Biomedical SAM 2: Segment Anything in Biomedical Images and Videos
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913470769790976 |
|---|---|
| author | Yan, Zhiling Sun, Weixiang Zhou, Rong Yuan, Zhengqing Zhang, Kai Li, Yiwei Liu, Tianming Li, Quanzheng Li, Xiang He, Lifang Sun, Lichao |
| author_facet | Yan, Zhiling Sun, Weixiang Zhou, Rong Yuan, Zhengqing Zhang, Kai Li, Yiwei Liu, Tianming Li, Quanzheng Li, Xiang He, Lifang Sun, Lichao |
| contents | Medical image segmentation and video object segmentation are essential for diagnosing and analyzing diseases by identifying and measuring biological structures. Recent advances in natural domain have been driven by foundation models like the Segment Anything Model 2 (SAM-2). To explore the performance of SAM-2 in biomedical applications, we designed three evaluation pipelines for single-frame 2D image segmentation, multi-frame 3D image segmentation and multi-frame video segmentation with varied prompt designs, revealing SAM-2's limitations in medical contexts. Consequently, we developed BioSAM-2, an enhanced foundation model optimized for biomedical data based on SAM-2. Our experiments show that BioSAM-2 not only surpasses the performance of existing state-of-the-art foundation models but also matches or even exceeds specialist models, demonstrating its efficacy and potential in the medical domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_03286 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Biomedical SAM 2: Segment Anything in Biomedical Images and Videos Yan, Zhiling Sun, Weixiang Zhou, Rong Yuan, Zhengqing Zhang, Kai Li, Yiwei Liu, Tianming Li, Quanzheng Li, Xiang He, Lifang Sun, Lichao Computer Vision and Pattern Recognition Medical image segmentation and video object segmentation are essential for diagnosing and analyzing diseases by identifying and measuring biological structures. Recent advances in natural domain have been driven by foundation models like the Segment Anything Model 2 (SAM-2). To explore the performance of SAM-2 in biomedical applications, we designed three evaluation pipelines for single-frame 2D image segmentation, multi-frame 3D image segmentation and multi-frame video segmentation with varied prompt designs, revealing SAM-2's limitations in medical contexts. Consequently, we developed BioSAM-2, an enhanced foundation model optimized for biomedical data based on SAM-2. Our experiments show that BioSAM-2 not only surpasses the performance of existing state-of-the-art foundation models but also matches or even exceeds specialist models, demonstrating its efficacy and potential in the medical domain. |
| title | Biomedical SAM 2: Segment Anything in Biomedical Images and Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.03286 |