JP2021176424A - Medical diagnosis support device, medical diagnosis support program and medical diagnosis support method - Google Patents

Abstract

To provide a medical diagnosis support device for accurately estimating an onset risk of a disease of an individual object person.SOLUTION: A medical diagnosis support device 100 comprises: an acquisition unit which acquires difference information about two or more pieces of medical treatment relevant information acquired for the same object person at different timings; an estimation unit which receives the input of the difference information acquired by the acquisition unit by using a discriminator that has learned and estimates information about an onset risk of a disease of the object person at a specific time point; and a control unit which causes an output unit to output the information about the onset risk estimated by the estimation unit.SELECTED DRAWING: Figure 4

Description

The present invention relates to a medical diagnosis support device, a medical diagnosis support program, and a medical diagnosis support method.

In tests for detecting diseases such as breast cancer, tests are generally performed on a population by a standardized program. In such tests, a uniform test is performed regardless of the level of risk of developing the disease in the individual subject, which may delay the early detection of the disease.

In relation to such problems, in recent years, as a technique for estimating the risk of developing a disease of an individual subject by analyzing information such as images obtained by photographing the subject, the following patents have been granted. Techniques as shown in Document 1 and Non-Patent Document 1 have also been proposed.

Japanese Patent Application Laid-Open No. 2007-524461

Adam Yala et al. , Radiology Vol. 292, No. 1, A Deep Learning Mammography-based Model for Improved Breast Cancer Risk Prediction, URL: https: // pubs. rsna. org / doi / 10.1148 / radio. 2019182716

However, in the above-mentioned prior art, the onset risk and the like are estimated based on the information acquired from the subject at a certain single timing, and there is a problem that the estimation accuracy is low.

The present invention has been made in view of the above circumstances, and provides a medical diagnosis support device, a medical diagnosis support program, and a medical diagnosis support method for accurately estimating the risk of developing a disease of an individual subject. The purpose.

The above object of the present invention is achieved by the following means.

(1) The difference acquired by the acquisition unit using a learning unit and an acquisition unit that acquires difference information regarding two or more medical-related information acquired for the same subject at different timings. It has an estimation unit that receives information as input and estimates information on the onset risk of the subject's disease at a specific time point, and a control unit that outputs information on the onset risk estimated by the estimation unit to an output unit. Medical diagnosis support device.

(2) The medical diagnosis support device according to (1) above, wherein the medical-related information includes medical image information related to a medical image acquired by photographing the subject.

(3) The medical diagnosis support device according to (2) above, wherein the medical image is an image acquired by at least one of an X-ray imaging device, an ultrasonic imaging device, MRI, and PET.

(4) The medical diagnosis support device according to any one of (1) to (3) above, wherein the medical-related information includes non-medical image information which is information related to medical treatment other than the medical image acquired for the subject.

(5) The medical diagnosis support device according to (4) above, wherein the non-medical image information includes information on at least one of the subject's EHR, PHR, and the result of a biological test.

(6) Any of the above (1) to (5), wherein the two or more medical-related information acquired at different timings includes two or more medical-related information acquired by different devices. The medical diagnosis support device described in.

(7) The medical diagnosis support device according to any one of (1) to (6) above, wherein the estimation unit estimates information on the risk of developing breast cancer as the risk of developing the disease.

(8) Any of the above (1) to (7), in which the estimation unit estimates at least one of the presence or absence of the onset of the disease and the onset probability of the subject at a specific time point as the onset risk of the subject. Medical diagnosis support device described in Crab.

(9) The medical diagnosis support device according to any one of (1) to (8) above, wherein the control unit outputs the consultation time of the examination related to the disease to the output unit according to the onset risk.

(10) The medical diagnosis according to any one of (1) to (9) above, wherein the control unit outputs at least one of a test item related to the disease and information related to life improvement to the output unit according to the risk of developing the disease. Support device.

(11) The estimation unit uses the medical-related information as an input to the discriminator in addition to the difference information to estimate information on the onset risk in any of the above (1) to (10). The described medical diagnosis support device.

(12) The discriminator uses the difference information of the two or more medical-related information about the same subject acquired at different timings as input data, and uses the information regarding the onset risk at a specific time point of the subject as input data. The medical diagnosis support device according to any one of (1) to (11) above, which is machine-learned as output data.

