Information processing apparatus, control method for information processing apparatus, and storage medium
An information processing apparatus includes a first generation unit configured to generate a list of one or more disease names from an affected area image of a patient, a first determination unit configured to determine a name of a part having an affected area, an acquisition unit configured to acquire a previous medical examination record for the part having the affected area, a second determination unit configured to detect an excluded disease name or an examination result excluding a possibility of a specific disease described in a medical examination history and determine an or the excluded disease name, and a display unit configured to display a disease name or disease names in the list of the one or more disease names that are not described in a list of the excluded disease name, differently from the excluded disease name in the list of the excluded disease name.
1 . An information processing apparatus that provides diagnosis support by presuming and displaying at least one disease name from an image, the information processing apparatus comprising:
at least one memory storing a program and storing disease data in which each of a plurality of disease names is associated with feature amounts; and
at least one processor that executes the program to cause the information processing apparatus to:
read an image of a part of a patient affected by a disease;
calculate feature amounts of the image, the feature amounts including a degree of diffuseness, a degree of circularity, a degree of redness, and a degree of roughness;
generate a list of one or more disease names from the feature amounts, by:
(i) comparing the feature amounts of the image with the feature amounts associated with each disease name stored in the disease data,
(ii) calculating, for each disease name, a sum of squares of distances of the feature amounts, and
(iii) enumerating one or more disease names for which the sum of squares of distances is lower than a threshold;
calculate, for each enumerated disease name, a degree of certainty based on the calculated sum of squares of distances;
determine a name of the part of the patient in the image that is affected by the disease;
acquire a previous medical examination record for the part affected by the disease;
detect an excluded disease name or an examination result excluding a possibility of a specific disease described in a medical examination history;
determine the excluded disease from the detected excluded disease name or an excluded disease name from the examination result;
generate a list of at least one excluded disease name;
correct the list of the one or more disease names by reducing, by a predetermined numerical value, a degree of certainty of a disease name included in the list of at least one excluded disease name; and
display at least one disease name in the list of the one or more disease names that are not included in the list of the excluded disease name differently from the excluded disease name in the list of the excluded disease name,
wherein:
an excluded disease name is displayed in a form indicating exclusion,
a reason for exclusion is displayed in response to a mouse-over operation on the displayed excluded disease name, and
a character string recommending a pathological examination is displayed for a disease classified as malignant, and a reason for recommending the pathological examination is displayed in response to a mouse-over operation;
wherein the processor further causes the information processing apparatus to:
determine whether a disease has been previously completely cured when the excluded disease name is determined; and
determine an excluded disease name only from a medical examination history of a disease determined to not be completely cured,
wherein the processor further causes the information processing apparatus to compare a list of one or more disease names generated from a current medical examination image with a list of one or more disease names generated from a previous medical examination image, and
wherein, when an amount of change is greater than or equal to a threshold, a previous medical examination history before the current medical examination is not referred to even when the disease of the previous medical examination is not completely cured and the excluded disease name is determined regardless of the previous medical examination history.
2 . The information processing apparatus according to claim 1 , wherein the processor further causes the information processing apparatus to determine that a specific disease is completely cured when an indication that the specific disease has been completely cured is included in the medical examination history.
3 . The information processing apparatus according to claim 2 wherein the specific disease is a lesion and the processor further causes the information processing apparatus to determine that the lesion is completely cured when an area indicating a lesion in a captured image at a previous medical examination is not present in a subsequently captured image.
4 . The information processing apparatus according to claim 1 , wherein the determined excluded disease name is a disease name indicated as an exclusion in the medical examination history.
5 . The information processing apparatus according to claim 1 , wherein the determined excluded disease name is a disease name of which a possibility is excluded with the examination result recorded in the medical examination history.
6 . The information processing apparatus according to claim 1 , wherein the determined excluded disease name is a disease name unrelated to the part of the patient.
7 . The information processing apparatus according to claim 6 , wherein information on the part of the patient affected by a disease can be input by a user or input based on the image of the part of the patient affected by a disease.
8 . The information processing apparatus according to claim 1 , wherein the processor further causes the information processing apparatus to display the determined excluded disease name in a form indicating the exclusion.
9 . The information processing apparatus according to claim 8 , wherein the processor further causes the information processing apparatus to display a reason for the exclusion of the displayed excluded disease name.
10 . The information processing apparatus according to claim 1 ,
wherein the processor further causes the information processing apparatus to calculate a name of a possible disease and a degree of certainty of the possible disease, and
to determine that the name of the possible disease is to be excluded, wherein the degree of certainty of the name of the possible disease is reduced by a predetermined numerical value.
