Medical Support System for Endoscopic Report Image Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In endoscopic examinations, doctors cannot attach images forgotten to be captured during the procedure to reports, and using CAD systems to display additional images increases the time and effort required for selecting images for reports due to the large number of detected lesions.
Innovation Solution
A medical support system and method that acquire both user-captured and computer-captured images, including lesions, and generate a selection screen for efficient image selection, where computer-captured images not included in the user-captured images are specified as candidate images for attachment, reducing duplication and effort in selecting images for reports.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If CAD system displays all detected lesion images as candidate images, then completeness of image coverage is improved, but selection time and effort increases
Solution Approach 1:
The patent extracts and displays only the necessary subset of candidate images (user-captured images and computer-captured images with lesions not included in user captures) rather than all detected lesion images. This extraction principle reduces the number of images displayed while ensuring completeness of lesion coverage, thereby reducing selection time without sacrificing diagnostic completeness.
2Productivity
If doctor performs rapid endoscopic examination, then patient burden is reduced, but images may be forgotten to be captured
Solution Approach 1:
The patent introduces a computer-aided diagnosis system as an intermediary that automatically detects lesions and identifies images containing lesions that were not captured by the user. This intermediary system bridges the gap between rapid examination and complete image capture, ensuring that no lesion images are missed even when the doctor performs the examination quickly.
3Ease of operation
If separation of user-captured and computer-captured images is implemented, then selection efficiency is improved, but system complexity increases
Solution Approach 1:
The patent segments the candidate images into two distinct categories: user-captured images and computer-captured images with lesions not included in user captures. This segmentation is implemented through separate display regions on the selection screen, allowing doctors to efficiently navigate and select images without being overwhelmed by a single large list, thereby improving selection efficiency while maintaining manageable system complexity.
Data Source
AI summary
An image acquisition unit acquires a user-captured image captured through a capture operation by a user and a computer-captured image captured by a computer including a lesion. An image specifying unit specifies computer-captured images that include a lesion not included in the user-captured images as candidate images for attachment. A display screen generation unit generates a selection screen that is for selecting an image to be attached to a report and that includes the user-captured images and the candidate images for attachment and displays the selection screen on a display device.