(13) The classifier is machine-learned using the difference information and the medical-related information as input data and information on the onset risk at a specific time point of the subject as output data (1) to (12). The medical diagnosis support device described in any of the above.

(14) A step (a) of acquiring difference information of two or more medical-related information about the same subject acquired at different timings, and an acquisition in the step (a) using a trained classifier. A step (b) of estimating the information on the onset risk of the subject's disease at a specific time point and a step of outputting the information on the onset risk estimated in the step (b) by inputting the difference information. (C) A medical diagnosis support program for causing a computer to execute a process having the above.

(15)
The step (a) of acquiring the difference information of two or more medical-related information about the same subject acquired at different timings, and the step (a) acquired in the step (a) using the learned classifier. A step (b) of estimating the information on the onset risk of the subject's disease at a specific time point by inputting the difference information, and a step (c) of outputting the information on the onset risk estimated in the step (b). And has a medical diagnosis support method.

The medical diagnosis support device according to the present invention uses an acquisition unit that acquires difference information regarding two or more medical-related information acquired for the same subject at different timings, and an acquisition unit that uses a learned classifier. An estimation unit that estimates the information on the onset risk of the subject's disease at a specific time point by inputting the difference information acquired by the estimation unit, and a control unit that outputs the information on the onset risk estimated by the estimation unit to the output unit. Have. Thereby, based on the information acquired about the individual subject, the risk of developing the disease of the individual subject can be accurately estimated and output.

It is a figure which shows the whole structure of a medical diagnosis support system. It is a block diagram which shows the schematic structure of an information processing apparatus. It is a block diagram which shows the functional structure of an information processing apparatus. It is a flowchart which shows the procedure of the medical diagnosis support processing executed in an information processing apparatus. It is a figure which shows an example of the display form of the information output by an information processing apparatus. It is a figure which shows another example of the display form of the information output by an information processing apparatus. It is a figure which shows another example of the display form of the information output by an information processing apparatus. It is a figure which shows another example of the display form of the information output by an information processing apparatus. It is a figure which shows another example of the display form of the information output by an information processing apparatus. It is a flowchart which shows the machine learning method of a trained model. It is a flowchart which shows the procedure of the medical diagnosis support processing executed in the information processing apparatus which concerns on modification 1. FIG. It is a flowchart which shows the procedure of the medical diagnosis support processing which is executed in the information processing apparatus which concerns on modification 2.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the description of the drawings, the same elements are designated by the same reference numerals, and duplicate description will be omitted. In addition, the dimensional ratios in the drawings are exaggerated for convenience of explanation and may differ from the actual ratios.

<Overall configuration>
FIG. 1 is a diagram showing an overall configuration of a medical diagnosis support system.

As shown in FIG. 1, the medical diagnosis support system includes an information processing device 100, an imaging device 200, and a server 300.

The information processing device 100 is, for example, a computer such as a PC, a smartphone, or a tablet terminal, and functions as a medical information support device in the present embodiment. The information processing device 100 is configured to be connectable to the photographing device 200 and the server 300, and transmits and receives various information to and from each device.

The imaging device 200 is a device for acquiring medical image information indicating a medical image of a subject. As the imaging device 200, for example, an X-ray imaging device, an ultrasonic imaging device, an MRI (Magnetic Resonance Imaging), a PET (Positron Emission Tomography), or the like is used. The X-ray imaging device includes a mammography or tomosynthesis imaging device, a simple X-ray or CT (Computed Tomography) imaging device, and the like.

The server 300 is a device for acquiring and storing non-medical image information which is medical information other than the medical image acquired for the subject. As non-medical image information, for example, EHR (Electronic Health Record: electronic health record), PHR (Personal Health Record: personal health record) of the subject, information on the results of various biological tests, and the like are recorded. In addition to the non-medical image information, the server 300 may acquire and store the medical image information acquired by the imaging device 200 from the imaging device 200.

<Configuration of information processing device 100>
FIG. 2 is a block diagram showing a schematic configuration of an information processing device.

As shown in FIG. 2, the information processing device 100 includes a CPU (Central Processing Unit) 110, a ROM (Read Only Memory) 120, a RAM (Random Access Memory) 130, a storage 140, a communication interface 150, a display unit 160, and an operation. It has a reception unit 170. Each configuration is communicably connected to each other via bus 180.

