MTCNet：基于运动和拓扑一致性引导的肺瓣膜4D超声分割
摘要
肺瓣反流是最常见的心脏疾病之一。四维（4D）超声声像已成为评估动态瓣膜形态的主要影像模态。然而，4D 肺瓣（MV）分析仍具有挑战性 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.
引用
@article{arxiv.2507.00660,
title = {MTCNet: Motion and Topology Consistency Guided Learning for Mitral Valve Segmentationin 4D Ultrasound},
author = {Rusi Chen and Yuanting Yang and Jiezhi Yao and Hongning Song and Ji Zhang and Yongsong Zhou and Yuhao Huang and Ronghao Yang and Dan Jia and Yuhan Zhang and Xing Tao and Haoran Dou and Qing Zhou and Xin Yang and Dong Ni},
journal= {arXiv preprint arXiv:2507.00660},
year = {2025}
}
备注
Accepted by MICCAI 2025