SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Images
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910602894508032 |
|---|---|
| author | Wang, Haoyu Guo, Sizheng Ye, Jin Deng, Zhongying Cheng, Junlong Li, Tianbin Chen, Jianpin Su, Yanzhou Huang, Ziyan Shen, Yiqing Fu, Bin Zhang, Shaoting He, Junjun Qiao, Yu |
| author_facet | Wang, Haoyu Guo, Sizheng Ye, Jin Deng, Zhongying Cheng, Junlong Li, Tianbin Chen, Jianpin Su, Yanzhou Huang, Ziyan Shen, Yiqing Fu, Bin Zhang, Shaoting He, Junjun Qiao, Yu |
| contents | Existing volumetric medical image segmentation models are typically task-specific, excelling at specific target but struggling to generalize across anatomical structures or modalities. This limitation restricts their broader clinical use. In this paper, we introduce SAM-Med3D for general-purpose segmentation on volumetric medical images. Given only a few 3D prompt points, SAM-Med3D can accurately segment diverse anatomical structures and lesions across various modalities. To achieve this, we gather and process a large-scale 3D medical image dataset, SA-Med3D-140K, from a blend of public sources and licensed private datasets. This dataset includes 22K 3D images and 143K corresponding 3D masks. Then SAM-Med3D, a promptable segmentation model characterized by the fully learnable 3D structure, is trained on this dataset using a two-stage procedure and exhibits impressive performance on both seen and unseen segmentation targets. We comprehensively evaluate SAM-Med3D on 16 datasets covering diverse medical scenarios, including different anatomical structures, modalities, targets, and zero-shot transferability to new/unseen tasks. The evaluation shows the efficiency and efficacy of SAM-Med3D, as well as its promising application to diverse downstream tasks as a pre-trained model. Our approach demonstrates that substantial medical resources can be utilized to develop a general-purpose medical AI for various potential applications. Our dataset, code, and models are available at https://github.com/uni-medical/SAM-Med3D. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_15161 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Images Wang, Haoyu Guo, Sizheng Ye, Jin Deng, Zhongying Cheng, Junlong Li, Tianbin Chen, Jianpin Su, Yanzhou Huang, Ziyan Shen, Yiqing Fu, Bin Zhang, Shaoting He, Junjun Qiao, Yu Computer Vision and Pattern Recognition Existing volumetric medical image segmentation models are typically task-specific, excelling at specific target but struggling to generalize across anatomical structures or modalities. This limitation restricts their broader clinical use. In this paper, we introduce SAM-Med3D for general-purpose segmentation on volumetric medical images. Given only a few 3D prompt points, SAM-Med3D can accurately segment diverse anatomical structures and lesions across various modalities. To achieve this, we gather and process a large-scale 3D medical image dataset, SA-Med3D-140K, from a blend of public sources and licensed private datasets. This dataset includes 22K 3D images and 143K corresponding 3D masks. Then SAM-Med3D, a promptable segmentation model characterized by the fully learnable 3D structure, is trained on this dataset using a two-stage procedure and exhibits impressive performance on both seen and unseen segmentation targets. We comprehensively evaluate SAM-Med3D on 16 datasets covering diverse medical scenarios, including different anatomical structures, modalities, targets, and zero-shot transferability to new/unseen tasks. The evaluation shows the efficiency and efficacy of SAM-Med3D, as well as its promising application to diverse downstream tasks as a pre-trained model. Our approach demonstrates that substantial medical resources can be utilized to develop a general-purpose medical AI for various potential applications. Our dataset, code, and models are available at https://github.com/uni-medical/SAM-Med3D. |
| title | SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.15161 |