The CPU 110 controls each of the above configurations and performs various arithmetic processes according to the programs recorded in the ROM 120 and the storage 140.

The ROM 120 stores various programs and various data.

The RAM 130 temporarily stores programs and data as a work area.

The storage 140 stores various programs including an operating system and various data. For example, in the storage 140, an application for estimating information on the risk of developing a disease of a subject from the difference information of two or more medical-related information acquired at different timings is installed using a learned discriminator. Has been done. Further, the storage 140 may store the medical image information acquired from the photographing apparatus 200 and the non-medical image information acquired from the server 300. Further, the storage 140 may store a trained model used as a discriminator and teacher data used for machine learning. Medical image information and non-medical image information constitute medical-related information. Details of medical information will be described later.

The communication interface 150 is an interface for communicating with another device. As the communication interface 150, a communication interface according to various wired or wireless standards is used. The communication interface 150 is used, for example, when receiving medical information from the imaging device 200 or the server 300, or transmitting the estimation result to the server 300 or the like for storage.

The display unit 160 includes an LCD (liquid crystal display), an organic EL display, and the like, and displays various information. In the present embodiment, the display unit 160 functions as an output unit.

The operation reception unit 170 is provided with a touch sensor, a pointing device such as a mouse, a keyboard, and the like, and accepts various user operations. The display unit 160 and the operation reception unit 170 may form a touch panel by superimposing a touch sensor as the operation reception unit 170 on the display surface as the display unit 160.

<Functions of information processing device 100>
FIG. 3 is a block diagram showing a functional configuration of the information processing apparatus.

As shown in FIG. 3, the information processing apparatus 100 functions as the acquisition unit 111, the estimation unit 112, and the control unit 113 by the CPU 110 reading the program stored in the storage 140 and executing the process.

The acquisition unit 111 acquires the difference information regarding two or more medical-related information acquired for the same subject at different timings.

The estimation unit 112 uses the learned classifier to input the difference information acquired by the acquisition unit, and estimates information regarding the risk of developing the disease of the subject at a specific time point.

The control unit 113 causes the output unit to output information on the onset risk estimated by the estimation unit.

Details of the processing executed by the information processing apparatus 100 will be described later.

<About medical information>
Medical-related information includes medical image information and non-medical image information.

The medical image information is information indicating an image obtained by photographing a subject with, for example, an X-ray imaging device, an ultrasonic imaging device, MRI, PET, or the like. The medical image information acquired by the X-ray imaging apparatus includes a mammography image, a tomosynthesis image, a simple X-ray image, a CT image, and the like.

Non-medical image information includes EHR / PHR information of the subject and information on the results of various biological tests.

EHR / PHR information includes, for example, in the case of breast cancer, cancer family history and affected age, ovarian cancer family history and affected age, age, weight, height, birth history, first child birth age, menstrual status, menopause age, first menstrual Includes information on age, history of benign breast disease, history of ovarian cancer and age of illness. In the case of lung cancer, the EHR / PHR information includes information on gender, cancer family history, smoking history, smoking amount, medical history, and the like. In the case of a brain tumor, the EHR / PHR information includes information on age, family history of cancer, medical history (virus infection), treatment history for the scalp and brain, and the like.

Information on the results of biological tests is information indicating test results such as blood tests and biological tests. Biological tests include, for example, tumor marker tests, amino acid tests, genetic analysis and the like. Gene analysis is performed by, for example, microarray analysis, polymerase chain reaction (PCR), gene (DNA / RNA) sequence analysis, etc., for gene pathway activity (gene passway activation), non-coding RNA (noncoding RNA), and multiple RNAs (multiple RNAs). ), Single nucleotide polymorphism, epigenetic polymorphism, and the like.

<Outline of processing>
<About estimation processing>
FIG. 4 is a flowchart showing a procedure of estimation processing executed in the information processing apparatus. FIG. 5 is a diagram showing an example of a display form of information output by the information processing device. 6 to 9 are diagrams showing another example of the display form of the information output by the information processing apparatus. The process of the information processing device 100 shown in the flowchart of FIG. 4 is stored as a program in the storage 140 of the information processing device 100, and is executed by the CPU 110 controlling each unit.

