Information processing apparatus, information processing method, information processing system, and program
An information processing apparatus disclosed in the present specification includes: estimation means for estimating a subject's risk of developing a disease using a learned model that has learned a relationship between a feature obtained from a fundus image and a risk of developing the disease, which is evaluated from the feature; and correction means for correcting the estimated risk of developing the disease based on the subject's biological information.
1 . An information processing apparatus comprising:
obtaining means for obtaining a subject's medical image;
estimation means for estimating the subject's risk of developing a disease (a) by inputting, as input data, a feature obtained from the obtained medical image to a learned model that has learned a relationship between a feature obtained from a medical image and a risk of developing the disease or (b) by inputting, as input data, the obtained-fundus medical image to a learned model that has deep-learned a relationship between a medical image and a risk of developing the disease; and
correction means for correcting the estimated risk of developing the disease using a weight coefficient of the probability of developing each disease, the weight coefficient being set in advance for each item of the subject's biological information.
2 . The information processing apparatus according to claim 1 , wherein the estimation means estimates the subject's risk of developing a first disease and a second disease using a learned model that has learned a relationship between a feature obtained from the medical image and a risk of developing the first disease, which is evaluated from the feature, and a relationship between a feature obtained from the medical image and a risk of developing the second disease, which is evaluated from the feature.
3 . The information processing apparatus according to claim 1 , wherein the estimation means estimates the subject's risk of developing a first disease and a second disease using a first learned model that has learned a relationship between a feature obtained from the medical image and a risk of developing the first disease, which is evaluated from the feature, and a second learned model that has learned a relationship between a feature obtained from the medical image and a risk of developing the second disease, which is evaluated from the feature.
4 . The information processing apparatus according to claim 1 , wherein the estimation means estimates a probability as the subject's risk of developing the disease by inputting a feature obtained from the subject's medical image to the learned model.
5 . The information processing apparatus according to claim 1 , wherein:
the learned model learns a relationship between vascular morphology obtained from the medical image and a risk of developing cardiovascular disease, which is evaluated from the vascular morphology,
the correction means performs correction using at least one type of biological information among the subject's blood pressure, body-mass index (BMI), age, sex, medical history, or smoking habit, and
the vascular morphology includes at least one of features indicating an artery diameter, vein diameter, ratio of the artery diameter and the vein diameter, vascular bifurcation angle, asymmetry of the bifurcation, arterial vein stenosis, or vascular twisting.
6 . The information processing apparatus according to claim 1 , further comprising display control means for displaying the corrected risk of developing the disease on a display unit,
wherein the display control means displays, on the display unit, at least one of (a) the corrected risk of developing the disease, which is classified in one of a plurality of classes, (b) the corrected risk of developing the disease in parallel with the subject's medical image, (c) a graph based on a probability corresponding to the corrected risk of developing the disease, or (d) the subject's medical image, a part of which highly correlated with the disease being emphasized.
7 . The information processing apparatus according to claim 1 , further comprising display control means for displaying the corrected risk of developing the disease on a display unit,
wherein the display control means displays a recommended medical institution in accordance with the corrected risk of developing the disease and a type of the disease on the display unit.
8 . The information processing apparatus according to claim 7 , wherein, in response to completion of an appointment with the recommended medical institution, the medical image used for estimating the risk of developing the disease, the biological information used for correcting the estimated risk of developing the disease, and the estimated risk of developing the disease are sent to the recommended medical institution via a system of the recommended medical institution.
9 . The information processing apparatus according to claim 7 , wherein diagnosis or consultation by a physician at the recommended medical institution is provided in accordance with the corrected risk of developing the disease and the type of the disease via a system capable of performing video communication.
10 . An information processing apparatus comprising:
estimation means for estimating a subject's risk of developing a disease using a learned model that has learned a relationship of a feature obtained from a medical image and biological information obtained by an examination apparatus with a risk of developing the disease;
correction means for correcting the estimated risk of developing the disease using a weight coefficient of the probability of developing each disease, the weight coefficient being set in advance for each item of the subject's biological information; and
display control means for displaying the estimated risk of developing the disease on a display unit.
11 . An information processing system comprising:
ophthalmic equipment that captures a medical image of a subject;
an examination apparatus that examines the subject and obtains biological information; and
an information processing apparatus according to claim 1 .
12 . An information processing method comprising:
obtaining a medical image captured by imaging a subject's medical;
estimating the subject's risk of developing a disease (a) by inputting, as input data, a feature obtained from the obtained medical image to a learned model that has learned a relationship between a feature obtained from a medical image and a risk of developing the disease or (b) by inputting, as input data, the obtained medical image to a learned model that has deep-learned a relationship between a medical image and a risk of developing the disease; and
correcting the estimated risk of developing the disease using a weight coefficient of the probability of developing each disease, the weight coefficient being set in advance for each item of the subject's biological information.
13 . An information processing method comprising:
estimating a subject's risk of developing a disease using a learned model that has learned a relationship of a feature obtained from a medical image and biological information obtained by an examination apparatus with a risk of developing the disease;
correction means for correcting the estimated risk of developing the disease using a weight coefficient of the probability of developing each disease, the weight coefficient being set in advance for each item of the subject's biological information; and
displaying the estimated risk of developing the disease on a display unit.
14 . A non transitory computer-readable storage medium storing a program for causing a computer to execute the method according to claim 12 .
15 . A non transitory computer-readable storage medium storing a program for causing a computer to execute the method according to claim 13 .