The reviewed record of science sign in
Pith

arxiv: 2412.16723 · v1 · pith:XIEH4TDD · submitted 2024-12-21 · cs.CV

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

Reviewed by Pithpith:XIEH4TDDopen to challenge →

classification cs.CV
keywords bleedingsegmentationclassificationgroundingmodeltwo-stagechallengedetection
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection -- after competition results

    cs.CV 2026-05 unverdicted novelty 3.0

    VISTA combines EndoFM-LV and DINOv3 with Diverse Head Ensemble, Validation-Guided Weighted Fusion, and Anatomy-Aware Temporal Event Decoding to reach 0.3726 mAP@0.5 on hidden test for rare-pathology VCE event detectio...