Partial Vessels Annotation-based Coronary Artery Segmentation with Self-training and Prototype Learning

TL;DR

This paper introduces a novel weakly supervised learning framework for coronary artery segmentation that effectively utilizes partial vessel annotations, reducing annotation effort while maintaining high segmentation accuracy.

Contribution

It proposes a progressive learning framework that propagates local vessel features, learns global structure, and leverages prototype similarity, advancing label-efficient coronary artery segmentation.

Findings

Outperforms existing methods under partial annotation (24.29% vessels).

Achieves comparable trunk continuity with fully annotated models.

Demonstrates effectiveness on clinical CCTA data.

Abstract

Coronary artery segmentation on coronary-computed tomography angiography (CCTA) images is crucial for clinical use. Due to the expertise-required and labor-intensive annotation process, there is a growing demand for the relevant label-efficient learning algorithms. To this end, we propose partial vessels annotation (PVA) based on the challenges of coronary artery segmentation and clinical diagnostic characteristics. Further, we propose a progressive weakly supervised learning framework to achieve accurate segmentation under PVA. First, our proposed framework learns the local features of vessels to propagate the knowledge to unlabeled regions. Subsequently, it learns the global structure by utilizing the propagated knowledge, and corrects the errors introduced in the propagation process. Finally, it leverages the similarity between feature embeddings and the feature prototype to enhance testing outputs. Experiments on clinical data reveals that our proposed framework outperforms the competing methods under PVA (24.29% vessels), and achieves comparable performance in trunk continuity with the baseline model using full annotation (100% vessels).