(Step S101)
The information processing apparatus 100 acquires medical image information indicating two or more medical images acquired for the same subject at different timings. For example, the information processing apparatus 100 captures the same subject as the medical image information obtained by photographing the subject at a certain time in the past, such as one year ago or two years ago, at the time of executing this process. Acquire the medical image information obtained in the above. Alternatively, the information processing device 100 obtains two or more medical image information acquired at different timings of several seconds or several minutes by different imaging devices 200 (different modality) such as a mammography imaging device and an ultrasonic imaging device. You may get it.

(Step S102)
The information processing apparatus 100 calculates the difference between the two or more medical image information acquired in the process of step S101 and acquires the difference information. For example, the information processing apparatus 100 may specify pixels corresponding to the same portion of the body of the target person for each of the two medical image information and calculate the difference in pixel values between the pixels. Alternatively, the information processing apparatus 100 may acquire a difference in the image information in the region of interest corresponding to the specific region in the body of the subject. Further, the information processing apparatus 100 extracts the feature amounts related to the shape, size, position, density, density, texture, etc. of the medical image information or the image information in the above-mentioned area of interest, and calculates the difference between the feature amounts. May be good. The medical image information acquisition process in step S101 and the difference calculation process in step S102 may be executed by an apparatus other than the information processing apparatus 100. In this case, the information processing device 100 acquires the difference information calculated and generated by the other device.

(Step S103)
The information processing apparatus 100 inputs the difference information acquired in the process of step S102 into a pre-machine-learned classifier to estimate information on the risk of developing a disease of the subject at a specific time point. For example, the discriminator uses a learning method as described later to obtain difference information on a plurality of medical images of past subjects prepared in advance at different timings and one year after the latest medical images are acquired. Machine learning is performed using teacher data having information on whether or not the subject has developed cancer at a specific time point such as 3 years or 5 years later. As a result, the information processing apparatus 100 inputs the difference information acquired about the medical image of the subject into the classifier, so that the disease of the subject at a specific time point such as 1 year, 3 years, 5 years, etc. It is possible to estimate the presence or absence of the onset or the probability of the onset of.

For example, when estimating the risk of developing breast cancer, a medical image of the subject's breast is placed in a discriminator machine-learned by a large number of teacher data having differential information about the medical image of the breast and the presence or absence of breast cancer at a specific time point. By entering the differential information about, the risk of developing breast cancer in the subject at a specific time point can be estimated.

The information input to the classifier is not limited to the difference information, and in addition to the difference information, medical image information and various feature quantities extracted from the medical image information are also input to the classifier for learning and estimation. It may be used as information of. Further, as medical-related information, in addition to medical image information, non-medical image information and difference information of non-medical image information may be used as information for inputting to a classifier for learning and estimation.

(Step S104)
The information processing apparatus 100 generates an estimation result of information regarding the risk of developing a disease of the subject based on the output by the discriminator in the process of step S103.

(Step S105)
The information processing device 100 outputs the estimation result generated in the process of step S104. For example, the information processing apparatus 100 outputs an estimation result by displaying a screen as shown in FIGS. 5 to 9 on the display unit 160 (end).

For example, as shown in FIG. 5, the information processing apparatus 100 may display a screen showing the onset probability of a disease for each region of the body of the subject as a heat map on the estimation result display unit 161. In the example shown in FIG. 5, on the medical image of the subject, the region having a higher probability of developing the disease is represented so as to have a darker color. As a result, medical staff such as doctors can easily visually recognize the site having a high probability of developing a disease at a glance. The thumbnail display unit 162 at the bottom of the screen of FIG. 5 can display a list of medical images of the subject at each timing as thumbnails (reduced images) in the order of time series or the like. Each thumbnail can be magnified by being selected. As a result, medical staff such as doctors can easily confirm the past state and the transition of the state such as the area where the probability of developing the disease is high. The display of the thumbnail display unit 162 is the same on the screens of FIGS. 6 to 9 below.

Further, as shown in FIG. 6, the information processing apparatus 100 arranges the identifiable figure 163 in the region where the probability of developing the disease is high in the body of the subject, and displays the medical image of the subject on the estimation result display unit 161. In addition to displaying, texts such as a specific numerical value of the onset probability may be associated and displayed. As a result, medical staff such as doctors can easily visually recognize the site having a high probability of developing a disease at a glance, and can also confirm detailed information such as a specific probability of developing the disease.

