Enhancing urine cytopathology with artificial intelligence: a systematic review
- 5 January 2026
- journal article
- review article
- Published by Oxford University Press (OUP) in American Journal of Clinical Pathology
- Vol. 165 (2)
Abstract
Objective: To evaluate the potential of artificial intelligence (AI) to enhance urine cytopathology for detecting urothelial carcinoma (UC), emphasizing improvements in diagnostic sensitivity, accuracy, and efficiency, as well as potential reductions in pathologist workload. Methods: A systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. PubMed, Google Scholar, EMBASE, and ScienceDirect were searched (January 2018 to July 2025) for English-language studies applying AI to urine cytology for UC detection and reporting sensitivity and specificity. Results: Eleven studies met the inclusion criteria, with sample sizes ranging from 116 to 2641 cases. The AI models, predominantly convolutional neural networks, achieved a sensitivity of 63% to 100% and a specificity of 61.8% to 100% for high-grade urothelial carcinoma (HGUC) detection. Artificial intelligence has the potential to improve detection and streamline workflows in clinical settings. Conclusions: Artificial intelligence shows strong potential as a diagnostic aid in urine cytopathology, particularly for HGUC detection, by improving accuracy and efficiency. However, challenges such as standardizing its use in different settings remain, along with the need for further large-scale validation studies.Keywords
This publication has 22 references indexed in Scilit:
- Evaluating artificial intelligence–enhanced digital urine cytology for bladder cancer diagnosisCancer Cytopathology, 2024
- Development and validation of an artificial intelligence-based model for detecting urothelial carcinoma using urine cytology images: a multicentre, diagnostic study with prospective validationeClinicalMedicine, 2024
- A Fully Automated Artificial Intelligence System to Assist Pathologists’ Diagnosis to Predict Histologically High-grade Urothelial Carcinoma from Digitized Urine Cytology Slides Using Deep LearningEuropean Urology Oncology, 2023
- Artificial intelligence to improve cytology performance in urothelial carcinoma diagnosis: results from validation phase of the French, multicenter, prospective VISIOCYT1 trialWorld Journal of Urology, 2023
- Evaluation of an artificial intelligence algorithm for assisting the Paris System in reporting urinary cytology: A pilot studyCancer Cytopathology, 2022
- A deep learning system to diagnose the malignant potential of urothelial carcinoma cells in cytology specimensCancer Cytopathology, 2021
- Deep learning based digital cell profiles for risk stratification of urine cytology imagesCytometry Part A, 2021
- Performance of an artificial intelligence algorithm for reporting urine cytopathologyCancer Cytopathology, 2019
- Automating the Paris System for urine cytopathology—A hybrid deep‐learning and morphometric approachCancer Cytopathology, 2019
- Artificial neural network in diagnosis of urothelial cell carcinoma in urine cytologyDiagnostic Cytopathology, 2015