Medical SAM adapter: Adapting segment anything model for medical image segmentation

The Segment Anything Model (SAM) has recently gained popularity in the field of image segmentation due to its impressive capabilities in various segmentation tasks and its prompt-based interface. However, recent studies and individual experiments have shown that SAM underperforms in medical image se...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Medical image analysis Ročník 102; s. 103547
Hlavní autoři: Wu, Junde, Wang, Ziyue, Hong, Mingxuan, Ji, Wei, Fu, Huazhu, Xu, Yanwu, Xu, Min, Jin, Yueming
Médium: Journal Article
Jazyk:angličtina
Vydáno: Netherlands Elsevier B.V 01.05.2025
Témata:
Algorithms
Efficient Learning
Fine-Tuning
Humans
Image Interpretation, Computer-Assisted - methods
Image Processing, Computer-Assisted - methods
Imaging, Three-Dimensional - methods
Medical Image Segmentation
Efficient Learning
Fine-Tuning
Medical Image Segmentation
41A10
65D05
65D17
41A05
ISSN:1361-8415, 1361-8423, 1361-8423
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The Segment Anything Model (SAM) has recently gained popularity in the field of image segmentation due to its impressive capabilities in various segmentation tasks and its prompt-based interface. However, recent studies and individual experiments have shown that SAM underperforms in medical image segmentation due to the lack of medical-specific knowledge. This raises the question of how to enhance SAM’s segmentation capability for medical images. We propose the Medical SAM Adapter (Med-SA), which is one of the first methods to integrate SAM into medical image segmentation. Med-SA uses a light yet effective adaptation technique instead of fine-tuning the SAM model, incorporating domain-specific medical knowledge into the segmentation model. We also propose Space-Depth Transpose (SD-Trans) to adapt 2D SAM to 3D medical images and Hyper-Prompting Adapter (HyP-Adpt) to achieve prompt-conditioned adaptation. Comprehensive evaluation experiments on 17 medical image segmentation tasks across various modalities demonstrate the superior performance of Med-SA while updating only 2% of the SAM parameters (13M). Our code is released at https://github.com/KidsWithTokens/Medical-SAM-Adapter. [Display omitted] •We present Med-SA, a simple yet powerful extension of SAM for medical applications.•Our method is one of the first adaption methods to transfer SAM to medical domain.•We propose SD-Trans and HyP-Adpt by considering the real challenges in medical domain.•Experiments on 17 tasks with various modalities establish Med-SA’s superiority.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1361-8415
1361-8423
1361-8423
DOI:10.1016/j.media.2025.103547