Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model

TL;DR

This paper introduces a hybrid model combining YOLOv8 and SAM 2 for efficient polyp segmentation in colonoscopy images and videos, reducing annotation effort while surpassing existing methods in accuracy.

Contribution

The novel integration of YOLOv8 with SAM 2 enables autonomous prompt generation from bounding boxes, improving polyp segmentation without manual annotations.

Findings

Outperforms state-of-the-art models in segmentation accuracy

Reduces annotation time by using bounding box prompts

Effective on multiple benchmark datasets

Abstract

Early diagnosis and treatment of polyps during colonoscopy are essential for reducing the incidence and mortality of Colorectal Cancer (CRC). However, the variability in polyp characteristics and the presence of artifacts in colonoscopy images and videos pose significant challenges for accurate and efficient polyp detection and segmentation. This paper presents a novel approach to polyp segmentation by integrating the Segment Anything Model (SAM 2) with the YOLOv8 model. Our method leverages YOLOv8's bounding box predictions to autonomously generate input prompts for SAM 2, thereby reducing the need for manual annotations. We conducted exhaustive tests on five benchmark colonoscopy image datasets and two colonoscopy video datasets, demonstrating that our method exceeds state-of-the-art models in both image and video segmentation tasks. Notably, our approach achieves high segmentation accuracy using only bounding box annotations, significantly reducing annotation time and effort. This advancement holds promise for enhancing the efficiency and scalability of polyp detection in clinical settings https://github.com/sajjad-sh33/YOLO_SAM2.