Original Article
Application and evaluation of artificial intelligence TPS-assisted cytologic screening system in urine exfoliative cytology
Zhu Lin, Jin Mulan, He Shurong, Xu Haimiao, Huang Jianwei, Kong Lingfei, Li Daohong, Hu Jinxing, Wang Xieyan, Jin Yuwei, He Hui, Wang Xueyan, Song Yaoyao, Wang Xueqing, Yang Zhiming, Hu Aixia
Published 2023-12-08
Cite as Chin J Pathol, 2023, 52(12): 1223-1229. DOI: 10.3760/cma.j.cn112151-20230831-00115
Abstract
ObjectiveTo explore the application of manual screening collaborated with the Artificial Intelligence TPS-Assisted Cytologic Screening System in urinary exfoliative cytology and its clinical values.
MethodsA total of 3 033 urine exfoliated cytology samples were collected at the Henan People's Hospital, Capital Medical University, Beijing, China. Liquid-based thin-layer cytology was prepared. The slides were manually read under the microscope and digitally presented using a scanner. The intelligent identification and analysis were carried out using an artificial intelligence TPS assisted screening system. The Paris Report Classification System of Urinary Exfoliated Cytology 2022 was used as the evaluation standard. Atypical urothelial cells and even higher grade lesions were considered as positive when evaluating the recognition sensitivity, specificity, and diagnostic accuracy of artificial intelligence-assisted screening systems and human-machine collaborative cytologic screening methods in urine exfoliative cytology. Among the collected cases, there were also 1 100 pathological tissue controls.
ResultsThe accuracy, sensitivity and specificity of the AI-assisted cytologic screening system were 77.18%, 90.79% and 69.49%; those of human-machine coordination method were 92.89%, 99.63% and 89.09%, respectively. Compared with the histopathological results, the accuracy, sensitivity and specificity of manual reading were 79.82%, 74.20% and 95.80%, respectively, while those of AI-assisted cytologic screening system were 93.45%, 93.73% and 92.66%, respectively. The accuracy, sensitivity and specificity of human-machine coordination method were 95.36%, 95.21% and 95.80%, respectively. Both cytological and histological controls showed that human-machine coordination review method had higher diagnostic accuracy and sensitivity, and lower false negative rates.
ConclusionsThe artificial intelligence TPS assisted cytologic screening system has achieved acceptable accuracy in urine exfoliation cytologic screening. The combination of manual screening and artificial intelligence TPS assisted screening system can effectively improve the sensitivity and accuracy of cytologic screening and reduce the risk of misdiagnosis.
Key words:
Atificial intelligence; Urethral diseases; Cytological diagnosis
Contributor Information
Zhu Lin
Department of Pathology, Henan People′s Hospital/Zhengzhou University People′s Hospital
Zhengzhou 450003, China
Jin Mulan
Department of Pathology, Beijing Chaoyang Hospital, Capital Medical University, Beijing 100020, China
He Shurong
Department of Pathology, Beijing Hospital, Beijing 100730, China
Xu Haimiao
Department of Pathology, Zhejiang Cancer Hospital, Hangzhou 310022, China
Huang Jianwei
Department of Pathology, Luoyang Central Hospital, Luoyang 471000, China
Kong Lingfei
Department of Pathology, Henan People′s Hospital/Zhengzhou University People′s Hospital
Zhengzhou 450003, China
Li Daohong
Department of Pathology, Henan People′s Hospital/Zhengzhou University People′s Hospital
Zhengzhou 450003, China
Hu Jinxing
Department of Pathology, Henan People′s Hospital/Zhengzhou University People′s Hospital
Zhengzhou 450003, China
Wang Xieyan
Department of Pathology, Henan People′s Hospital/Zhengzhou University People′s Hospital
Zhengzhou 450003, China
Jin Yuwei
Department of Pathology, Henan People′s Hospital/Zhengzhou University People′s Hospital
Zhengzhou 450003, China
He Hui
Department of Pathology, Henan People′s Hospital/Zhengzhou University People′s Hospital
Zhengzhou 450003, China
Wang Xueyan
iDeepwise Artificial Intelligence Robot Technology (Beijing) Limited Company, Beijing 100089, China
Song Yaoyao
iDeepwise Artificial Intelligence Robot Technology (Beijing) Limited Company, Beijing 100089, China
Wang Xueqing
iDeepwise Artificial Intelligence Robot Technology (Beijing) Limited Company, Beijing 100089, China
Yang Zhiming
iDeepwise Artificial Intelligence Robot Technology (Beijing) Limited Company, Beijing 100089, China
Hu Aixia
Department of Pathology, Henan People′s Hospital/Zhengzhou University People′s Hospital
Zhengzhou 450003, China