2025 International Conference on Machine Learning and Applications (ICMLA)

A Multi-Stage Machine Learning Pipeline for Automated Bowel Preparation Scale Assessment in Colonoscopy Videos

Yiqin He, Qilei Chen, Ke Wan, Alimire Nabijiang, Yu Cao, Benyuan Liu

2025 International Conference on Machine Learning and Applications (ICMLA)


Abstract

Accurate assessment of intestinal cleanliness is essential for effective colonoscopy, but manual scoring with the Boston Bowel Preparation Scale (BBPS) remains subjective and labor-intensive. In this study, we propose a novel, fully automated multi-stage pipeline for objective BBPS-based bowel preparation assessment in colonoscopy videos. Our approach utilizes deep image classifiers, enhanced by a hierarchical sequence of binary classification tasks, to assign precise frame-level BBPS scores. From the resulting sequence of scores, we extract statistical and temporal features to train machine learning regression models for video-level BBPS prediction. Extensive experiments demonstrate that our pipeline achieves robust, reproducible, and granular video-level bowel cleanliness assessment, outperforming standard multi-class models at the frame level and offering a scalable tool for large-scale endoscopic quality analysis.


BibTeX

@INPROCEEDINGS{11471382, author={He, Yiqin and Chen, Qilei and Wan, Ke and Nabijiang, Alimire and Cao, Yu and Liu, Benyuan}, booktitle={2025 International Conference on Machine Learning and Applications (ICMLA)}, title={A Multi-Stage Machine Learning Pipeline for Automated Bowel Preparation Scale Assessment in Colonoscopy Videos}, year={2025}, volume={}, number={}, pages={302-309}, keywords={Filtering;Filters;Videos;Computer networks;Storage area networks;Video equipment;Wide area networks;Protocols;Communication systems;HTTP;Image classification;Machine learning;Colonoscopy}, doi={10.1109/ICMLA66185.2025.00047}}