Machine-Learning Vascular Tree Segmentation via Optimal Angiographic Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vascular segmentation and feature identification in angiographic images are prone to errors due to low contrast and complex environments, leading to inaccurate three-dimensional models of the heart.
Innovation Solution
A system utilizing machine learning models, such as convolutional neural networks, to select an optimal angiographic image from a sequence based on contrast and quality scores, reducing the need for manual adjustments and enhancing the accuracy of downstream processes like three-dimensional model generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated analysis is used for vascular segmentation and feature identification, then time and effort are reduced, but accuracy decreases due to low contrast and complex environment
Solution Approach 1:
The patent introduces an intermediary optimization process that selects the best angiographic image from multiple candidate images before performing automated vascular segmentation. This intermediary step improves the quality of input data for automated analysis, thereby maintaining accuracy while still benefiting from automation. The system evaluates multiple images and selects the optimal one based on vascular tree visibility and image quality metrics.
2Manufacturing precision
If image resolution is increased to improve segmentation accuracy, then precision improves, but radiant exposure and energy consumption increase
Solution Approach 1:
The patent applies partial action by selecting only the most suitable image from multiple candidates for downstream processing, rather than processing all images or increasing resolution across all images. This selective approach achieves high segmentation precision for the chosen image while avoiding the excessive radiant exposure that would result from capturing multiple high-resolution images.
3Measurement precision
If manual confirmation is required for automated vascular identification, then accuracy improves, but time and operator attention increase
Solution Approach 1:
The patent performs preliminary optimization by selecting the best angiographic image before automated vascular segmentation and identification. This preliminary action ensures that the automated system works with the highest quality input possible, thereby improving accuracy while minimizing the need for subsequent manual confirmation and reducing operator time requirements.
Data Source
AI summary
Methods for automated identification of vascular features are described. In some embodiments, one or more machine learning (ML)-based vascular classifiers are used, with their results being combined to with results of at least one other vascular classifier in order to produce the final results. Potentially advantages of this approach include the ability to combine certain strengths of ML classifiers with segmentation approaches based on more classical (“formula-based”) methods. These strengths may include particularly the identification of anatomically identified targets mixed within an image also showing similar looking but anatomically distinct targets.