Endoscopy support apparatus, endoscopy support method, and computer readable recording medium
An endoscopy support apparatus 1 includes: an analysis information generation unit 2 that inputs image information of an imaged living body into a model, estimates a region of a target site of the living body, and generates analysis information including region information indicating the estimated region and score information indicating likeness of the region to the target site; a user information generation unit 3 that generates user information related to the user, which has been input by a user using a user interface 23 ; an image-related information generation unit 4 that generates image-related information by associating imaging date and time information, the analysis information, and the user information, for each piece of image information; and an examination management information generation unit 5 that generates examination management information by associating a plurality of pieces of the image-related information with examination information indicating an examination period.
1. An endoscopy support apparatus comprising:
a processor; and
a memory storing instructions executable by the processor to:
input a plurality of pieces of image information of a living body imaged by an endoscope into a model;
for each piece of image information, estimate a region of a target site of the living body, and generate analysis information including region information indicating the estimated region and score information indicating a likeness of the region to the target site;
generate user information related to a user, which has been input by the user using a user interface;
generate image-related information by associating imaging date and time information indicating a date and time when an image was captured, the analysis information, and the user information, for each piece of image information;
generate examination management information by associating the image-related information generated for each piece of image information during an examination period with examination information identifying an examination;
cause a display of an output device to display an examination result screen indicating an examination result based on examination management information;
classify the score information for each piece of image information that lies within a score range set by the user via the examination result screen; and
cause the display to display the user information, the imaging date and time information, and the analysis information, for each piece of image information for which the score has been classified.
2. The endoscopy support apparatus according to claim 1 , wherein the instructions are executable by the processor to further:
generate user setting information used for setting output of the analysis information for each of a plurality of users.
3. The endoscopy support apparatus according to claim 2 ,
wherein the user setting information includes at least one of setting information for changing display of the region according to the score information and setting information for changing a volume according to the score information, in the examination.
4. The endoscopy support apparatus according to claim 1 ,
wherein when the processor obtains end information indicating an end of the examination, the processor generates the examination management information.
5. The endoscopy support apparatus according to claim 1 , wherein
the model is generated by machine learning, and
the examination result is optimized for the user based on a user profile included in the user information to support decision making by the user.
6. An endoscopy support method performed by a computer and comprising:
inputting a plurality of pieces of image information of a living body imaged by an endoscope into a model;
for each piece of image information, estimating a region of a target site of the living body, and generating analysis information including region information indicating the estimated region and score information indicating a likeness of the region to the target site;
generating user information related to a user, which has been input by the user using a user interface;
generating image-related information by associating imaging date and time information indicating a date and time when an image was captured, the analysis information, and the user information, for each piece of image information;
generating examination management information by associating the image-related information generated for each piece of image information during an examination period with examination information identifying an examination;
causing a display of an output device to display an examination result screen indicating an examination result based on the examination management information;
classifying the score information for each piece of image information that lies within a score range set by the user via the examination result screen; and
causing the display to display the user information, the imaging date and time information, and the analysis information, for each piece of image information for which the score has been classified.
7. The endoscopy support method according to claim 6 , further comprising
generating user setting information used for setting output of the analysis information for each of a plurality of users.
8. The endoscopy support method according to claim 6 ,
wherein the user setting information includes at least one of setting information for changing display of the region according to the score information and setting information for changing a volume according to the score information, in the examination.
9. The endoscopy support method according to claim 6 ,
wherein when end information indicating an end of the examination is obtained, the examination management information is generated.
10. The endoscopy support method according to claim 6 , wherein
the model is generated by machine learning, and
the examination result is optimized for the user based on a user profile included in the user information to support user's decision making by the user.
11. A non-transitory computer readable recording medium storing a program including instructions that cause a computer to carry out:
inputting a plurality of pieces of image information of a living body imaged by an endoscope into a model;
for each piece of image information, estimating a region of a target site of the living body, and generating analysis information including region information indicating the estimated region and score information indicating a likeness of the region to the target site;
generating user information related to a user, which has been input by the user using a user interface;
generating image-related information by associating imaging date and time information indicating a date and time when an image was captured, the analysis information, and the user information, for each piece of image information;
generating examination management information by associating the image-related information generated for each piece of image information during an examination period with examination information identifying an examination;
causing a display of an output device to display an examination result screen indicating an examination result based on the examination management information;
classifying the score information for each piece of image information that lies within a score range set by the user via the examination result screen; and
causing the display to display the user information, the imaging date and time information, and the analysis information, for each piece of image information for which the score has been classified.
12. The non-transitory computer readable recording medium according to claim 11 , wherein the instructions further cause the computer to carry out
generating user setting information used for setting output of the analysis information for each of a plurality of users.
13. The non-transitory computer readable recording medium according to claim 11 ,
wherein the user setting information includes at least one of setting information for changing display of the region according to the score information and setting information for changing a volume according to the score information, in the examination.
14. The non-transitory computer readable recording medium according to claim 11 ,
wherein when end information indicating an end of the examination is obtained, the examination management information is generated.
15. The non-transitory computer readable recording medium according to claim 11 , wherein
the model is generated by machine learning, and
the examination result is optimized for the user based on a user profile included in the user information to support decision making by the user.