Uncertainty-Aware Concept and Motion Segmentation for Semi-Supervised Angiography Videos

2026-02-28

AI Summary

This work proposes SMART, a novel framework addressing the challenges of main coronary artery segmentation in X-ray coronary angiography (XCA) videos, including ambiguous boundaries, uneven contrast, complex motion dynamics, and scarce annotations. Built upon SAM3, SMART introduces a teacher–student semi-supervised architecture that innovatively integrates motion-aware consistency constraints—achieved through optical flow–guided deformation of vessel masks—with a progressive confidence regularization mechanism. This design significantly enhances segmentation robustness and accuracy under limited annotation conditions. Evaluated on three multicenter XCA datasets, SMART substantially outperforms existing methods, markedly reducing reliance on labeled data while demonstrating strong clinical applicability.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Segmentation of the main coronary artery from X-ray coronary angiography (XCA) sequences is crucial for the diagnosis of coronary artery diseases. However, this task is challenging due to issues such as blurred boundaries, inconsistent radiation contrast, complex motion patterns, and a lack of annotated images for training. Although Semi-Supervised Learning (SSL) can alleviate the annotation burden, conventional methods struggle with complicated temporal dynamics and unreliable uncertainty quantification. To address these challenges, we propose SAM3-based Teacher-student framework with Motion-Aware consistency and Progressive Confidence Regularization (SMART), a semi-supervised vessel segmentation approach for X-ray angiography videos. First, our method utilizes SAM3's unique promptable concept segmentation design and innovates a SAM3-based teacher-student framework to maximize the performance potential of both the teacher and the student. Second, we enhance segmentation by integrating the vessel mask warping technique and motion consistency loss to model complex vessel dynamics. To address the issue of unreliable teacher predictions caused by blurred boundaries and minimal contrast, we further propose a progressive confidence-aware consistency regularization to mitigate the risk of unreliable outputs. Extensive experiments on three datasets of XCA sequences from different institutions demonstrate that SMART achieves state-of-the-art performance while requiring significantly fewer annotations, making it particularly valuable for real-world clinical applications where labeled data is scarce. Our code is available at: https://github.com/qimingfan10/SMART.

Problem

• coronary artery segmentation
• X-ray angiography
• semi-supervised learning
• motion dynamics
• uncertainty quantification

Innovation

• SAM3
• teacher-student framework
• motion-aware consistency
• progressive confidence regularization
• semi-supervised segmentation