Deep learning system for malignancy risk prediction in cystic renal lesions: a multicenter study

作者全名：He, Quan-Hao; Feng, Jia-Jun; Wu, Ling-Cheng; Wang, Yun; Zhang, Xuan; Jiang, Qing; Zeng, Qi-Yuan; Yin, Si-Wen; He, Wei-Yang; Lv, Fa-Jin; Xiao, Ming-Zhao

作者地址：[He, Quan-Hao; Wu, Ling-Cheng; Zeng, Qi-Yuan; He, Wei-Yang; Xiao, Ming-Zhao] Chongqing Med Univ, Dept Urol, Affiliated Hosp 1, Chongqing, Peoples R China; [Feng, Jia-Jun] South China Univ Technol, Guangzhou Peoples Hosp 1, Sch Med, Dept Med Imaging, Guangzhou, Peoples R China; [Wang, Yun] Sun Yat Sen Univ, Sun Yat Sen Mem Hosp, Dept Urol, Guangzhou, Peoples R China; [Zhang, Xuan] Chongqing Med Univ, Dept Urol, Yongchuan Hosp, Chongqing, Peoples R China; [Jiang, Qing] Chongqing Med Univ, Dept Urol, Affiliated Hosp 2, Chongqing, Peoples R China; [Yin, Si-Wen] Chongqing Univ, Dept Urol, Fuling Hosp, Chongqing, Peoples R China; [Lv, Fa-Jin] Chongqing Med Univ, Dept Radiol, Affiliated Hosp 1, Chongqing, Peoples R China

通信作者：He, WY; Xiao, MZ (通讯作者)，Chongqing Med Univ, Dept Urol, Affiliated Hosp 1, Chongqing, Peoples R China.; Lv, FJ (通讯作者)，Chongqing Med Univ, Dept Radiol, Affiliated Hosp 1, Chongqing, Peoples R China.

来源：INSIGHTS INTO IMAGING

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001227620800001

JCR分区：Q1

影响因子：4.1

年份：2024

卷号：15

期号：1

开始页：　

结束页：　

文献类型：Article

关键词：Cystic renal lesions; Bosniak-2019 classification; Deep learning; Radiomics

摘要：Objectives To develop an interactive, non-invasive artificial intelligence (AI) system for malignancy risk prediction in cystic renal lesions (CRLs).Methods In this retrospective, multicenter diagnostic study, we evaluated 715 patients. An interactive geodesic-based 3D segmentation model was created for CRLs segmentation. A CRLs classification model was developed using spatial encoder temporal decoder (SETD) architecture. The classification model combines a 3D-ResNet50 network for extracting spatial features and a gated recurrent unit (GRU) network for decoding temporal features from multi-phase CT images. We assessed the segmentation model using sensitivity (SEN), specificity (SPE), intersection over union (IOU), and dice similarity (Dice) metrics. The classification model's performance was evaluated using the area under the receiver operator characteristic curve (AUC), accuracy score (ACC), and decision curve analysis (DCA).Results From 2012 to 2023, we included 477 CRLs (median age, 57 [IQR: 48-65]; 173 men) in the training cohort, 226 CRLs (median age, 60 [IQR: 52-69]; 77 men) in the validation cohort, and 239 CRLs (median age, 59 [IQR: 53-69]; 95 men) in the testing cohort (external validation cohort 1, cohort 2, and cohort 3). The segmentation model and SETD classifier exhibited excellent performance in both validation (AUC = 0.973, ACC = 0.916, Dice = 0.847, IOU = 0.743, SEN = 0.840, SPE = 1.000) and testing datasets (AUC = 0.998, ACC = 0.988, Dice = 0.861, IOU = 0.762, SEN = 0.876, SPE = 1.000).Conclusion The AI system demonstrated excellent benign-malignant discriminatory ability across both validation and testing datasets and illustrated improved clinical decision-making utility.Critical relevance statement In this era when incidental CRLs are prevalent, this interactive, non-invasive AI system will facilitate accurate diagnosis of CRLs, reducing excessive follow-up and overtreatment.Key Points The rising prevalence of CRLs necessitates better malignancy prediction strategies. The AI system demonstrated excellent diagnostic performance in identifying malignant CRL. The AI system illustrated improved clinical decision-making utility.

基金机构：Supercomputing Center of Chongqing Medical University

基金资助正文：We appreciate all radiologists and related staff in each enrolled institution for their assistance in data collection. The computing work in this paper was partly supported by the Supercomputing Center of Chongqing Medical University.