Academic Journal
EndoClean: A Hybrid Deep Learning Framework for Automated Full-Video Boston Bowel Preparation Scale Assessment.
| Title: | EndoClean: A Hybrid Deep Learning Framework for Automated Full-Video Boston Bowel Preparation Scale Assessment. |
|---|---|
| Authors: | Zhu Y; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, China.; Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai 200032, China.; Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention, Shanghai 200032, China.; Shanghai Collaborative Innovation Center of Endoscopy, Shanghai 200032, China., Li SY; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, China.; Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai 200032, China.; Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention, Shanghai 200032, China., Fu PY; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, China.; Shanghai Collaborative Innovation Center of Endoscopy, Shanghai 200032, China., Zhang Z; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, China.; Shanghai Collaborative Innovation Center of Endoscopy, Shanghai 200032, China., Wang S; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, China.; Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai 200032, China.; Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention, Shanghai 200032, China.; Shanghai Collaborative Innovation Center of Endoscopy, Shanghai 200032, China.; Data Science Institute, Imperial College London, London SW7 2AZ, UK., Li QL; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, China.; Shanghai Collaborative Innovation Center of Endoscopy, Shanghai 200032, China., Zhou PH; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, China.; Shanghai Collaborative Innovation Center of Endoscopy, Shanghai 200032, China. |
| Source: | Bioengineering (Basel, Switzerland) [Bioengineering (Basel)] 2026 Mar 02; Vol. 13 (3). Date of Electronic Publication: 2026 Mar 02. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: MDPI AG Country of Publication: Switzerland NLM ID: 101676056 Publication Model: Electronic Cited Medium: Print ISSN: 2306-5354 (Print) Linking ISSN: 23065354 NLM ISO Abbreviation: Bioengineering (Basel) Subsets: PubMed not MEDLINE |
| Imprint Name(s): | Original Publication: Basel, Switzerland : MDPI AG, [2014]- |
| Abstract: | Background and Aims: Adequate bowel preparation is the cornerstone of high-quality colonoscopy. The Boston Bowel Preparation Scale (BBPS) is the gold standard for assessment, yet its application suffers from inter-observer variability and lacks a fully automated solution for entire video analysis. This study proposes EndoClean, a novel, fully automated deep learning framework designed to compute the full-segment BBPS score from colonoscopy videos, aiming to provide a standardized, objective, and near expert-level assessment. Methods: EndoClean integrates three distinct models: frame selection, anatomical segmentation, and BBPS scoring. Its performance was rigorously evaluated against a reference standard established by senior experts and compared with junior endoscopists. We assessed assessment precision, inter-rater agreement (quadratic weighted Kappa), and consistency across all colonic segments. Results: The EndoClean system demonstrated superior reliability, achieving a global accuracy of 97.8% for the total BBPS score, with satisfying agreement with senior experts (κ = 0.984; 95% CI: 0.976-0.989). Notably, EndoClean performed significantly better than junior endoscopists in overall BBPS agreements (κ: 0.984 vs. 0.949, p < 0.001) and overall accuracy (97.8% vs. 94.6%, p = 0.037). In segment-specific analysis, the EndoClean surpassed junior doctors particularly in the transverse colon (Accuracy: 97.5% vs. 90.4%, p < 0.001) and effectively reduced misclassifications in clinically ambiguous intermediate scores. For binary adequacy classification, the system achieved a sensitivity of 98.2% and a specificity of 97.3%. Conclusions: EndoClean represents a robust solution in automated quality control, demonstrating performance comparable to senior experts in bowel preparation assessment. By significantly reducing the variability seen in junior endoscopists and providing objective, full-video BBPS scoring, this framework offers a viable, standardized, and efficient solution for clinical practice and large-scale quality monitoring. |
| References: | Gastrointest Endosc. 2022 Mar;95(3):512-518.e1. (PMID: 34896100) Gastrointest Endosc. 2025 Jun;101(6):1201-1210. (PMID: 39557204) Best Pract Res Clin Gastroenterol. 2023 Oct;66:101838. (PMID: 37852706) Prz Gastroenterol. 2019;14(2):89-103. (PMID: 31616522) Gastrointest Endosc. 2024 Sep;100(3):352-381. (PMID: 39177519) Endosc Int Open. 2025 Jul 01;13:a26256327. (PMID: 40611829) Dig Dis Sci. 2025 May;70(5):1595-1605. (PMID: 39666212) Sci Data. 2025 Aug 7;12(1):1382. (PMID: 40775217) BMJ Open Gastroenterol. 2019 Jan 24;6(1):e000254. (PMID: 30740233) Br J Hosp Med (Lond). 2025 Jan 24;86(1):1-11. (PMID: 39862028) Endosc Int Open. 2018 Aug;6(8):E1044-E1050. (PMID: 30105292) J Gastroenterol Hepatol. 2024 Sep;39(9):1917-1923. (PMID: 38766682) Gastrointest Endosc. 2024 Oct;100(4):728-736.e9. (PMID: 38636818) Front Med (Lausanne). 2023 Dec 18;10:1296249. (PMID: 38164219) |
| Contributed Indexing: | Keywords: Boston bowel preparation scale; EndoClean; artificial intelligence; bowel preparation; colonoscopy; deep learning |
| Entry Date(s): | Date Created: 20260328 Date Completed: 20260328 Latest Revision: 20260813 |
| Update Code: | 20260813 |
| PubMed Central ID: | PMC13023680 |
| DOI: | 10.3390/bioengineering13030294 |
| PMID: | 41899825 |
| Database: | MEDLINE |
| ISSN: | 2306-5354 |
|---|---|
| DOI: | 10.3390/bioengineering13030294 |