Further, as shown in FIG. 7, the information processing apparatus 100 arranges the identifiable figure 163 in the region where the probability of developing a disease is high in the body of the subject, and displays the medical image of the subject on the estimation result display unit 161. In addition to the display, information indicating the onset risk and the onset probability may be displayed on the explanatory display unit 164 provided side by side. As a result, medical staff such as doctors can confirm the medical image while grasping the onset risk and the onset probability of the disease of the subject.

Further, as shown in FIG. 8, the information processing apparatus 100 may display the past medical image and the current medical image of the subject on the estimation result display unit 161 side by side so as to be comparable. In this case, the information processing apparatus 100 displays information on the onset risk of the disease estimated at that time in association with the past medical image, and the current medical image of the portion estimated to have a high onset risk of the disease. Also, an identifiable figure 163 may be displayed so that the onset status of the lesion or the like can be easily confirmed. As a result, medical staff such as doctors can quickly and easily grasp the current situation of places where the risk of developing a disease is estimated to be high in the past.

Further, as shown in FIG. 9, the information processing apparatus 100 may display information indicating the onset risk and the onset probability of the subject at a specific time point on the estimation result display unit 161 as a time-series graph. As a result, medical staff such as doctors can quickly and easily visually grasp the time-dependent changes in the onset risk and the onset probability of the disease of the subject.

The information processing device 100 transmits information on the risk of developing a disease to another device such as the server 300 via the communication interface 150 instead of displaying the information on the display unit 160 as a screen as shown in FIGS. 5 to 9. It may be output by doing. Alternatively, the information processing apparatus 100 may output information regarding the risk of developing a disease by transmitting it to a printer and printing it. In the above case, the communication interface 150 functions as an output unit.

In addition, the information processing device 100 may output the consultation time of the examination related to the disease according to the estimated risk of developing the disease. For example, the information processing apparatus 100 proposes to a subject who is presumed to have a high risk of developing a disease to undergo a normal group examination at a time or earlier than the age of the examination, or to undergo a normal group examination. It is possible to propose a consultation in a cycle shorter than the cycle. Alternatively, the information processing apparatus 100 may store a threshold value related to the onset probability of the disease in the storage 140 in advance, and present a time point at which the estimated onset probability of the disease exceeds the above threshold value as a consultation time for the examination related to the disease. good.

In addition, the information processing device 100 may output test items related to the disease and information related to life improvement according to the estimated risk of developing the disease. For example, the information processing apparatus 100 undergoes a more detailed examination such as a genetic examination, an ultrasonic examination, or an MRI examination, which is not performed by a normal mass examination, for a subject who is estimated to have a high risk of developing a disease. You may suggest that. Alternatively, the information processing device 100 stores a threshold value related to the onset probability of the disease in the storage 140 in advance, and when the estimated onset probability of the disease exceeds the above threshold value, the subject receives a more detailed examination. You may propose to.

In addition, the information processing device 100 reduces the amount of drinking, quits smoking, and exercises appropriately for a subject who is presumed to have a high risk of developing a disease, depending on the content of the disease and the degree of risk. Information on life improvement such as things may be presented. Alternatively, the information processing apparatus 100 stores a threshold value related to the onset probability of the disease in the storage 140 in advance, and is considered to be effective for preventing the disease when the estimated onset probability of the disease exceeds the above threshold value. The subject may be provided with advice on lifestyle improvement such as eating, sleeping, exercising, abstinence from drinking, and quitting.

In addition, the information processing device 100 may output an instruction to increase the number of doctors and the like who are in charge of interpreting medical images of the subject who is presumed to have a high risk of developing a disease.

Further, the information processing apparatus 100 stores in advance the skill level of the doctor in charge of image interpretation, and has a high skill level in interpreting the medical image of the subject who is estimated to have a high risk of developing a disease. You may output the instruction to ask the doctor automatically. Alternatively, the information processing apparatus 100 may automatically determine the doctor in charge of interpreting the medical image of the subject based on the estimated risk of developing the disease and the skill level of the doctor in charge of interpretation. ..

<About learning process>
Next, the machine learning method of the trained model used in the classifier will be described.

FIG. 10 is a flowchart showing a machine learning method of the trained model.

