Development of a Novel Real-Time Computer-Assisted Colonoscopy Diagnostic Tool for Colorectal Neoplasia and Cancer to Enable Personalized Patient Management: Protocol for a Multicenter Proof-of-Concept Study.

@article{olabintan2026development,
  title = {{Development of a Novel Real-Time Computer-Assisted Colonoscopy Diagnostic Tool for Colorectal Neoplasia and Cancer to Enable Personalized Patient Management: Protocol for a Multicenter Proof-of-Concept Study.}},
  author = {Olaolu Olabintan and Angelo Brunori and Natalie Halvorsen and Nils Andersen and Verónica G Zubiaurre and Mehrnaz Mirzaei and Ina Dam Pedersen and Alessandro D'Aprano and Johnathan Sun and Ahmed Ghazwan Waraich and Omer Ahmad and Nastazja Pilonis and Michal Kaminski and Francisco Lamosa and Rune Erichsen and Johannes Blom and Thomas Rosch and Maria Pellise and Ignasi Puig and Cesare Hassan and Kensaku Mori and Yuichi Mori and Massashi Misawa and Shraddha Gulati},
  journal = {JMIR research protocols},
  year = {2026},
  month = oct,
  doi = {10.2196/77277},
  url = {https://europepmc.org/article/MED/42905971},
  note = {CC BY},
}

TY  - JOUR
TI  - Development of a Novel Real-Time Computer-Assisted Colonoscopy Diagnostic Tool for Colorectal Neoplasia and Cancer to Enable Personalized Patient Management: Protocol for a Multicenter Proof-of-Concept Study.
AU  - Olaolu Olabintan
AU  - Angelo Brunori
AU  - Natalie Halvorsen
AU  - Nils Andersen
AU  - Verónica G Zubiaurre
AU  - Mehrnaz Mirzaei
AU  - Ina Dam Pedersen
AU  - Alessandro D'Aprano
AU  - Johnathan Sun
AU  - Ahmed Ghazwan Waraich
AU  - Omer Ahmad
AU  - Nastazja Pilonis
AU  - Michal Kaminski
AU  - Francisco Lamosa
AU  - Rune Erichsen
AU  - Johannes Blom
AU  - Thomas Rosch
AU  - Maria Pellise
AU  - Ignasi Puig
AU  - Cesare Hassan
AU  - Kensaku Mori
AU  - Yuichi Mori
AU  - Massashi Misawa
AU  - Shraddha Gulati
PY  - 2026
DA  - 2026/10/21
JO  - JMIR research protocols
DO  - 10.2196/77277
UR  - https://europepmc.org/article/MED/42905971
AB  - Background  Accurate real-time classification of colorectal polyps during colonoscopy is essential for risk stratification, therapeutic decision-making, and surveillance planning, with important implications for colorectal cancer prevention, health care costs, and patient burden. Despite advances in optical diagnosis techniques, including virtual chromoendoscopy and magnification, widespread adoption remains limited because of high operator dependency and variable diagnostic accuracy. Existing computer-assisted diagnosis (CADx) systems predominantly provide binary classification of colorectal lesions, thereby constraining their clinical utility for nuanced endoscopic decision-making.Objective  This study aims to develop and validate a real-time, multiclass AI-based CADx system capable of classifying colorectal lesions into 5 categories: nonneoplastic lesions, low-grade adenomas, high-grade adenomas, sessile serrated lesions (SSL), and invasive colorectal cancer.Methods  This multicenter international study consists of 2 phases: model development and proof-of-concept validation. During the model development phase, a large, diverse dataset of >17,000 deidentified endoscopic images and video frames will be prospectively collected from 8 European centers and 1 Japanese center, capturing a broad spectrum of lesion types and patient demographics. A semisupervised learning framework using contrastive representation learning (SimCLR [simple framework for contrastive learning of visual representations]) will be used to leverage both labeled and unlabeled data, enhancing feature extraction and classification performance. Expert consensus annotation will be used for labeled data. Lesion localization will be supported by an integrated computer-assisted detection (CADe) module, while model interpretability will be facilitated through gradient-weighted class activation mapping (Grad-CAM). Proof-of-concept validation will be conducted using 250 previously unseen lesion images that will be independently assessed by expert endoscopists. The primary outcome is multiclass diagnostic accuracy, with a predefined target accuracy threshold of 85%, alongside sensitivity and specificity for invasive cancer detection. Secondary outcomes include interobserver agreement, performance across demographic and lesion subgroups, and a qualitative analysis of misclassification patterns. All data will be securely managed within a REDCap database, with strict deidentification protocols and plans to generate an open-access research resource.Results  Ethics approval has been obtained at all participating centres. Data transfer agreements have been executed by the majority of collaborating sites, with de-identified polyp images and videos currently being uploaded to a secure central database.Conclusions  This study aims to deliver a clinically applicable, real-time multiclass CADx system that extends beyond current binary AI models and supports more granular, personalized endoscopic decision-making. By integrating semisupervised learning, diverse international data, and explainable AI techniques, this approach has the potential to substantially advance the methodological foundations and clinical utility of AI-assisted optical diagnosis in routine colonoscopy, contributing to improved colorectal cancer prevention and patient care.
SN  - 1929-0748
ER  -