Jingqiu Li, Tsung Wen Chong, Khi Yung Fong, Benjamin Lim Jia Han, Si Ying Tan, Joanne Tan San Mui, Li Yan Khor, Bhaskar Kumar Somoni, Thomas R W Herrmann, Vineet Gauhar, Valerie Gan Huei Li, Christopher Cheng Wai Sam, Ee Jean Lim
{"title":"Will artificial intelligence (AI) replace cytopathologists: a scoping review of current applications and evidence of A.I. in urine cytology.","authors":"Jingqiu Li, Tsung Wen Chong, Khi Yung Fong, Benjamin Lim Jia Han, Si Ying Tan, Joanne Tan San Mui, Li Yan Khor, Bhaskar Kumar Somoni, Thomas R W Herrmann, Vineet Gauhar, Valerie Gan Huei Li, Christopher Cheng Wai Sam, Ee Jean Lim","doi":"10.1007/s00345-025-05583-8","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Urine cytology, while valuable in facilitating the detection and surveillance of bladder cancer, has notable limitations. The application of artificial intelligence (AI) in urine cytology holds significant promise for improving diagnostic accuracy and efficiency. Our scoping review aims to assess the current evidence of AI's utility in urine cytology.</p><p><strong>Method: </strong>An electronic literature research on the application of AI in the setting of urine cytology was conducted on PubMed, EMBASE, and Scopus from inception to 1st November 2024. Case reports, abstracts, and reviews were excluded from this analysis. Our search strategy retrieved 1356 articles; after excluding 142 duplicates, the remaining 1214 papers were screened by title and abstract. 31 studies entered full-article review, and a total of 16 articles were included in the final analysis.</p><p><strong>Results: </strong>The main application of AI in urine cytology diagnosis is to automate the identification and characterization of abnormal cells. It has also been utilized for risk stratification of abnormal cells, predicting histologic results from urine cytology samples, and predicting bladder cancer recurrence. Current limitation includes the need for robust training datasets and validation studies to ensure the generalizability of AI algorithms.</p><p><strong>Conclusion: </strong>In summary, AI in urine cytology, though still developing, shows significant promise in enhancing diagnostic accuracy and efficiency. Current evidence suggests that AI, as a valuable tool, could revolutionize urinary tract cancer diagnosis and management.</p>","PeriodicalId":23954,"journal":{"name":"World Journal of Urology","volume":"43 1","pages":"200"},"PeriodicalIF":2.8000,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"World Journal of Urology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00345-025-05583-8","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"UROLOGY & NEPHROLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose: Urine cytology, while valuable in facilitating the detection and surveillance of bladder cancer, has notable limitations. The application of artificial intelligence (AI) in urine cytology holds significant promise for improving diagnostic accuracy and efficiency. Our scoping review aims to assess the current evidence of AI's utility in urine cytology.
Method: An electronic literature research on the application of AI in the setting of urine cytology was conducted on PubMed, EMBASE, and Scopus from inception to 1st November 2024. Case reports, abstracts, and reviews were excluded from this analysis. Our search strategy retrieved 1356 articles; after excluding 142 duplicates, the remaining 1214 papers were screened by title and abstract. 31 studies entered full-article review, and a total of 16 articles were included in the final analysis.
Results: The main application of AI in urine cytology diagnosis is to automate the identification and characterization of abnormal cells. It has also been utilized for risk stratification of abnormal cells, predicting histologic results from urine cytology samples, and predicting bladder cancer recurrence. Current limitation includes the need for robust training datasets and validation studies to ensure the generalizability of AI algorithms.
Conclusion: In summary, AI in urine cytology, though still developing, shows significant promise in enhancing diagnostic accuracy and efficiency. Current evidence suggests that AI, as a valuable tool, could revolutionize urinary tract cancer diagnosis and management.
期刊介绍:
The WORLD JOURNAL OF UROLOGY conveys regularly the essential results of urological research and their practical and clinical relevance to a broad audience of urologists in research and clinical practice. In order to guarantee a balanced program, articles are published to reflect the developments in all fields of urology on an internationally advanced level. Each issue treats a main topic in review articles of invited international experts. Free papers are unrelated articles to the main topic.