CAD System Adaptive Display for Real-Time Lesion Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Computer-Aided Diagnosis (CAD) systems hinder real-time diagnosis by providing excessive information to doctors, which can complicate the diagnostic process, and there is a need for a system that can efficiently identify lesions in real-time from video frames while allowing doctors to focus on manual diagnosis.
Innovation Solution
A CAD apparatus and method that includes an automatic diagnoser for real-time image analysis, an information determiner to prioritize diagnosis information based on user input and probe speed, and a display to overlay relevant markers and information on the image, allowing doctors to focus on specific regions of interest (ROIs) with tailored information display during detection and observation processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all types of diagnosis information are displayed to assist doctors in real-time, then diagnostic support is improved, but doctor's diagnosis process is hindered
Solution Approach 1:
The diagnosis information is segmented into different types (detection information, observation information, reference information) and displayed selectively based on the current diagnostic phase. During ROI detection, only detection-related information is shown, while during ROI observation, observation-related information is prioritized, reducing cognitive overload while maintaining diagnostic support
Solution Approach 2:
The system dynamically adjusts the type and amount of information displayed based on the detected probe speed and current diagnostic task. When probe speed indicates detection phase, the system displays detection information; when it indicates observation phase, the system switches to displaying observation information, making the interface adaptive to the doctor's workflow
2Reliability
If real-time CAD system provides all diagnosis information, then diagnostic accuracy is improved, but information overload occurs
Solution Approach 1:
The system extracts and displays only the most relevant information for the current diagnostic task. Based on probe speed detection, it extracts detection-related information during fast movement and observation-related information during slow movement, filtering out unnecessary information to prevent overload while maintaining accuracy
Solution Approach 2:
Different quality and detail levels of information are provided based on the diagnostic phase. During detection phase, coarse-grained detection information is displayed, while during observation phase, fine-grained observation information is shown, optimizing information quality for each specific task
3Measurement precision
If comprehensive information is displayed during ROI detection, then detection accuracy is improved, but processing time increases
Solution Approach 1:
The system periodically switches between different information display modes based on probe speed thresholds. When probe speed exceeds a threshold, detection information is displayed; when it falls below, observation information is displayed, creating a rhythmic information flow that matches the diagnostic workflow and reduces processing time
Data Source
AI summary
A Computer-Aided Diagnosis (CAD) apparatus and a CAD method are provided. The CAD apparatus includes an automatic diagnoser configured to perform automatic diagnosis using an image that is received from a probe, and generate diagnosis information including results of the automatic diagnosis. The CAD apparatus further includes an information determiner configured to determine diagnosis information to be displayed among the generated diagnosis information, based on a manual diagnosis of a user, and a display configured to display the received image and the determined diagnosis information.