Polyp-SAM: transfer SAM for polyp segmentation

Yuheng Li; Mingzhe Hu; Xiaofeng Yang

doi:10.1117/12.3006809

3 April 2024 Polyp-SAM: transfer SAM for polyp segmentation

Yuheng Li, Mingzhe Hu, Xiaofeng Yang

Proceedings Volume 12927, Medical Imaging 2024: Computer-Aided Diagnosis; 1292735 (2024) https://doi.org/10.1117/12.3006809
Event: SPIE Medical Imaging, 2024, San Diego, California, United States

Conference Poster

Abstract

Automatic segmentation of colon polyps can significantly reduce the misdiagnosis of colon cancer and improve physician annotation efficiency. While many methods have been proposed for polyp segmentation, training large-scale segmentation networks with limited colonoscopy data remains a challenge. Recently, the Segment Anything Model (SAM) has recently gained much attention in both natural image and medical image segmentation. SAM demonstrates superior performance in several vision benchmarks and shows great potential for medical image segmentation. In this study, we propose Poly-SAM, a finetuned SAM model for polyp segmentation, and compare its performance to several state-of-the-art polyp segmentation models. We also compare two transfer learning strategies of SAM with and without finetuning its encoders. Evaluated on five public datasets, our Polyp-SAM achieves state-of-the-art performance on two datasets and impressive performance on three datasets, with dice scores all above 88%. This study demonstrates the great potential of adapting SAM to medical image segmentation tasks.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yuheng Li, Mingzhe Hu, and Xiaofeng Yang "Polyp-SAM: transfer SAM for polyp segmentation ", Proc. SPIE 12927, Medical Imaging 2024: Computer-Aided Diagnosis, 1292735 (3 April 2024); https://doi.org/10.1117/12.3006809

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available