MTCNet: Motion and Topology Consistency Guided Learning for Mitral Valve Segmentationin 4D Ultrasound

TL;DR

This paper introduces MTCNet, a semi-supervised learning framework that leverages motion and topology consistency for accurate 4D mitral valve segmentation in ultrasound, addressing challenges like limited annotations and motion artifacts.

Contribution

MTCNet is the first to incorporate motion-guided consistency and topology regularization for 4D MV segmentation, enabling effective semi-supervised learning with sparse annotations.

Findings

Achieved Dice score of 87.30% in 4D MV segmentation.

Outperformed existing methods in cross-phase consistency.

Validated on the largest 4D MV dataset with 1408 phases.

Abstract

Mitral regurgitation is one of the most prevalent cardiac disorders. Four-dimensional (4D) ultrasound has emerged as the primary imaging modality for assessing dynamic valvular morphology. However, 4D mitral valve (MV) analysis remains challenging due to limited phase annotations, severe motion artifacts, and poor imaging quality. Yet, the absence of inter-phase dependency in existing methods hinders 4D MV analysis. To bridge this gap, we propose a Motion-Topology guided consistency network (MTCNet) for accurate 4D MV ultrasound segmentation in semi-supervised learning (SSL). MTCNet requires only sparse end-diastolic and end-systolic annotations. First, we design a cross-phase motion-guided consistency learning strategy, utilizing a bi-directional attention memory bank to propagate spatio-temporal features. This enables MTCNet to achieve excellent performance both per- and inter-phase. Second, we devise a novel topology-guided correlation regularization that explores physical prior knowledge to maintain anatomically plausible. Therefore, MTCNet can effectively leverage structural correspondence between labeled and unlabeled phases. Extensive evaluations on the first largest 4D MV dataset, with 1408 phases from 160 patients, show that MTCNet performs superior cross-phase consistency compared to other advanced methods (Dice: 87.30%, HD: 1.75mm). Both the code and the dataset are available at https://github.com/crs524/MTCNet.