Medical Image Report Support Through Cross-Time Region Linking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing number of medical images requiring interpretation outpaces the availability of radiologists, leading to a burden in creating interpretation reports, and existing methods do not efficiently facilitate reference to past images for efficient creation of current reports, especially when multiple images of the same patient are taken at different times.
Innovation Solution
A document creation support apparatus that specifies corresponding regions across multiple images of varying imaging times, displays and switches between descriptions of these regions, and optionally transcribes or generates descriptions to assist in creating interpretation reports.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the number of medical images to be interpreted is increased, then the productivity of the imaging system is improved, but the burden on radiologists increases due to insufficient number of radiologists
Solution Approach 1:
The system enables self-service by automatically generating interpretation reports based on AI analysis of medical images. The AI model processes images, extracts findings, and generates structured reports without requiring radiologist intervention for each image, allowing the system to serve itself in the analysis and reporting process.
Solution Approach 2:
The invention introduces an intermediary AI-based report generation system between the medical imaging process and the radiologist. This intermediary automatically processes images and creates initial reports, which radiologists can then review and modify as needed, reducing the direct burden on radiologists while maintaining quality control.
2Ease of operation
If past image interpretation reports are referred to for efficient report creation, then the ease of operation is improved, but the device complexity increases due to need to manage multiple images and descriptions
Solution Approach 1:
The system segments the medical image data by separating current images being interpreted from past images stored in the database. It also segments the report generation process into automatic AI-generated content and manual radiologist review portions. This segmentation allows efficient reference to past reports without overwhelming complexity in managing all image data simultaneously.
Solution Approach 2:
The system performs preliminary action by pre-processing and storing past medical images and their interpretation reports in a database before they are needed. When a new image needs interpretation, the system can quickly retrieve and reference relevant past reports without requiring complex real-time search and processing, thus improving ease of operation while managing complexity through advance preparation.
Data Source
AI summary
A document creation support apparatus includes at least one processor, and the processor specifies, with respect to a first region specified in a first image of a subject, a second region corresponding to the first region in each of a plurality of second images of the subject whose imaging time is different from that of the first image. The processor specifies a second description regarding the specified second region, which is included in a plurality of sentences related to each of the plurality of second images. The processor displays a plurality of second descriptions specified for each of the plurality of second images in a switchable manner.