Foundation Model for Whole-Heart Segmentation: Leveraging Student-Teacher Learning in Multi-Modal Medical Imaging
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_ | 1866916661818294272 |
|---|---|
| author | Qayyum, Abdul Mazher, Moona Ugurlu, Devran Lemus, Jose Alonso Solis Rodero, Cristobal Niederer, Steven A |
| author_facet | Qayyum, Abdul Mazher, Moona Ugurlu, Devran Lemus, Jose Alonso Solis Rodero, Cristobal Niederer, Steven A |
| contents | Whole-heart segmentation from CT and MRI scans is crucial for cardiovascular disease analysis, yet existing methods struggle with modality-specific biases and the need for extensive labeled datasets. To address these challenges, we propose a foundation model for whole-heart segmentation using a self-supervised learning (SSL) framework based on a student-teacher architecture. Our model is pretrained on a large, unlabeled dataset of CT and MRI scans, leveraging the xLSTM backbone to capture long-range spatial dependencies and complex anatomical structures in 3D medical images. By incorporating multi-modal pretraining, our approach ensures strong generalization across both CT and MRI modalities, mitigating modality-specific variations and improving segmentation accuracy in diverse clinical settings. The use of large-scale unlabeled data significantly reduces the dependency on manual annotations, enabling robust performance even with limited labeled data. We further introduce an xLSTM-UNet-based architecture for downstream whole-heart segmentation tasks, demonstrating its effectiveness on few-label CT and MRI datasets. Our results validate the robustness and adaptability of the proposed model, highlighting its potential for advancing automated whole-heart segmentation in medical imaging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19005 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Foundation Model for Whole-Heart Segmentation: Leveraging Student-Teacher Learning in Multi-Modal Medical Imaging Qayyum, Abdul Mazher, Moona Ugurlu, Devran Lemus, Jose Alonso Solis Rodero, Cristobal Niederer, Steven A Image and Video Processing Computer Vision and Pattern Recognition Whole-heart segmentation from CT and MRI scans is crucial for cardiovascular disease analysis, yet existing methods struggle with modality-specific biases and the need for extensive labeled datasets. To address these challenges, we propose a foundation model for whole-heart segmentation using a self-supervised learning (SSL) framework based on a student-teacher architecture. Our model is pretrained on a large, unlabeled dataset of CT and MRI scans, leveraging the xLSTM backbone to capture long-range spatial dependencies and complex anatomical structures in 3D medical images. By incorporating multi-modal pretraining, our approach ensures strong generalization across both CT and MRI modalities, mitigating modality-specific variations and improving segmentation accuracy in diverse clinical settings. The use of large-scale unlabeled data significantly reduces the dependency on manual annotations, enabling robust performance even with limited labeled data. We further introduce an xLSTM-UNet-based architecture for downstream whole-heart segmentation tasks, demonstrating its effectiveness on few-label CT and MRI datasets. Our results validate the robustness and adaptability of the proposed model, highlighting its potential for advancing automated whole-heart segmentation in medical imaging. |
| title | Foundation Model for Whole-Heart Segmentation: Leveraging Student-Teacher Learning in Multi-Modal Medical Imaging |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.19005 |