SparseMamba-PCL: Scribble-Supervised Medical Image Segmentation via SAM-Guided Progressive Collaborative Learning
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_ | 1866910855589789696 |
|---|---|
| author | Qiu, Luyi Till, Tristan Guo, Xiaobao Kong, Adams Wai-Kin |
| author_facet | Qiu, Luyi Till, Tristan Guo, Xiaobao Kong, Adams Wai-Kin |
| contents | Scribble annotations significantly reduce the cost and labor required for dense labeling in large medical datasets with complex anatomical structures. However, current scribble-supervised learning methods are limited in their ability to effectively propagate sparse annotation labels to dense segmentation masks and accurately segment object boundaries. To address these issues, we propose a Progressive Collaborative Learning framework that leverages novel algorithms and the Med-SAM foundation model to enhance information quality during training. (1) We enrich ground truth scribble segmentation labels through a new algorithm, propagating scribbles to estimate object boundaries. (2) We enhance feature representation by optimizing Med-SAM-guided training through the fusion of feature embeddings from Med-SAM and our proposed Sparse Mamba network. This enriched representation also facilitates the fine-tuning of the Med-SAM decoder with enriched scribbles. (3) For inference, we introduce a Sparse Mamba network, which is highly capable of capturing local and global dependencies by replacing the traditional sequential patch processing method with a skip-sampling procedure. Experiments on the ACDC, CHAOS, and MSCMRSeg datasets validate the effectiveness of our framework, outperforming nine state-of-the-art methods. Our code is available at \href{https://github.com/QLYCode/SparseMamba-PCL}{SparseMamba-PCL.git}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01633 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SparseMamba-PCL: Scribble-Supervised Medical Image Segmentation via SAM-Guided Progressive Collaborative Learning Qiu, Luyi Till, Tristan Guo, Xiaobao Kong, Adams Wai-Kin Computer Vision and Pattern Recognition Scribble annotations significantly reduce the cost and labor required for dense labeling in large medical datasets with complex anatomical structures. However, current scribble-supervised learning methods are limited in their ability to effectively propagate sparse annotation labels to dense segmentation masks and accurately segment object boundaries. To address these issues, we propose a Progressive Collaborative Learning framework that leverages novel algorithms and the Med-SAM foundation model to enhance information quality during training. (1) We enrich ground truth scribble segmentation labels through a new algorithm, propagating scribbles to estimate object boundaries. (2) We enhance feature representation by optimizing Med-SAM-guided training through the fusion of feature embeddings from Med-SAM and our proposed Sparse Mamba network. This enriched representation also facilitates the fine-tuning of the Med-SAM decoder with enriched scribbles. (3) For inference, we introduce a Sparse Mamba network, which is highly capable of capturing local and global dependencies by replacing the traditional sequential patch processing method with a skip-sampling procedure. Experiments on the ACDC, CHAOS, and MSCMRSeg datasets validate the effectiveness of our framework, outperforming nine state-of-the-art methods. Our code is available at \href{https://github.com/QLYCode/SparseMamba-PCL}{SparseMamba-PCL.git}. |
| title | SparseMamba-PCL: Scribble-Supervised Medical Image Segmentation via SAM-Guided Progressive Collaborative Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.01633 |