Diagnosis Support System Using Extra-Coronary Calcification for CVD Risk
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods fail to effectively utilize incidental findings of vascular calcification from non-target medical examinations for early detection and prevention of cardiovascular disease, as these findings are often overlooked in routine reports.
Innovation Solution
A diagnosis support system that evaluates cardiovascular disease risk by using extra-coronary calcification as a trigger, acquired from non-heart examination images such as mammography, chest X-ray, or lung field CT images, and integrates this information into image interpretation reports to provide CVD risk values and recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If incidental findings of vascular calcification from non-target medical examinations are overlooked in routine reports, then the examination process remains simple and quick, but early detection of cardiovascular disease is delayed
Solution Approach 1:
The system extracts incidental findings of vascular calcification from non-target medical examination images and separates them as a specific evaluation item. This allows the calcification detection function to be isolated and automated, enabling early CVD detection without significantly increasing overall system complexity.
Solution Approach 2:
The system automatically evaluates image interpretation information for vascular calcification and integrates it into reports without requiring manual review. This self-service approach detects CVD risks from incidental findings while maintaining efficient examination workflows.
2Reliability
If incidental findings of vascular calcification are integrated into routine reports, then early detection of cardiovascular disease is improved, but the complexity of image interpretation reports increases
Solution Approach 1:
The system integrates multiple functions into a single evaluation process: it assesses both the primary examination target and incidental vascular calcification findings within the same image interpretation workflow. This multi-functionality improves CVD detection reliability while avoiding the need for separate complex evaluation systems.
Solution Approach 2:
The system merges the evaluation of incidental vascular calcification with the routine image interpretation process. By combining these evaluations into a unified report structure, the system improves cardiovascular disease detection reliability without creating separate complex reporting systems.
3Loss of time
If non-target examination images are used to detect cardiovascular calcification, then the number of additional examinations is reduced, but the precision of cardiovascular disease risk evaluation may be affected
Solution Approach 1:
The system uses artificial intelligence as an intermediary to accurately detect and evaluate vascular calcification in non-target examination images. This AI intermediary maintains measurement precision by reliably identifying calcification patterns that might be missed in routine reviews, enabling accurate CVD risk evaluation without additional specialized examinations.
Solution Approach 2:
The system replaces manual review of incidental findings with automated AI-based evaluation. This substitution maintains or improves measurement precision while eliminating the need for additional examinations, as the AI system can accurately assess vascular calcification from existing non-target images.
Data Source
AI summary
According to one embodiment, a diagnosis support system evaluates a cardiovascular disease risk by using extra-coronary calcification as a trigger. The diagnosis support system includes a processing circuit. The processing circuit is configured to acquire image interpretation information related to an image interpretation result of a photographed image of a patient, determine whether calcification is present or not based on the image interpretation information, evaluate the cardiovascular disease risk based on medical information on a patient, and output a determination result and an evaluation result.