UCtracker: A Deep Learning–Based DNA Methylation Model for Noninvasive Diagnosis and Recurrence Surveillance of Urothelial Carcinoma in a Prospective Study
Advanced Science · 2026
DOI: 10.1002/advs.76710 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, 2026. Verfasst von Shengwei Xiong und 19 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, Institute of Urology, Beijing Key Laboratory of Precision Medicine and Innovative Translation for Urogenital Diseases, Peking …. Hauptthemen laut MEDLINE: Deep Learning, DNA Methylation, Neoplasm Recurrence, Local, Urinary Bladder Neoplasms. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Science and Technology Plan-Capital Clinical Diagnosis, Treatment Technology Research and Demonstration Application, Natural Science Foundation of China.
Abstract (Originalsprache)
Noninvasive diagnosis and longitudinal surveillance of urothelial carcinoma (UC) remain clinically challenging. Here, we developed and prospectively validate UCtracker, a urine DNA methylation–based deep learning model for UC detection and postoperative recurrence monitoring. UC‐specific differentially methylated regions (DMRs) were identified by high‐depth whole‐genome bisulfite sequencing of UC tissues, paired adjacent normal tissues, and non‐tumor urine samples. UCtracker was constructed using the top 2000 hypomethylated DMRs and a convolutional neural network–bidirectional long short‐term memory architecture. In an internal validation cohort ( n = 165), UCtracker achieved a sensitivity of 94.6% and a specificity of 94.4%, and maintained high performance in an independent multicenter cohort ( n = 55), with a sensitivity of 90.6% and a specificity of 91.3%. UCtracker showed higher sensitivity than UroVysion fluorescence in situ hybridization for T1 tumors, high‐grade tumors, and bladder UC. Subsampling analyses demonstrated stable diagnostic performance even at ultralow sequencing depths. In postoperative surveillance, longitudinal urine profiling of 131 samples from 48 UC patients detected 94.1% of recurrence events and identified recurrence up to 250 days before clinical confirmation. These findings support UCtracker as a highly accurate and cost‐effective urine‐based tool for UC diagnosis, postoperative surveillance, and personalized patient management.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Urology, Institute of Urology, Beijing Key Laboratory of Precision Medicine and Innovative Translation for Urogenital Diseases, Peking University First Hospital, National Urological Cancer Center, Peking U…
- China National Center for Bioinformation, Beijing Institute of Genomics, Chinese Academy of Sciences, Beijing, China.
- Institute for Regenerative Biology and Medicine, Chinese Institutes for Medical Research, Beijing, China.
- Department of Urology, Beijing Chao-Yang Hospital, Institute of Urology, Capital Medical University, Beijing, China.
- Department of Urology, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
- Department of Urology, Chinese PLA General Hospital, Beijing, China.
ORCID-Profile: Shengwei Xiong, Yucai Wu, Yanqing Gong, Xuesong Li
Förderung
- Beijing Science and Technology Plan-Capital Clinical Diagnosis
- Treatment Technology Research and Demonstration Application
- Natural Science Foundation of China
- Capital's Funds for Health Improvement and Research
- National High Level Hospital Clinical Research Funding
- National Health Commission Capacity Building and Continuing Education Center
- National Key R&D Program of China
- Beijing Municipal Health Commission Research Ward Excellence Clinical Research Program
Zitieren
APA
Xiong, S., Li, G., Wu, Y., Liang, Y., Guo, H., Zhang, Y., Xiong, G., Tian, L., Zhang, X., Tian, Y., Ji, Z., Guo, B., Shi, Y., Fan, J., Li, Z., Gong, Y., He, S., Li, X., Ci, W., & Zhou, L. (2026). UCtracker: A Deep Learning–Based DNA Methylation Model for Noninvasive Diagnosis and Recurrence Surveillance of Urothelial Carcinoma in a Prospective Study. Advanced Science. https://doi.org/10.1002/advs.76710
Vancouver
Xiong S, Li G, Wu Y, Liang Y, Guo H, Zhang Y, et al. UCtracker: A Deep Learning–Based DNA Methylation Model for Noninvasive Diagnosis and Recurrence Surveillance of Urothelial Carcinoma in a Prospective Study. Advanced Science. 2026. doi:10.1002/advs.76710
BibTeX
@article{Xiong2026,
author = {Xiong, Shengwei and Li, Gaojie and Wu, Yucai and Liang, Yuan and Guo, Heng and Zhang, Yu and Xiong, Gengyan and Tian, Long and Zhang, Xin and Tian, Ye and Ji, Zhengguo and Guo, Bin and Shi, Yue and Fan, Jian and Li, Zhihua and Gong, Yanqing and He, Shiming and Li, Xuesong and Ci, Weimin and Zhou, Liqun},
title = {UCtracker: A Deep Learning–Based DNA Methylation Model for Noninvasive Diagnosis and Recurrence Surveillance of Urothelial Carcinoma in a Prospective Study},
journal = {Advanced Science},
year = {2026},
doi = {10.1002/advs.76710}
}
EUVIMED