CLIP Based Region-Aware Feature Fusion for Automated BBPS Scoring in Colonoscopy Images
This addresses the problem of subjective and variable manual BBPS scoring for clinicians, representing an incremental improvement in automated colonoscopy analysis.
The paper tackles automated assessment of bowel cleanliness in colonoscopy images using the Boston Bowel Preparation Scale (BBPS), proposing a CLIP-based framework that fuses global visual features with stool-related textual priors, achieving superior performance on a new dataset of 2,240 images and a public dataset compared to existing baselines.
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.