Divide and Conquer: Grounding a Bleeding Areas in Gastrointestinal Image with Two-Stage Model

TL;DR

This paper introduces a two-stage model for gastrointestinal bleeding detection and segmentation that improves accuracy and robustness by decoupling classification from grounding, validated on a challenging dataset.

Contribution

The study presents a novel two-stage framework that separates classification and grounding tasks, enhancing performance over traditional multi-task models in GI bleeding analysis.

Findings

Achieved second place on Auto-WCEBleedGen Challenge V2 dataset.

Significant improvements in classification accuracy.

Enhanced segmentation precision, especially on sequential datasets.

Abstract

Accurate detection and segmentation of gastrointestinal bleeding are critical for diagnosing diseases such as peptic ulcers and colorectal cancer. This study proposes a two-stage framework that decouples classification and grounding to address the inherent challenges posed by traditional Multi-Task Learning models, which jointly optimizes classification and segmentation. Our approach separates these tasks to achieve targeted optimization for each. The model first classifies images as bleeding or non-bleeding, thereby isolating subsequent grounding from inter-task interference and label heterogeneity. To further enhance performance, we incorporate Stochastic Weight Averaging and Test-Time Augmentation, which improve model robustness against domain shifts and annotation inconsistencies. Our method is validated on the Auto-WCEBleedGen Challenge V2 Challenge dataset and achieving second place. Experimental results demonstrate significant improvements in classification accuracy and segmentation precision, especially on sequential datasets with consistent visual patterns. This study highlights the practical benefits of a two-stage strategy for medical image analysis and sets a new standard for GI bleeding detection and segmentation. Our code is publicly available at this GitHub repository.