Publication Name	World Journal of Gastroenterology
Manuscript ID	125066
DOI	10.3748/wjg.125066
Country	China

Category	Gastroenterology & Hepatology
Manuscript Type	Retrospective Study
Article Title	Development and validation of a deep learning-based multitask model for multidimensional quality assessment of colonic endocytoscopic images
Manuscript Source	Unsolicited Manuscript
All Author List	Jia-Wei Fan, Ming-Qing Liu, Ke Tao, Feng-Ming Ni, Dong Yang, Guo-Hua Jin, Jun Gao, He Zhu and Hong Xu
Funding Agency and Grant Number	Funding Agency Grant Number Ministry of Science and Technology of China 2022YFE0118100 Natural Science Foundation of Jilin Province YDZJ202601ZYTS558
Corresponding Author	Hong Xu, PhD, Professor, Department of Gastroenterology, The First Hospital of Jilin University, No. 71 Xinmin Street, Changchun 130021, Jilin Province, China. x_hong@jlu.edu.cn
Key Words	Endocytoscopy; Image quality assessment; Deep learning; Multitask learning; Artificial intelligence
Core Tip	This study introduces Endocytoscopic Image Quality Assessment via Multitask Learning, a multitask deep-learning framework for standardized quality assessment of endocytoscopy images. By combining degradation-aware self-supervised pre-training with multidimensional supervised learning, the system simultaneously grades overall image quality and identifies specific deficits in structure clarity, stain wash, focus, and brightness. The model showed promising performance in internal and external test sets, and junior endoscopists performed better during subsequent artificial intelligence-assisted image quality assessment. Its structured feedback and rapid inference may support standardized image acquisition and future real-time quality control.
Citation	Fan JW, Liu MQ, Tao K, Ni FM, Yang D, Jin GH, Gao J, Zhu H, Xu H. Development and validation of a deep learning-based multitask model for multidimensional quality assessment of colonic endocytoscopic images. World J Gastroenterol 2026; In press DOI: https://doi.org/10.3748/wjg.125066
PDF	125066-in-press.pdf

Received	2026-06-30 08:18
Peer-Review Started	2026-06-30 09:21
First Decision by Editorial Office Director
Return for Revision	2026-08-05 07:02
Revised	2026-08-15 18:42
Publication Fee Transferred	2026-09-14 13:10
Second Decision by Editor	2026-10-13 06:01
Second Decision by Editor-in-Chief
Final Decision by Editorial Office Director	2026-10-13 09:50
Articles in Press	2026-10-13 09:50
Edit the Manuscript by Language Editor
Typeset the Manuscript

ISSN	1007-9327 (print) and 2219-2840 (online)
Open Access	This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/Licenses/by-nc/4.0/
Copyright	©Author(s) (or their employer(s)) 2026. No commercial re-use. See Permissions. Published by Baishideng Publishing Group Inc.
Permissions	For details, please visit: http://www.wjgnet.com/bpg/gerinfo/207
Publisher	Baishideng Publishing Group Inc, 7041 Koll Center Parkway, Suite 160, Pleasanton, CA 94566, USA
Website	http://www.wjgnet.com