Medical Image Sorting and Filtering Using CAD Confidence Levels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing CAD systems in medical imaging provide inefficient results, often presenting too many disease candidates and requiring inefficient sorting and filtering processes.
Innovation Solution
The system implements methods for filtering, sorting, and displaying medical images based on characteristics such as disease size, features, AI confidence levels, user preferences, and diagnostic guidelines, using a combination of computer-aided detection and diagnosis (CAD) and picture archiving and communication systems (PACS).
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If CAD programs detect diseases in medical images, then diagnostic accuracy is improved, but the quantity of results increases excessively making review inefficient
Solution Approach 1:
The system changes parameters by introducing multiple sorting criteria (confidence level, disease type, anatomical location, size) and filtering options to reorganize and refine the presentation of CAD results, transforming the overwhelming quantity of undifferentiated results into a manageable, prioritized list that maintains diagnostic accuracy while improving review efficiency
2Reliability
If multiple CAD programs are executed to improve detection coverage, then diagnostic thoroughness is improved, but result processing complexity increases
Solution Approach 1:
The system merges results from multiple CAD programs into a single unified interface, combining detection results, confidence levels, and disease candidates from different programs and presenting them through a common sorting and filtering framework, thereby reducing the complexity of processing multiple separate results while maintaining comprehensive detection coverage
3Reliability
If all disease candidates are presented to ensure completeness, then diagnostic completeness is improved, but time to review results increases
Solution Approach 1:
The system performs preliminary action by automatically sorting disease candidates according to multiple criteria (confidence level, disease type, location, size) before presentation to the user, and providing filtering capabilities that allow practitioners to pre-select relevant categories, thereby reducing the time required to review results while maintaining diagnostic completeness through systematic organization
Data Source
AI summary
Methods and system for filtering, sorting, and displaying images are provided. The method can include receiving a request to view two or more images associated with a patient and receiving a request to perform Computer Aided Detection and Diagnosis (CAD) on the two or more images. The method can include performing CAD on the two or more images. Performing CAD can include identifying at least one characteristic of each of the two or more images, respectively. The method can include sorting the two or more images to generate an image order, the image order determined based at least in part on the at least one characteristic of each of the two or more images. The two or more images can be transferred from the one or more computing devices to the client device, and the two or more images can be displayed in the image order.