MTCNet: Motion and Topology Consistency Guided Learning for Mitral Valve Segmentationin 4D Ultrasound
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908431225454592 |
|---|---|
| author | Chen, Rusi Yang, Yuanting Yao, Jiezhi Song, Hongning Zhang, Ji Zhou, Yongsong Huang, Yuhao Yang, Ronghao Jia, Dan Zhang, Yuhan Tao, Xing Dou, Haoran Zhou, Qing Yang, Xin Ni, Dong |
| author_facet | Chen, Rusi Yang, Yuanting Yao, Jiezhi Song, Hongning Zhang, Ji Zhou, Yongsong Huang, Yuhao Yang, Ronghao Jia, Dan Zhang, Yuhan Tao, Xing Dou, Haoran Zhou, Qing Yang, Xin Ni, Dong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00660 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MTCNet: Motion and Topology Consistency Guided Learning for Mitral Valve Segmentationin 4D Ultrasound Chen, Rusi Yang, Yuanting Yao, Jiezhi Song, Hongning Zhang, Ji Zhou, Yongsong Huang, Yuhao Yang, Ronghao Jia, Dan Zhang, Yuhan Tao, Xing Dou, Haoran Zhou, Qing Yang, Xin Ni, Dong Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition 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. |
| title | MTCNet: Motion and Topology Consistency Guided Learning for Mitral Valve Segmentationin 4D Ultrasound |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.00660 |