Coronary Artery Image Segmentation for Objective Occlusion Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current coronary angiography methods for diagnosing chronic total occlusion (CTO) in coronary arteries rely heavily on human expertise, leading to inconsistent and potentially erroneous results due to subjective interpretation.
Innovation Solution
An analysis method using a machine learning model for coronary artery images, involving segmentation and threshold-based pixel quantity analysis to objectively determine occlusion and its location, utilizing preprocessing techniques like blurring and contrast enhancement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If coronary angiography interpretation relies on experienced cardiologists or radiology specialists, then diagnostic accuracy may be improved, but diagnostic consistency and objectivity deteriorate due to operator experience and subjective judgment
Solution Approach 1:
The patent replaces the manual interpretation process (mechanical system of human expert analysis) with an automated machine learning model that processes coronary angiography images. This substitution eliminates subjective judgment while maintaining diagnostic accuracy through algorithmic objectivity, directly resolving the contradiction between expert-level accuracy and consistent reliability.
Solution Approach 2:
The machine learning model performs self-service by automatically analyzing coronary artery images without requiring human expert intervention. The system independently executes segmentation, occlusion detection, and diagnosis, ensuring consistent results across different cases while maintaining high diagnostic accuracy through trained algorithms.
2Reliability
If manual interpretation by experts is used, then complex occlusion cases can be handled, but time consumption and productivity deteriorate
Solution Approach 1:
The automated machine learning system replaces time-consuming manual expert interpretation with rapid algorithmic processing. The model can analyze multiple images simultaneously and provide diagnoses instantly, dramatically improving productivity while maintaining reliable diagnostic capability through consistent application of trained criteria.
Solution Approach 2:
The machine learning model performs preliminary analysis of coronary angiography images automatically before human review, pre-identifying potential occlusions and preparing diagnostic recommendations. This preliminary action reduces the time required for final diagnosis while ensuring comprehensive evaluation of all cases.
3Illumination intensity
If contrast agent imaging is used to show occlusion conditions, then visualization quality is improved, but reliance on subjective interpretation worsens
Solution Approach 1:
The patent replaces subjective human interpretation of contrast agent images with automated machine learning analysis. The model objectively processes the visual information from contrast-enhanced images, eliminating subjectivity while preserving the high visualization quality provided by contrast agent imaging.
Solution Approach 2:
The machine learning model serves as an intermediary between the contrast agent imaging and final diagnosis. It objectively translates the visual information from contrast-enhanced images into quantifiable metrics and diagnostic conclusions, removing the subjective element while maintaining the benefits of high-quality visualization.
Data Source
AI summary
An analysis method and an electronic device for a coronary artery image are provided. The method includes: performing segmentation on the coronary artery image based on a machine learning model to obtain a plurality of categories; setting one of the categories as a currently evaluated vessel, and determining whether a pixel quantity corresponding to the currently evaluated vessel is less than a first threshold to generate a result; and determining whether the coronary artery image has an occlusion phenomenon according to the result.