In the processing of FIG. 10, the difference information of two or more medical-related information prepared in advance is input, and the information regarding the risk of developing the disease of the subject at a specific time point set as the correct answer is output. Machine learning is executed using a data set of i sets (i is, for example, thousands to hundreds of thousands) as training sample data. As the learner (not shown) that functions as a discriminator, for example, a stand-alone high-performance computer using a CPU and GPU processor, or a cloud computer is used. In the following, a learning method using a neural network configured by combining perceptrons such as deep learning in a learning device will be described, but the learning method is not limited to this, and various methods can be applied. For example, random forest, decision tree, support vector machine (SVM), logistic regression, k-nearest neighbor method, topic model, etc. may be applied.

(Step S111)
The learner reads the learning sample data which is the teacher data. If it is the first time, the first set of training sample data is read, and if it is the i-th time, the i-th set of training sample data is read.

(Step S112)
The learner inputs the input data of the read learning sample data to the neural network.

(Step S113)
The learner compares the estimation result of the neural network with the correct answer data.

(Step S114)
The learner adjusts the parameters based on the comparison result. The learner adjusts the parameters so that the difference in the comparison results is small, for example, by executing a process based on backpropagation (backpropagation, error backpropagation method).

(Step S115)
If the processing of all the data from the 1st to the i-th group is completed (YES), the learning device advances the processing to step S116, and if it is not completed (NO), the learning device returns the processing to step S111 and the next learning sample data. Is read, and the process of step S111 and subsequent steps is repeated.

(Step S116)
The learner determines whether or not to continue learning, and if it continues (YES), returns the process to step S111, executes the processes from the first group to the i-group again in steps S111 to S115, and continues. If not (NO), the process proceeds to step S117.

(Step S117)
The learner memorizes the trained model built by the processing so far and ends (end). The storage destination includes the internal memory of the information processing device 100. In the process of FIG. 4 described above, the risk of developing a disease is estimated using the trained model thus generated.

<Modification example 1>
As a modification 1, a specific example will be described in which non-medical image information is input to the classifier in addition to the difference information of the medical image information to estimate the risk of onset.

FIG. 11 is a flowchart showing a procedure of medical diagnosis support processing executed in the information processing apparatus according to the first modification.

(Steps S201, S202)
Since the processing of steps S201 and S202 is the same as the processing of steps S101 and S102 of FIG. 4, duplicate description will be omitted.

(Step S203)
The information processing device 100 acquires non-medical image information about the same target person who has acquired the medical image from the server 300.

(Step S204)
The information processing device 100 inputs the difference information of the medical image information acquired in the process of step S202 and the non-medical image information acquired in the process of step S203 into a pre-machine-learned classifier to specify the information processing device 100. Estimate information about the subject's risk of developing the disease at that time. The classifier is machine-learned in advance using a large number of teacher data having differential information of medical image information and non-medical image information, and information on the risk of developing a disease at a specific time point.

(Steps S205 and S206)
Since the processing of steps S205 and S206 is the same as the processing of steps S104 and S105 of FIG. 4, duplicate description will be omitted.

<Modification 2>
As a second modification, an example in which the difference information of the non-medical image information and the medical image information are input to the classifier to estimate the onset risk will be specifically described.

FIG. 12 is a flowchart showing a procedure of medical diagnosis support processing executed in the information processing apparatus according to the second modification.

(Step S301)
The information processing device 100 acquires two or more non-medical image information acquired for the same subject at different timings. For example, the information processing apparatus 100 is obtained for various non-medical image information obtained for a subject at a certain time in the past, such as one year ago or two years ago, and for the same subject at the time of executing this process. Acquire various non-medical image information.

(Step S302)
The information processing apparatus 100 calculates the difference regarding two or more non-medical image information acquired in the process of step S301 and acquires the difference information. For example, the information processing apparatus 100 may specify the same item for each of the two non-medical image information and calculate the difference between the values of the same item. Alternatively, the information processing apparatus 100 may acquire a difference for the value of a specific item for which the onset risk is to be estimated. Further, the information processing apparatus 100 may extract the feature amount of the non-medical image information by using a predetermined method and calculate the difference between the feature amounts. The non-medical image information acquisition process in step S301 and the difference calculation process in step S302 may be executed by an apparatus other than the information processing apparatus 100. In this case, the information processing device 100 acquires the difference information calculated and generated by the other device.

