Coronary Artery Segmentation With Iterative ROI Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing coronary artery segmentation methods struggle to accurately distinguish between coronary arteries and veins, especially in the presence of motion artifacts or plaques, leading to false positives and difficulty in identifying small branches.
Innovation Solution
A method involving iterative detection steps with regional coronary artery inspiration data, where a to-be-detected region is replaced by a comparison result, and a pre-trained model is used to enhance segmentation accuracy and robustness, utilizing growth connectivity of coronary arteries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing segmentation methods are used, then processing speed is maintained, but segmentation accuracy deteriorates due to inability to distinguish coronary arteries from veins and susceptibility to motion artifacts or plaques
Solution Approach 1:
The method segments the coronary artery imaging data into multiple regions of interest (ROIs) based on spatial location and anatomical characteristics. Each ROI is processed independently with the segmentation model, allowing focused analysis of specific coronary artery segments while maintaining overall context through regional inspiration data propagation.
Solution Approach 2:
The method performs preliminary actions by first obtaining regional coronary artery inspiration data from annotated images before performing the actual segmentation. This pre-processing step establishes ground truth references and guides the segmentation model's initial predictions, improving accuracy before final segmentation occurs.
Solution Approach 3:
The method implements feedback mechanisms by comparing segmentation results with regional inspiration data and iteratively refining the segmentation. The comparison result is used to update and replace regions in the to-be-detected image, with the updated image serving as input for subsequent detection steps, creating a feedback loop that improves segmentation accuracy.
2Measurement precision
If iterative detection with regional inspiration data is applied, then segmentation accuracy improves, but processing time increases
Solution Approach 1:
The method divides the coronary artery imaging data into multiple regions of interest (ROIs) that can be processed in parallel. By segmenting the image into distinct anatomical regions, the system can perform iterative detection independently in each region, reducing the overall processing time while maintaining high accuracy through localized refinement.
Solution Approach 2:
The method applies partial action by performing iterative detection only on specific regions where segmentation uncertainty is highest or where regional inspiration data indicates potential errors. Rather than uniformly applying multiple detection steps to the entire image, the system targets only the necessary regions, reducing computational time while maintaining accuracy where needed.
Data Source
AI summary
Disclosed are a coronary artery segmentation method, an electronic device, and a computer-readable storage medium. The coronary artery segmentation method includes: iteratively performing a detection step for a to-be-detected image; for a plurality of the detection steps corresponding to the to-be-detected image, selecting the to-be-detected region in a current detection step from the replaced to-be-detected image in a previous detection step, and using a part of the comparison result in the previous detection step as the regional coronary artery inspiration data in the current detection step; and outputting a finally replaced to-be-detected image as coronary artery segmentation data. This method implements precise segmentation, and effectively distinguishes between a coronary artery and a vein false positive.