Deep learning-based assessment of ulcerative colitis activity from full-length endoscopic videos with spatial characterisation and histological correlation
- 1Perspectum Ltd
Abstract
Background and study aimsEndoscopic assessment of ulcerative colitis (UC) is central to clinical decision-making however remains subjective and limited in characterisation of disease distribution. Artificial intelligence (AI) enables analysis of entire endoscopic examination, rather than relying on selected views. We aimed to develop and validate a deep learning model for automated assessment of UC severity from full-length endoscopic videos, introducing spatial representation of inflammation (Continuous Disease Score, CDS), and assess histological correlation.
Patients and methodsFull-length endoscopy videos from adult patients with UC undergoing colonoscopy or flexible sigmoidoscopy were analysed; isolated proctitis was excluded. Videos were segmented and annotated using Mayo Endoscopic Score (MES) and Ulcerative Colitis Endoscopic Index of Activity (UCEIS). A deep learning model was trained for frame-level quality control and severity prediction, enabling analysis of full-length videos. Performance was evaluated using quadratic weighted kappa (QWK) and Cohens kappa, with patient-level separation between datasets. CDS was derived from UCEIS predictions to quantify cumulative inflammatory burden, spatial extent of disease and histological prediction.
ResultsA total of 67 videos from 59 patients were included. The model demonstrated agreement for remission classification (MES=0 {kappa} 0.76; UCEIS[≤]1 {kappa} 0.84). CDS enabled quantification of inflammatory burden and revealed spatial heterogeneity not reflected in categorical scores. Agreement with histology was strong (AUROC 0.84-0.87).
ConclusionsAI-based analysis enables automated assessment of UC activity from full-length endoscopic videos, including remission detection and estimation of histological healing. CDS provides continuous characterisation of inflammatory burden and disease extent beyond conventional categorical scores, with potential to support more standardised assessment in clinical trials and practice.
Related
- Bowel Urgency Is More Strongly Associated with Biochemical, Endoscopic, and Histological Disease Activity than Other Clinical Symptoms in Ulcerative Colitis
- Pitfalls and challenges in endoscopic assessment of ulcerative colitis.
- Automated assessment of the ulcerative colitis endoscopic index of severity using a multi-task deep learning model
- Bilirubin statistically accounts for the association between Enterobacterales lineage and Mayo endoscopic score in ulcerative colitis: a cross-sectional associational variable analysis.
- Diagnostic prediction of ulcerative colitis using simplified endoscopic features and blood count-derived indices: a multicenter study
BibTeX
@misc{bogush2026deep,
title = {{Deep learning-based assessment of ulcerative colitis activity from full-length endoscopic videos with spatial characterisation and histological correlation}},
author = {A. Bogush and A. Toskas and G. Ralli and D. Windell and P. Aljabar and M. DeLegge and A. Walsh and J. P. Thomas and P. Wakefield and C. Langford and E. Fryer and R. Goldin and N. Suzuki and J. Landy},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.16.26363201},
url = {https://www.medrxiv.org/content/10.64898/2026.09.16.26363201v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Deep learning-based assessment of ulcerative colitis activity from full-length endoscopic videos with spatial characterisation and histological correlation
AU - A. Bogush
AU - A. Toskas
AU - G. Ralli
AU - D. Windell
AU - P. Aljabar
AU - M. DeLegge
AU - A. Walsh
AU - J. P. Thomas
AU - P. Wakefield
AU - C. Langford
AU - E. Fryer
AU - R. Goldin
AU - N. Suzuki
AU - J. Landy
PY - 2026
DA - 2026/09/16
PB - medRxiv
DO - 10.64898/2026.09.16.26363201
UR - https://www.medrxiv.org/content/10.64898/2026.09.16.26363201v1
AB - Background and study aimsEndoscopic assessment of ulcerative colitis (UC) is central to clinical decision-making however remains subjective and limited in characterisation of disease distribution. Artificial intelligence (AI) enables analysis of entire endoscopic examination, rather than relying on selected views. We aimed to develop and validate a deep learning model for automated assessment of UC severity from full-length endoscopic videos, introducing spatial representation of inflammation (Continuous Disease Score, CDS), and assess histological correlation. Patients and methodsFull-length endoscopy videos from adult patients with UC undergoing colonoscopy or flexible sigmoidoscopy were analysed; isolated proctitis was excluded. Videos were segmented and annotated using Mayo Endoscopic Score (MES) and Ulcerative Colitis Endoscopic Index of Activity (UCEIS). A deep learning model was trained for frame-level quality control and severity prediction, enabling analysis of full-length videos. Performance was evaluated using quadratic weighted kappa (QWK) and Cohens kappa, with patient-level separation between datasets. CDS was derived from UCEIS predictions to quantify cumulative inflammatory burden, spatial extent of disease and histological prediction. ResultsA total of 67 videos from 59 patients were included. The model demonstrated agreement for remission classification (MES=0 {kappa} 0.76; UCEIS[≤]1 {kappa} 0.84). CDS enabled quantification of inflammatory burden and revealed spatial heterogeneity not reflected in categorical scores. Agreement with histology was strong (AUROC 0.84-0.87). ConclusionsAI-based analysis enables automated assessment of UC activity from full-length endoscopic videos, including remission detection and estimation of histological healing. CDS provides continuous characterisation of inflammatory burden and disease extent beyond conventional categorical scores, with potential to support more standardised assessment in clinical trials and practice.
ER -