You have accessJournal of UrologyProstate Cancer: Localized: Surgical Therapy I (MP19)1 Apr 2020MP19-02 DEEP LEARNING USING PREOPERATIVE MRI INFORMATION STRONGLY PREDICTS EARLY RECOVERY OF URINARY CONTINENCE AFTER ROBOT-ASSISTED RADICAL PROSTATECTOMY Makoto Sumitomo*, Atsushi Teramoto, Naohiko Fukami, Kosuke Fukaya, Kenji Zennami, Manabu Ichino, Kiyoshi Takahara, Mamoru Kusaka, and Ryoichi Shiroki Makoto Sumitomo*Makoto Sumitomo* More articles by this author , Atsushi TeramotoAtsushi Teramoto More articles by this author , Naohiko FukamiNaohiko Fukami More articles by this author , Kosuke FukayaKosuke Fukaya More articles by this author , Kenji ZennamiKenji Zennami More articles by this author , Manabu IchinoManabu Ichino More articles by this author , Kiyoshi TakaharaKiyoshi Takahara More articles by this author , Mamoru KusakaMamoru Kusaka More articles by this author , and Ryoichi ShirokiRyoichi Shiroki More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000000852.02AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Urinary incontinence remains one of the most bothersome postoperative complications even after robot-assisted radical prostatectomy (RARP). We aimed to make a novel prediction system that can be used preoperatively to inform patients of the accuracy of early recovery of urinary continence after RARP using a deep learning (DL) model from magnetic resonance imaging (MRI) information and preoperative clinicopathological parameters. METHODS: A retrospective cohort study was conducted on prostate cancer (PC) patients who had undergone RARP at Fujita Health University Hospital between August 2015 and July 2019. Patients using no pads/no leakage of urine or the use of a safety pad within 3 months after RARP is categorized into “good” continence and others into “no good” continence. MRI DICOM data from axial, coronal and sagittal imaging as well as preoperative clinicopathological covariates (age, BMI, prostate volume, serum PSA level, Gleason score, clinical stage) and intraoperative covariates (main operator, operation time, console time, with or without nerve sparing, bleeding) were assessed. Supervised DL algorithms, which included AdaBoost, Naive Bayes, Neural Network, Random Forest, and SVM were trained and tested as binary classifiers (good or no good). To evaluate the DL models from the testing data set, their sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), as well area under the receiver operating characteristic curve (AUC) were analyzed. RESULTS: Data were available for 497 patients in the study period. Continence rates at 1, 3, 6, and 12 months after RARP were 47%, 76%, 87%, and 94%, respectively. The AdaBoost DL algorithm using MRI information in addition to clinicopathological parameters had the highest performance with sensitivity at 92%, specificity at 77%, PPV at 79%, NPV at 91%, and AUC at 84% for predicting good continence, while that using clinicopathological parameters only had the performance with sensitivity at 50%, specificity at 69%, PPV at 60%, NPV at 60%, and AUC at 60%. Furthermore, little increase in AUC was observed in the DL algorithms using intraoperative parameters in addition to preoperative information. CONCLUSIONS: Our results suggest that the DL algorithms using MRI information are highlighted as an accurate method for strongly predicting early recovery of urinary continence after RARP. Thus, DL predictions may help allocation of treatment strategies for PC patients who dislike prolonged urinary incontinence after RARP. Source of Funding: None © 2020 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 203Issue Supplement 4April 2020Page: e298-e298 Advertisement Copyright & Permissions© 2020 by American Urological Association Education and Research, Inc.MetricsAuthor Information Makoto Sumitomo* More articles by this author Atsushi Teramoto More articles by this author Naohiko Fukami More articles by this author Kosuke Fukaya More articles by this author Kenji Zennami More articles by this author Manabu Ichino More articles by this author Kiyoshi Takahara More articles by this author Mamoru Kusaka More articles by this author Ryoichi Shiroki More articles by this author Expand All Advertisement PDF downloadLoading ...