CLIP Based Region-Aware Feature Fusion for Automated BBPS Scoring in Colonoscopy Images

TL;DR

This paper introduces a novel CLIP-based feature fusion framework for automated BBPS scoring in colonoscopy images, combining visual and textual features to improve accuracy without segmentation, supported by a new dataset and extensive experiments.

Contribution

The paper presents a new CLIP-based model with adapter transfer learning and fecal feature extraction for automated BBPS scoring, enhancing robustness and accuracy.

Findings

Outperforms existing baselines on multiple datasets

Demonstrates high correlation with expert BBPS scores

Shows potential for clinical application in colonoscopy analysis

Abstract

Accurate assessment of bowel cleanliness is essential for effective colonoscopy procedures. The Boston Bowel Preparation Scale (BBPS) offers a standardized scoring system but suffers from subjectivity and inter-observer variability when performed manually. In this paper, to support robust training and evaluation, we construct a high-quality colonoscopy dataset comprising 2,240 images from 517 subjects, annotated with expert-agreed BBPS scores. We propose a novel automated BBPS scoring framework that leverages the CLIP model with adapter-based transfer learning and a dedicated fecal-feature extraction branch. Our method fuses global visual features with stool-related textual priors to improve the accuracy of bowel cleanliness evaluation without requiring explicit segmentation. Extensive experiments on both our dataset and the public NERTHU dataset demonstrate the superiority of our approach over existing baselines, highlighting its potential for clinical deployment in computer-aided colonoscopy analysis.