Can SAM Segment Polyps?

Tao Zhou, Yizhe Zhang, Yi Zhou, Ye Wu, Chen Gong
4/15/2023
cs.CV

No official code found. Best implementation: taozh2017/Awesome-Polyp-Segmentation (202 stars, last commit 2024-09-21).

Abstract

Recently, Meta AI Research releases a general Segment Anything Model (SAM), which has demonstrated promising performance in several segmentation tasks. As we know, polyp segmentation is a fundamental task in the medical imaging field, which plays a critical role in the diagnosis and cure of colorectal cancer. In particular, applying SAM to the polyp segmentation task is interesting. In this report, we evaluate the performance of SAM in segmenting polyps, in which SAM is under unprompted settings. We hope this report will provide insights to advance this polyp segmentation field and promote more interesting works in the future. This project is publicly at https://github.com/taozh2017/SAMPolyp.

View on arXivView PDF

Code Implementations(1)

taozh2017/Awesome-Polyp-SegmentationCommunity100%
20222Apr 13, 20232 years ago

Similar Papers

Polyp-SAM: Transfer SAM for Polyp Segmentation

90% match1 repo322023

ProMamba: Prompt-Mamba for polyp segmentation

90% match2024

Polyp-SAM++: Can A Text Guided SAM Perform Better for Polyp Segmentation?

89% match1 repo132023

ASPS: Augmented Segment Anything Model for Polyp Segmentation

88% match1 repo492024

Polyp-E: Benchmarking the Robustness of Deep Segmentation Models via Polyp Editing

88% match1 repo12024

Multi-scale and Multi-path Cascaded Convolutional Network for Semantic Segmentation of Colorectal Polyps

88% match2024

Cite this paper

@article{zhou2023segment,
  title  = {Can SAM Segment Polyps?},
  author = {Tao Zhou and Yizhe Zhang and Yi Zhou and Ye Wu and Chen Gong},
  year   = {2023},
  eprint = {2304.07583},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2304.07583v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2304.07583.svg)](https://codeofpaper.com/paper/2304.07583)

Discussion