An artificial intelligence model for detecting pathological lymph node metastasis in prostate cancer using whole slide images: a retrospective, multicentre, diagnostic study

作者全名：Wu, Shaoxu; Wang, Yun; Hong, Guibin; Luo, Yun; Lin, Zhen; Shen, Runnan; Zeng, Hong; Xu, Abai; Wu, Peng; Xiao, Mingzhao; Li, Xiaoyang; Rao, Peng; Yang, Qishen; Feng, Zhengyuan; He, Quanhao; Jiang, Fan; Xie, Ye; Liao, Chengxiao; Huang, Xiaowei; Chen, Rui; Lin, Tianxin

作者地址：[Wu, Shaoxu; Wang, Yun; Hong, Guibin; Shen, Runnan; Xu, Abai; Jiang, Fan; Xie, Ye; Liao, Chengxiao; Lin, Tianxin] Sun Yat Sen Univ, Sun Yat Sen Mem Hosp, Dept Urol, 107th Yanjiangxi Rd, Guangzhou 510120, Peoples R China; [Wu, Shaoxu; Lin, Tianxin] Sun Yat Sen Univ, Sun Yat Sen Mem Hosp, Guangdong Prov Key Lab Malignant Tumour Epigenet &, Guangdong Hong Kong Joint Lab RNA Med, Guangzhou, Peoples R China; [Wu, Shaoxu; Lin, Tianxin] Guangdong Prov Clin Res Ctr Urol Dis, Guangzhou, Peoples R China; [Luo, Yun; Li, Xiaoyang] Sun Yat Sen Univ, Affiliated Hosp 3, Dept Urol, Guangzhou, Peoples R China; [Lin, Zhen; Huang, Xiaowei; Chen, Rui] CellsVis Med Technol Serv Co Ltd, Guangzhou, Peoples R China; [Zeng, Hong] Sun Yat Sen Univ, Sun Yat Sen Mem Hosp, Dept Pathol, Guangzhou, Peoples R China; [Xu, Abai; Rao, Peng] Southern Med Univ, Zhujiang Hosp, Dept Urol, Guangzhou, Peoples R China; [Wu, Peng; Yang, Qishen; Feng, Zhengyuan] Southern Med Univ, Nanfang Hosp, Dept Urol, Guangzhou, Peoples R China; [Xiao, Mingzhao; He, Quanhao] Chongqing Med Univ, Affiliated Hosp 1, Dept Urol, Chongqing, Peoples R China

通信作者：Lin, TX (通讯作者)，Sun Yat Sen Univ, Sun Yat Sen Mem Hosp, Dept Urol, 107th Yanjiangxi Rd, Guangzhou 510120, Peoples R China.

来源：ECLINICALMEDICINE

ESI学科分类：　

WOS号：WOS:001225052400001

JCR分区：Q1

影响因子：9.6

年份：2024

卷号：71

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：Arti fi cial intelligence; Prostate cancer; Lymph node metastasis; Digital pathology; Multicentre validation

摘要：Background The pathological examination of lymph node metastasis (LNM) is crucial for treating prostate cancer (PCa). However, the limitations with naked -eye detection and pathologist workload contribute to a high misseddiagnosis rate for nodal micrometastasis. We aimed to develop an arti fi cial intelligence (AI) -based, time -eff i cient, and high -precision PCa LNM detector (ProCaLNMD) and evaluate its clinical application value. Methods In this multicentre, retrospective, diagnostic study, consecutive patients with PCa who underwent radical prostatectomy and pelvic lymph node dissection at fi ve centres between Sep 2, 2013 and Apr 28, 2023 were included, and histopathological slides of resected lymph nodes were collected and digitised as whole -slide images for model development and validation. ProCaLNMD was trained at a dataset from a single centre (the Sun Yat-sen Memorial Hospital of Sun Yat-sen University [SYSMH]), and externally validated in the other four centres. A bladder cancer dataset from SYSMH was used to further validate ProCaLNMD, and an additional validation (human -AI comparison and collaboration study) containing consecutive patients with PCa from SYSMH was implemented to evaluate the application value of integrating ProCaLNMD into the clinical work fl ow. The primary endpoint was the area under the receiver operating characteristic curve (AUROC) of ProCaLNMD. In addition, the performance measures for pathologists with ProCaLNMD assistance was also assessed. Findings In total, 8225 slides from 1297 patients with PCa were collected and digitised. Overall, 8158 slides (18,761 lymph nodes) from 1297 patients with PCa (median age 68 years [interquartile range 64 - 73]; 331 [26%] with LNM) were used to train and validate ProCaLNMD. The AUROC of ProCaLNMD ranged from 0.975 (95% con fi dence interval 0.953 - 0.998) to 0.992 (0.982 - 1.000) in the training and validation datasets, with sensitivities > 0.955 and speci fi cities > 0.921. ProCaLNMD also demonstrated an AUROC of 0.979 in the cross -cancer dataset. ProCaLNMD use triggered true reclassi fi cation in 43 (4.3%) slides in which micrometastatic tumour regions were initially missed by pathologists, thereby correcting 28 (8.5%) missed -diagnosed cases of previous routine pathological reports. In the human -AI comparison and collaboration study, the sensitivity of ProCaLNMD (0.983 [0.908 - 1.000]) surpassed that of two junior pathologists (0.862 [0.746 - 0.939], P = 0.023; 0.879 [0.767 - 0.950], P = 0.041) by 10 - 12% and showed no difference to that of two senior pathologists (both 0.983 [0.908 - 1.000], both P > 0.99). Furthermore, ProCaLNMD signi fi cantly boosted the diagnostic sensitivity of two junior pathologists (both P = 0.041) to the level of senior pathologists (both P > 0.99), and substantially reduced the four pathologists ' slide reviewing time ( - 31%, P < 0.0001; - 34%, P < 0.0001; - 29%, P < 0.0001; and - 27%, P = 0.00031). Interpretation ProCaLNMD demonstrated high diagnostic capabilities for identifying LNM in prostate cancer, reducing the likelihood of missed diagnoses by pathologists and decreasing the slide reviewing time, highlighting its potential for clinical application.

基金机构：National Natural Science Foundation of China; Science and Technology Planning Project of Guangdong Province; National Key Research and Development Programme of China; Guangdong Provincial Clinical Research Centre for Urological Diseases; Science and Technology Projects in Guangzhou

基金资助正文：National Natural Science Foundation of China, the Science and Technology Planning Project of Guangdong Province, the National Key Research and Development Programme of China, the Guangdong Provincial Clinical Research Centre for Urological Diseases, and the Science and Technology Projects in Guangzhou.