MP07-08 A FULLY AUTOMATED MULTI-TASK MACHINE LEARNING PROGNOSTIC MODEL INTEGRATING RADIOMICS AND CLINICAL DATA TO PREDICT OUTCOMES IN HIGH-GRADE PROSTATE CANCER

You have accessJournal of UrologySurgical Technology & Simulation: Artificial Intelligence I (MP07)1 May 2024MP07-08 A FULLY AUTOMATED MULTI-TASK MACHINE LEARNING PROGNOSTIC MODEL INTEGRATING RADIOMICS AND CLINICAL DATA TO PREDICT OUTCOMES IN HIGH-GRADE PROSTATE CANCER Nawar Touma, Maxence Larose, Raphaël Brodeur, Félix Desroches, Daphnée Bédard-Tremblay, Nicolas Raymond, Danahé Leblanc, Fatemeh Rasekh, Hélène Hovington, Bertrand Neveu, Martin Vallières, Louis Archambault, and Frédéric Pouliot Nawar ToumaNawar Touma , Maxence LaroseMaxence Larose , Raphaël BrodeurRaphaël Brodeur , Félix DesrochesFélix Desroches , Daphnée Bédard-TremblayDaphnée Bédard-Tremblay , Nicolas RaymondNicolas Raymond , Danahé LeblancDanahé Leblanc , Fatemeh RasekhFatemeh Rasekh , Hélène HovingtonHélène Hovington , Bertrand NeveuBertrand Neveu , Martin VallièresMartin Vallières , Louis ArchambaultLouis Archambault , and Frédéric PouliotFrédéric Pouliot View All Author Informationhttps://doi.org/10.1097/01.JU.0001008728.41882.d7.08AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: To develop an automated multi-task prognostic model that combines clinical data with radiomics from positron emission tomography (PET) with 18F-fluorodeoxyglucose (FDG) combined with computed tomography (CT), eliminating the need for manual segmentation while providing clinically interpretable results. This is the first study of its kind using radiomics in prostate cancer that describes long-term clinical outcomes. METHODS: A total of 295 individuals with high-grade PCa (Gleason score≥8) underwent radical prostatectomy (RP) with preoperative FDG-PET/CT imaging at our tertiary care health center. Clinical data (CD), including age, prostate-specific antigen (PSA) level, clinical stage, and Gleason grade, were collected. Six prognostic tasks were defined, including lymph node invasion (LNI), biochemical recurrence (BCR)-free survival (FS), metastasis-free survival (MFS), definitive androgen deprivation therapy (dADT)-FS, castration-resistant prostate cancer (CRPC)-FS, and prostate cancer-specific survival (PCSS). A Bayesian Sequential Network (BSN), a dynamic prediction model quantifying uncertainty and adapting over time as outcomes from prior tasks unfold, was developed. It was compared with commonly used nomograms (MSKCC and CAPRA-S). Performance metrics on the holdout set were evaluated using the area under the curve of the receiver operator characteristic (AUC-ROC) and the concordance index (C-index). RESULTS: Median follow-up was 64.7 (range 29.3-89.6) months. Median age was 66 (48-80) years. Median PSA was 7.4 (1.1-155.3) ng/ml. 230 (88%) and 31 (12%) had clinical T1-T2 and T3a disease, respectively. At RP, 86 (29%) had LNI. At follow-up, 160 had BCR, 38 had metastases, 72 started dADT, 23 had CRPC, and 11 had PCSS. On the holdout set comprising 45 individuals, the BSN model outperformed nomograms for predicting LNI (AUC=66.3%), MFS (CI=75.3%), and dADT-FS (CI=69.6%). The nomogram outperformed our BSN model for predicting BCR-FS (CI=63.5% [MSKCC] vs 59.2%), CRPC-FS (CI=67.6% [CAPRA-S] vs 65.6%), and PCSS (CI=87.8% [MSKCC] vs 78.0%). CONCLUSIONS: We present a fully automated self-learning multi-task model that integrates FDG-PET/CT imaging data to predict clinical outcomes while quantifying predictions' associated uncertainty. It achieved good results with minimal training compared to commonly used nomograms. Source of Funding: None © 2024 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 211Issue 5SMay 2024Page: e107 Advertisement Copyright & Permissions© 2024 by American Urological Association Education and Research, Inc.Metrics Author Information Nawar Touma More articles by this author Maxence Larose More articles by this author Raphaël Brodeur More articles by this author Félix Desroches More articles by this author Daphnée Bédard-Tremblay More articles by this author Nicolas Raymond More articles by this author Danahé Leblanc More articles by this author Fatemeh Rasekh More articles by this author Hélène Hovington More articles by this author Bertrand Neveu More articles by this author Martin Vallières More articles by this author Louis Archambault More articles by this author Frédéric Pouliot More articles by this author Expand All Advertisement PDF downloadLoading ...