Development and validation of an artificial intelligence-based model for detecting urothelial carcinoma using urine cytology images: a multicentre, diagnostic study with prospective validation

作者：Shaoxu Wu, Runnan Shen, Guibin Hong, Yun Luo, Huan Wan, Jiahao Feng, Zeshi Chen, Fan Jiang, Yun Wang, Chengxiao Liao, Xiaoyang Li, Bohao Liu, Xiaowei Huang, Kai Liu, Ping Qin, Ya‐Hui Wang, Ye Xie, Nengtai Ouyang, Jian Huang, Tianxin Lin · 发表于：EClinicalMedicine · 年份：2024 · DOI：10.1016/j.eclinm.2024.102566 · 被引用次数：27 · 研究领域：Bladder and Urothelial Cancer Treatments、AI in cancer detection、Cutaneous Melanoma Detection and Management

Background: Urine cytology is an important non-invasive examination for urothelial carcinoma (UC) diagnosis and follow-up. We aimed to explore whether artificial intelligence (AI) can enhance the sensitivity of urine cytology and help avoid unnecessary endoscopy. Methods: In this multicentre diagnostic study, consecutive patients who underwent liquid-based urine cytology examinations at four hospitals in China were included for model development and validation. Patients who declined surgery and lacked associated histopathology results, those diagnosed with rare subtype tumours of the urinary tract, or had low-quality images were excluded from the study. All liquid-based cytology slides were scanned into whole-slide images (WSIs) at 40 × magnification and the WSI-labels were derived from the corresponding histopathology results. The Precision Urine Cytology AI Solution (PUCAS) was composed of three distinct stages (patch extraction, features extraction, and classification diagnosis) and was trained to identify important WSI features associated with UC diagnosis. The diagnostic sensitivity was mainly used to validate the performance of PUCAS in retrospective and prospective validation cohorts. This study is registered with the ChiCTR, ChiCTR2300073192. Findings: Between January 1, 2018 and October 31, 2022, 2641 patients were retrospectively recruited in the training cohort, and 2335 in retrospective validation cohorts; 400 eligible patients were enrolled in the prospective val...