(Step S303)
Since the process of step S303 is the same as the process of step S101 of FIG. 4, a duplicate description will be omitted.

(Step S304)
The information processing device 100 inputs the difference information of the non-medical image information acquired in the process of step S302 and the medical image information acquired in the process of step S303 into a pre-machine-learned classifier to specify the information processing device 100. Estimate information about the subject's risk of developing the disease at that time. The classifier is machine-learned in advance using a large number of teacher data having difference information of non-medical image information, medical image information, and information on the risk of developing a disease at a specific time point.

(Steps S305, S306)
Since the processes of steps S305 and S306 are the same as the processes of steps S104 and S105 of FIG. 4, redundant description will be omitted.

As described above, according to the information processing apparatus 100, the difference information regarding two or more medical-related information acquired for the same subject at different timings is acquired, and the difference information is input to the learned classifier. By doing so, information on the risk of developing the disease of the subject at a specific time point is estimated and output. Thereby, based on the information acquired about the individual subject, the risk of developing the disease of the individual subject can be accurately estimated and output. More specifically, by using the difference information of the medical-related information of the subject acquired at a plurality of timings, it is possible to consider the information regarding the change over time of the subject. As a result, it is possible to improve the prediction accuracy of information on the development or regression of a region of interest for which the risk of developing a disease is estimated, for example, the development or regression of the mammary gland, and it is possible to improve the prediction accuracy of the risk of developing a disease.

In addition, the medical-related information includes medical image information related to the medical image obtained by photographing the subject. This makes it possible to estimate the risk of developing a disease with higher accuracy by using the difference information of the medical image information.

The medical image is an image acquired by at least one of an X-ray imaging apparatus, an ultrasonic imaging apparatus, MRI, and PET. As a result, the risk of developing the disease can be estimated using appropriate medical images according to the type and site of the disease to be diagnosed.

In addition, the medical-related information includes non-medical image information which is information related to medical treatment other than the medical image acquired for the subject. As a result, information from various viewpoints regarding the medical treatment of the subject can be considered from various aspects, so that the risk of developing the disease can be estimated with higher accuracy.

Non-medical imaging information also includes information about at least one of the subject's EHR, PHR, and biological test results. As a result, information such as the subject's EHR, PHR, and the results of biological tests can be taken into consideration, so that the risk of developing a disease can be estimated with higher accuracy.

Further, the two or more medical-related information acquired at different timings includes two or more medical-related information acquired by different devices. As a result, the difference between the medical-related information acquired by different devices can be taken into consideration, so that the risk of developing the disease can be estimated with higher accuracy.

In addition, the information processing device 100 estimates information on the risk of developing breast cancer as the risk of developing the disease. As a result, the risk of developing breast cancer, for which early detection is important, can be estimated with higher accuracy, and appropriate measures can be taken according to the risk of developing breast cancer.

In addition, the information processing device 100 estimates at least one of the presence or absence of the onset of the disease and the onset probability of the subject at a specific time point as the risk of developing the disease. As a result, the presence or absence of the onset of the disease and the probability of the onset of the disease at a specific time in the future can be estimated, so that appropriate measures for prevention and early detection of the disease can be systematically promoted.

In addition, the information processing device 100 outputs the consultation time of the examination related to the disease according to the risk of developing the disease. As a result, it is possible to determine the appropriate time to receive the test according to the risk of developing the disease for each individual subject, so that the test can be performed more appropriately and effectively than the conventional group test.

In addition, the information processing device 100 outputs at least one of a test item related to the disease and information related to life improvement according to the risk of developing the disease. As a result, it is possible to determine appropriate test items and promote life improvement according to the risk of developing a disease for each individual subject.

Further, the information processing apparatus 100 uses the medical-related information as an input to the discriminator in addition to the difference information to estimate the information regarding the onset risk. Since medical image information and non-medical image information itself are used as inputs in addition to the difference information, the risk of developing a disease can be estimated with higher accuracy.

The present invention is not limited to the above-described embodiments and modifications, and various modifications can be made within the scope of the claims.

For example, the information processing device 100, the photographing device 200, and the server 300 may each include components other than the above-mentioned components, or even if some of the above-mentioned components are not included. good.

