatus for supporting medical diagnosis using medical images,
Targeting the past case including the medical image for which a diagnosis of a disease has been made, the case data of the past case, the gradation setting information relating to the gradation setting appropriately performed for observing the disease state, and the Past case accumulation means for associating and accumulating disease information obtained by diagnosis,
Interpretation target case recognition means for performing processing for recognizing the case data of the interpretation target case including the medical image;
For each type of disease information, comparing the case data of the interpretation target case with the case data of the past case, similarity determination means for determining the similarity between the interpretation target case and the past case;
For each type of disease information, gradation processing for generating a gradation processed image by performing gradation processing on the interpretation target case using the gradation setting information based on the similarity determined by the similarity determination means Image generating means;
Accuracy calculation means for calculating the accuracy of disease information in the interpretation target case;
And a gradation processed image presenting means for performing a process of presenting the gradation processed image generated by the gradation processed image generating means according to the accuracy calculated by the accuracy calculating means. Support device.   The gradation processed image generation means generates the gradation processed image using the gradation setting information in the past case similar to the interpretation target case based on the similarity determined by the similarity determination means. The medical diagnosis support apparatus according to claim 1, wherein: The accuracy calculation means calculates the accuracy based on the similarity in the past case that is determined by the similarity determination means and is similar to the interpretation target case,
The medical diagnosis support apparatus according to claim 1, wherein the gradation processed image presenting unit presents the gradation processed images in descending order of the accuracy. The accuracy calculation means estimates one or more disease information that may be diagnosed as the interpretation target case, calculates the accuracy of the disease information,
The medical diagnosis support apparatus according to claim 1, wherein the gradation processed image presenting unit presents the gradation processed images in descending order of accuracy of the estimated disease information.   The medical diagnosis support apparatus according to claim 1, wherein the interpretation target case recognition unit automatically detects case data of the interpretation target case and recognizes the case data of the interpretation target case.   The medical diagnosis support apparatus according to claim 1, wherein the case data includes at least one of image statistical data, clinical data, and imaging parameters.   The gradation processing image generation means generates the gradation processing image by directly applying the gradation setting information in the past case similar to the interpretation target case when performing gradation processing on the interpretation target case. The medical diagnosis support apparatus according to claim 1, wherein:   The similarity determination unit compares the case data of the interpretation target case with the case data of the past case after gradation processing based on the gradation setting information, and determines the similarity The medical diagnosis support apparatus according to claim 1.   The gradation processing image generating means uses the gradation setting information in the past case similar to the interpretation target case and a reference value set in advance for each disease information to convert the interpretation target case into the gradation. The medical diagnosis support apparatus according to claim 1, wherein the medical diagnosis support apparatus performs processing.   The medical diagnosis support apparatus according to claim 1, wherein the gradation processed image presenting unit displays the gradation processed image as a list on an interpretation report for each disease information.   The gradation processed image presenting means displays the gradation processed image of the disease information with the highest accuracy on the medical image display area, and the gradation of the image area obtained by cutting out the diseased part from the medical image on another area. The medical diagnosis support apparatus according to claim 1, wherein the processed image is displayed as a list for each disease information.   The medical diagnosis support apparatus according to claim 1, wherein the gradation processed image presenting unit displays the gradation processed image as a moving image. A method for controlling a medical diagnosis support apparatus for supporting medical diagnosis using medical images, comprising:
Targeting the past case including the medical image for which a diagnosis of a disease has been made, the case data of the past case, the gradation setting information relating to the gradation setting appropriately performed for observing the disease state, and the Past case accumulation step of accumulating in association with disease information obtained by diagnosis,
An interpretation target case recognition step for performing a process of recognizing case data of an interpretation target case including the medical image;
For each type of disease information, comparing the case data of the interpretation target case with the case data of the past case, a similarity determination step for determining the similarity between the interpretation target case and the past case;
For each type of disease information, gradation processing for generating a gradation processed image by gradation processing the interpretation target case using the gradation setting information based on the similarity determined in the similarity determination step An image generation step;
An accuracy calculation step of calculating the accuracy of the disease information in the interpretation target case;
A gradation processed image presenting step for performing a process of presenting the gradation processed image generated in the gradation processed image generating step according to the accuracy calculated in the accuracy calculating step. Control method of support device. A program for causing a computer to execute a control method of a medical diagnosis support apparatus that supports medical diagnosis using a medical image,
Targeting the past case including the medical image for which a diagnosis of a disease has been made, the case data of the past case, the gradation setting information relating to the gradation setting appropriately performed for observing the disease state, and the Past case accumulation step of accumulating in association with disease information obtained by diagnosis,
An interpretation target case recognition step for performing a process of recognizing case data of an interpretation target case including the medical image;
For each type of disease information, comparing the case data of the interpretation target case with the case data of the past case, a similarity determination step for determining the similarity between the interpretation target case and the past case;
For each type of disease information, gradation processing for generating a gradation processed image by gradation processing the interpretation target case using the gradation setting information based on the similarity determined in the similarity determination step An image generation step;
An accuracy calculation step of calculating the accuracy of the disease information in the interpretation target case;
A gradation processing image presenting step for causing a computer to execute a gradation processing image presenting step for performing a process of presenting the gradation processing image generated in the gradation processing image generation step according to the accuracy calculated in the accuracy calculation step.

Images