11 . The information processing apparatus according to claim 1 , wherein the processor further causes the information processing apparatus to calculate a size of a lesion from an image of the part of the patient previously captured,
wherein a chronic disease is to be excluded when a calculated amount of change in the size of the lesion is greater than or equal to a predetermined amount, and
wherein an acute disease is to be excluded when the calculated amount of change in the size of the lesion is less than the predetermined amount.
12 . A method for controlling an information processing apparatus that provides diagnosis support by presuming and displaying at least one disease name from an image, the method comprising:
reading an image of a part of a patient affected by a disease;
calculating feature amounts of the image, the feature amounts including a degree of diffuseness, a degree of circularity, a degree of redness, and a degree of roughness;
generating a list of one or more disease names from the feature amounts, by:
(i) comparing the feature amounts of the image with feature amounts associated with each of a plurality of disease names stored in disease data;
(ii) calculating, for each disease name, a sum of squares of distances of the feature amounts, and
(iii) enumerating one or more disease names for which the sum of squares of distances is lower than a threshold;
calculating, for each enumerated disease name, a degree of certainty based on the calculated sum of squares of distances;
determining a name of the part of the patient in the image that is affected by the disease;
acquiring a previous medical examination record for the part affected by the disease;
detecting an excluded disease name or an examination result excluding a possibility of a specific disease described in a medical examination history;
determining the excluded disease from the detected excluded disease name or an excluded disease name from the examination result;
generating a list of at least one excluded disease name;
correcting the list of the one or more disease names by reducing, by a predetermined numerical value, a degree of certainty of a disease name included in the list of at least one excluded disease name; and
displaying at least one disease name in the list of the one or more disease names that are not included in the list of the excluded disease name differently from the excluded disease name in the list of the excluded disease name,
wherein:
an excluded disease name is displayed in a form indicating exclusion,
a reason for exclusion is displayed in response to a mouse-over operation on the displayed excluded disease name, and
a character string recommending a pathological examination is displayed for a disease classified as malignant, and
a reason for recommending the pathological examination is displayed in response to a mouse-over operation;
determining whether a disease has been previously completely cured when the excluded disease name is determined;
determining an excluded disease name only from a medical examination history of a disease determined to not be completely cured; and
comparing a list of one or more disease names generated from a current medical examination image with a list of one or more disease names generated from a previous medical examination image,
wherein, when an amount of change is greater than or equal to a threshold, a previous medical examination history before the current medical examination is not referred to even when the disease of the previous medical examination is not completely cured and the excluded disease name is determined regardless of the previous medical examination history.
13 . A non-transitory computer-readable storage medium storing a computer-readable program for causing a computer to execute a method to control an information processing apparatus that provides diagnosis support by presuming and displaying at least one disease name from an image, the method comprising:
reading an image of a part of a patient affected by a disease;
calculating feature amounts of the image, the feature amounts including a degree of diffuseness, a degree of circularity, a degree of redness, and a degree of roughness;
generating a list of one or more disease names from the feature amounts of the image of a part of a patient affected by the disease, by:
(i) comparing the feature amounts of the image with feature amounts associated with each of a plurality of disease names stored in disease data;
(ii) calculating, for each disease name, a sum of squares of distances of the feature amounts, and
(iii) enumerating one or more disease names for which the sum of squares of distances is lower than a threshold;
calculating, for each enumerated disease name, a degree of certainty based on the calculated sum of squares of distances;
determining a name of the part of the patient in the image that is affected by the disease;
acquiring a previous medical examination record for the part affected by the disease;
detecting an excluded disease name or an examination result excluding a possibility of a specific disease described in a medical examination history;
determining the excluded disease from the detected excluded disease name or an excluded disease name from the examination result;
generating a list of at least one excluded disease name;
correcting the list of the one or more disease names by reducing, by a predetermined numerical value, a degree of certainty of a disease name included in the list of at least one excluded disease name; and
displaying at least one disease name in the list of the one or more disease names that are not included in the list of the excluded disease name differently from the excluded disease name in the list of the excluded disease name,
wherein:
an excluded disease name is displayed in a form indicating exclusion,
a reason for exclusion is displayed in response to a mouse-over operation on the displayed excluded disease name, and
a character string recommending a pathological examination is displayed for a disease classified as malignant, and
a reason for recommending the pathological examination is displayed in response to a mouse-over operation;
determining whether a disease has been previously completely cured when the excluded disease name is determined;
determining an excluded disease name only from a medical examination history of a disease determined to not be completely cured; and
comparing a list of one or more disease names generated from a current medical examination image with a list of one or more disease names generated from a previous medical examination image,
wherein, when an amount of change is greater than or equal to a threshold, a previous medical examination history before the current medical examination is not referred to even when the disease of the previous medical examination is not completely cured and the excluded disease name is determined regardless of the previous medical examination history.