Polyp SAM 2: Advancing Zero shot Polyp Segmentation in Colorectal Cancer Detection

TL;DR

This paper evaluates the Segment Anything Model 2 (SAM 2) for zero-shot polyp segmentation in colorectal cancer detection, highlighting its potential to improve segmentation accuracy without extensive annotations.

Contribution

It provides the first comprehensive assessment of SAM 2's performance in polyp segmentation, demonstrating its effectiveness across various prompted settings.

Findings

SAM 2 achieves promising segmentation results without training on polyp data.

The model performs well across different prompting scenarios.

Insights are provided to guide future polyp segmentation research.

Abstract

Polyp segmentation plays a crucial role in the early detection and diagnosis of colorectal cancer. However, obtaining accurate segmentations often requires labor-intensive annotations and specialized models. Recently, Meta AI Research released a general Segment Anything Model 2 (SAM 2), which has demonstrated promising performance in several segmentation tasks. In this manuscript, we evaluate the performance of SAM 2 in segmenting polyps under various prompted settings. We hope this report will provide insights to advance the field of polyp segmentation and promote more interesting work in the future. This project is publicly available at https://github.com/ sajjad-sh33/Polyp-SAM-2.