Mp51-05 Radiomics Model for Predicting Renal Sinus Invasion in Renal Cell Carcinoma

You have accessJournal of UrologyKidney Cancer: Epidemiology & Evaluation/Staging/Surveillance II (MP51)1 May 2024MP51-05 RADIOMICS MODEL FOR PREDICTING RENAL SINUS INVASION IN RENAL CELL CARCINOMA Ye Yan, Haibin Zhu, Li Zhou, Guoying Ji, Chao Liang, Lizhi Shao, Xiaoming Jiang, Fan Zhang, and Shudong Zhang Ye YanYe Yan , Haibin ZhuHaibin Zhu , Li ZhouLi Zhou , Guoying JiGuoying Ji , Chao LiangChao Liang , Lizhi ShaoLizhi Shao , Xiaoming JiangXiaoming Jiang , Fan ZhangFan Zhang , and Shudong ZhangShudong Zhang View All Author Informationhttps://doi.org/10.1097/01.JU.0001009492.49624.4b.05AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Determining renal sinus invasion in renal cell carcinoma (RCC) is critical for surgical planning and prognosis. This study developed and validated a radiomics model for preoperative prediction of sinus invasion. METHODS: 413 RCC patients from two institutions were retrospectively analyzed. Tumors were segmented on arterial phase CT and a radiomics signature (RSI) extracted using a deep convolutional neural network. Logistic regression incorporated RSI, RENAL score parameters, and radiologists' assessments. Model performance was evaluated and compared to human readers. RESULTS: RSI demonstrated good discrimination for sinus invasion (AUC 0.822 internal, 0.700 external validation). The combined model outperformed RSI or clinical features alone. Radiomics model performed better than most readers, with AUC 0.700-0.867 versus 0.517-0.867 for readers. CONCLUSIONS: Radiomics can predict RCC sinus invasion, outperforming clinical features or human assessment alone. RSI has potential to optimize surgical planning if prospectively validated. Download PPT Source of Funding: None © 2024 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 211Issue 5SMay 2024Page: e843 Advertisement Copyright & Permissions© 2024 by American Urological Association Education and Research, Inc.Metrics Author Information Ye Yan More articles by this author Haibin Zhu More articles by this author Li Zhou More articles by this author Guoying Ji More articles by this author Chao Liang More articles by this author Lizhi Shao More articles by this author Xiaoming Jiang More articles by this author Fan Zhang More articles by this author Shudong Zhang More articles by this author Expand All Advertisement PDF downloadLoading ...