Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909250072084480 |
|---|---|
| author | Shi, Hairong Han, Songhao Huang, Shaofei Liao, Yue Li, Guanbin Kong, Xiangxing Zhu, Hua Wang, Xiaomu Liu, Si |
| author_facet | Shi, Hairong Han, Songhao Huang, Shaofei Liao, Yue Li, Guanbin Kong, Xiangxing Zhu, Hua Wang, Xiaomu Liu, Si |
| contents | Tumor lesion segmentation on CT or MRI images plays a critical role in cancer diagnosis and treatment planning. Considering the inherent differences in tumor lesion segmentation data across various medical imaging modalities and equipment, integrating medical knowledge into the Segment Anything Model (SAM) presents promising capability due to its versatility and generalization potential. Recent studies have attempted to enhance SAM with medical expertise by pre-training on large-scale medical segmentation datasets. However, challenges still exist in 3D tumor lesion segmentation owing to tumor complexity and the imbalance in foreground and background regions. Therefore, we introduce Mask-Enhanced SAM (M-SAM), an innovative architecture tailored for 3D tumor lesion segmentation. We propose a novel Mask-Enhanced Adapter (MEA) within M-SAM that enriches the semantic information of medical images with positional data from coarse segmentation masks, facilitating the generation of more precise segmentation masks. Furthermore, an iterative refinement scheme is implemented in M-SAM to refine the segmentation masks progressively, leading to improved performance. Extensive experiments on seven tumor lesion segmentation datasets indicate that our M-SAM not only achieves high segmentation accuracy but also exhibits robust generalization. The code is available at https://github.com/nanase1025/M-SAM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05912 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation Shi, Hairong Han, Songhao Huang, Shaofei Liao, Yue Li, Guanbin Kong, Xiangxing Zhu, Hua Wang, Xiaomu Liu, Si Image and Video Processing Computer Vision and Pattern Recognition Tumor lesion segmentation on CT or MRI images plays a critical role in cancer diagnosis and treatment planning. Considering the inherent differences in tumor lesion segmentation data across various medical imaging modalities and equipment, integrating medical knowledge into the Segment Anything Model (SAM) presents promising capability due to its versatility and generalization potential. Recent studies have attempted to enhance SAM with medical expertise by pre-training on large-scale medical segmentation datasets. However, challenges still exist in 3D tumor lesion segmentation owing to tumor complexity and the imbalance in foreground and background regions. Therefore, we introduce Mask-Enhanced SAM (M-SAM), an innovative architecture tailored for 3D tumor lesion segmentation. We propose a novel Mask-Enhanced Adapter (MEA) within M-SAM that enriches the semantic information of medical images with positional data from coarse segmentation masks, facilitating the generation of more precise segmentation masks. Furthermore, an iterative refinement scheme is implemented in M-SAM to refine the segmentation masks progressively, leading to improved performance. Extensive experiments on seven tumor lesion segmentation datasets indicate that our M-SAM not only achieves high segmentation accuracy but also exhibits robust generalization. The code is available at https://github.com/nanase1025/M-SAM. |
| title | Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.05912 |