CAD Detection Display Sequencing and Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Radiologists face challenges in efficiently navigating and perceiving multiple computer-aided detection (CAD) results in medical images due to overwhelming information, which affects their ability to provide high-quality diagnoses within a reasonable time frame, especially in high-throughput radiology environments.
Innovation Solution
A method for displaying CAD detections in a mammographic case using a predetermined sequencing criterion, such as a scalar overall probability metric, to prioritize and sequentially present CAD detections, accompanied by a navigational tool that maps computed features onto an operating curve, allowing for quick comparison of detections relative to each other and a reference database.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple CAD detections are displayed simultaneously with detailed information, then diagnostic completeness is improved, but radiologist cognitive load and navigation time increase
Solution Approach 1:
The patent segments the display of CAD detections into a hierarchical structure: an overview map showing all detection locations, and detailed view windows that display comprehensive information. Radiologists can navigate between these levels to access detailed information only when needed, reducing cognitive load while maintaining diagnostic completeness.
Solution Approach 2:
The system performs preliminary organization of CAD detections by computing confidence scores and sorting detections before display. This pre-processing arranges information in a logical sequence, allowing radiologists to efficiently navigate through prioritized detections rather than searching through unorganized results.
2Measurement precision
If comprehensive CAD detection information is provided, then diagnostic accuracy is improved, but information overload occurs reducing radiologist efficiency
Solution Approach 1:
The patent applies local quality by providing different levels of information detail in different display regions. The overview map provides location context with minimal detail, while detailed view windows provide comprehensive information only when activated. This allows radiologists to maintain efficiency during overview navigation while accessing complete diagnostic information when needed.
Solution Approach 2:
The system displays partial information (overview map with detection markers) by default, and only provides excessive detailed information when the radiologist explicitly requests it through interaction. This on-demand approach maintains efficiency for routine cases while enabling thorough analysis when clinically indicated.
3Reliability
If all CAD detection details are displayed at once, then complete analysis is enabled, but radiologist stamina and decision-making speed decrease
Solution Approach 1:
The patent implements a dynamic display system where the level of information detail adapts based on radiologist interaction. The system transitions between overview mode (fast navigation) and detailed view mode (comprehensive analysis), allowing radiologists to optimize between speed and completeness based on clinical needs and case complexity.
Data Source
AI summary
Display and navigation for multiple computer-aided detection (CAD) detections is described. A medical image is displayed to a viewer, and a request is received to instantiate CAD-assisted viewing. A timewise presentation sequence for the CAD detections is automatically computed according to a predetermined sequencing criterion. For each CAD detection, an expanded presentation window is displayed for its associated location in the medical image, the expanded presentation windows being displayed according to the timewise presentation sequence. Also described is a navigational tool comprising a plot of an operating curve onto which a computed feature associated with the CAD algorithm can be mapped, the operating curve characterizing an application of the CAD algorithm to a reference database of mammographic cases having known diagnoses. The navigational tool further comprises a plurality of CAD pointer icons spatially distributed therealong according to mappings of the computed feature for the CAD detections onto the operating curve.