Further, the information processing device 100, the photographing device 200, and the server 300 may each be configured by a plurality of devices, or may be configured by a single device.

Further, the functions of each configuration may be realized by other configurations. For example, the photographing device 200 and the server 300 may be integrated into the information processing device 100, and a part or all of the functions of the photographing device 200 and the server 300 may be realized by the information processing device 100.

Further, the processing unit of the flowchart in the above embodiment is divided according to the main processing contents in order to facilitate understanding of each processing. The invention of the present application is not limited by the method of classifying the processing steps. Each process can be divided into more processing steps. Also, one processing step may perform more processing.

The means and methods for performing various processes in the system according to the above-described embodiment can be realized by either a dedicated hardware circuit or a programmed computer. The program may be provided, for example, by a computer-readable recording medium such as a flexible disk and a CD-ROM, or may be provided online via a network such as the Internet. In this case, the program recorded on the computer-readable recording medium is usually transferred and stored in a storage unit such as a hard disk. Further, the above program may be provided as a single application software, or may be incorporated into the software of the device as a function of the system.

100 information processing device,
110 CPU,
111 acquisition part,
112 estimation part,
113 Control unit,
120 ROM,
130 RAM,
140 storage,
150 communication interface,
160 display section,
170 Operation reception department,
200 shooting equipment,
300 servers.

Claims (15)

An acquisition unit that acquires difference information about two or more medical-related information acquired for the same subject at different timings, and an acquisition unit.
Using the learned classifier, the difference information acquired by the acquisition unit is input, and the estimation unit that estimates information on the risk of developing the disease of the subject at a specific time point, and the estimation unit.
A control unit that outputs information on the onset risk estimated by the estimation unit to the output unit,
Medical diagnosis support device with. The medical diagnosis support device according to claim 1, wherein the medical-related information includes medical image information relating to a medical image obtained by photographing the subject. The medical diagnosis support device according to claim 2, wherein the medical image is an image acquired by at least one of an X-ray imaging device, an ultrasonic imaging device, MRI, and PET. The medical diagnosis support device according to any one of claims 1 to 3, wherein the medical-related information includes non-medical image information that is medical information other than the medical image acquired for the subject. The medical diagnostic support device according to claim 4, wherein the non-medical image information includes information on at least one of the subject's EHR, PHR, and biological test results. The medical diagnosis support according to any one of claims 1 to 5, wherein the two or more medical-related information acquired at different timings includes two or more medical-related information acquired by different devices. Device. The medical diagnosis support device according to any one of claims 1 to 6, wherein the estimation unit estimates information on the onset risk of breast cancer as the onset risk of the disease. The medical diagnosis according to any one of claims 1 to 7, wherein the estimation unit estimates at least one of the presence or absence of the onset of the disease and the onset probability of the subject at a specific time point as the onset risk of the subject. Support device. The medical diagnosis support device according to any one of claims 1 to 8, wherein the control unit outputs the consultation time of the examination related to the disease to the output unit according to the onset risk. The medical diagnosis support device according to any one of claims 1 to 9, wherein the control unit outputs at least one of a test item related to the disease and information related to life improvement to the output unit according to the onset risk. The medical diagnosis support device according to any one of claims 1 to 10, wherein the estimation unit uses the medical-related information as an input to the classifier in addition to the difference information to estimate information on the onset risk. .. The discriminator uses the difference information of the two or more medical-related information about the same subject acquired at different timings as input data, and the information about the onset risk at a specific time point of the subject as output data. The medical diagnosis support device according to any one of claims 1 to 11, which is machine-learned. 13. Medical diagnosis support device. Step (a) of acquiring the difference information of two or more medical-related information about the same subject acquired at different timings, and
Using the trained classifier, the difference information acquired in the step (a) is input, and the step (b) of estimating the information on the risk of developing the disease of the subject at a specific time point and the step (b).
In step (c), which outputs information regarding the onset risk estimated in step (b),
A medical diagnosis support program that allows a computer to perform processing with. Step (a) of acquiring the difference information of two or more medical-related information about the same subject acquired at different timings, and
Using the trained classifier, the difference information acquired in the step (a) is input, and the step (b) of estimating the information on the risk of developing the disease of the subject at a specific time point and the step (b).
In step (c), which outputs information regarding the onset risk estimated in step (b),
Medical diagnosis support method with.

Images