Segment Anything in Medical Images and Videos: Benchmark and Deployment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929450913890304 |
|---|---|
| author | Ma, Jun Kim, Sumin Li, Feifei Baharoon, Mohammed Asakereh, Reza Lyu, Hongwei Wang, Bo |
| author_facet | Ma, Jun Kim, Sumin Li, Feifei Baharoon, Mohammed Asakereh, Reza Lyu, Hongwei Wang, Bo |
| contents | Recent advances in segmentation foundation models have enabled accurate and efficient segmentation across a wide range of natural images and videos, but their utility to medical data remains unclear. In this work, we first present a comprehensive benchmarking of the Segment Anything Model 2 (SAM2) across 11 medical image modalities and videos and point out its strengths and weaknesses by comparing it to SAM1 and MedSAM. Then, we develop a transfer learning pipeline and demonstrate SAM2 can be quickly adapted to medical domain by fine-tuning. Furthermore, we implement SAM2 as a 3D slicer plugin and Gradio API for efficient 3D image and video segmentation. The code has been made publicly available at \url{https://github.com/bowang-lab/MedSAM}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_03322 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Segment Anything in Medical Images and Videos: Benchmark and Deployment Ma, Jun Kim, Sumin Li, Feifei Baharoon, Mohammed Asakereh, Reza Lyu, Hongwei Wang, Bo Image and Video Processing Computer Vision and Pattern Recognition Recent advances in segmentation foundation models have enabled accurate and efficient segmentation across a wide range of natural images and videos, but their utility to medical data remains unclear. In this work, we first present a comprehensive benchmarking of the Segment Anything Model 2 (SAM2) across 11 medical image modalities and videos and point out its strengths and weaknesses by comparing it to SAM1 and MedSAM. Then, we develop a transfer learning pipeline and demonstrate SAM2 can be quickly adapted to medical domain by fine-tuning. Furthermore, we implement SAM2 as a 3D slicer plugin and Gradio API for efficient 3D image and video segmentation. The code has been made publicly available at \url{https://github.com/bowang-lab/MedSAM}. |
| title | Segment Anything in Medical Images and Videos: Benchmark and Deployment |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.03322 |