Mp41-20 effectiveness of radiomic tumor zone of transition (zot) features in the automated discrimination of oncocytoma from clear cell renal cancer

You have accessJournal of UrologyCME1 Apr 2023MP41-20 EFFECTIVENESS OF RADIOMIC TUMOR ZONE OF TRANSITION (ZOT) FEATURES IN THE AUTOMATED DISCRIMINATION OF ONCOCYTOMA FROM CLEAR CELL RENAL CANCER Lorenzo Bianchi, Elena Tonin, Pietro Piazza, Gianluca Carlini, Caterina Gaudiano, Rita Golfieri, Nico Curti, Riccardo Schiavina, Francesca Giunchi, Riccardo Biondi, Damiano Caruso, Enrico Giampieri, Alessandra Merlotti, Daniele Dall'Olio, Claudia Sala, Sara Pandolfi, Daniel Remondini, Arianna Rustici, Luigi Vincenzo Pastore, Leonardo Scarpetti, Barbara Bortolani, Eugenio Brunocilla, Emanuela Marcelli, Francesca Coppola, and Gastone Castellani Lorenzo BianchiLorenzo Bianchi More articles by this author , Elena ToninElena Tonin More articles by this author , Pietro PiazzaPietro Piazza More articles by this author , Gianluca CarliniGianluca Carlini More articles by this author , Caterina GaudianoCaterina Gaudiano More articles by this author , Rita GolfieriRita Golfieri More articles by this author , Nico CurtiNico Curti More articles by this author , Riccardo SchiavinaRiccardo Schiavina More articles by this author , Francesca GiunchiFrancesca Giunchi More articles by this author , Riccardo BiondiRiccardo Biondi More articles by this author , Damiano CarusoDamiano Caruso More articles by this author , Enrico GiampieriEnrico Giampieri More articles by this author , Alessandra MerlottiAlessandra Merlotti More articles by this author , Daniele Dall'OlioDaniele Dall'Olio More articles by this author , Claudia SalaClaudia Sala More articles by this author , Sara PandolfiSara Pandolfi More articles by this author , Daniel RemondiniDaniel Remondini More articles by this author , Arianna RusticiArianna Rustici More articles by this author , Luigi Vincenzo PastoreLuigi Vincenzo Pastore More articles by this author , Leonardo ScarpettiLeonardo Scarpetti More articles by this author , Barbara BortolaniBarbara Bortolani More articles by this author , Eugenio BrunocillaEugenio Brunocilla More articles by this author , Emanuela MarcelliEmanuela Marcelli More articles by this author , Francesca CoppolaFrancesca Coppola More articles by this author , and Gastone CastellaniGastone Castellani More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003279.20AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: The aim of this study was to build a machine learning model based on CT-derived radiomic features to discriminate renal oncocytoma (RO) from clear cell renal cell carcinoma (ccRCC), focusing on tumor zone of transition (ZOT) features capturing tumor characteristics which are usually overlooked. METHODS: We collected CT images of 77 patients with a single T1a renal mass, who underwent partial nephrectomy at a single tertiary urologic center from January 2019 to December 2021. Radiomic features were extracted both from the tumor volumes identified by the clinicians and from the tumor ZOT, after images segmentation performed to carry out 3D virtual model. We used a genetic algorithm (GA) to perform feature selection, identifying the most descriptive set of features for the tumor classification. We built a decision tree classifier to distinguish between ROs and ccRCCs (Figure). We proposed two versions of the pipeline: in the first one the feature selection was performed before the splitting of the data, while in the second one the feature selection was performed after on the training data only. We evaluated the efficiency of the two pipelines in the cancer classification. RESULTS: Overall, 30 cases had RO (39%) and 47 cases had ccRCC (61%) confirmed at final pathologic specimens. The ZOT features were found to be the most predictive by the genetic algorithm. The pipeline with the feature selection performed on the whole dataset obtained an average Receiver Operating Characteristic (ROC) Area Under the Curve (AUC) score of 0.87±0.09. The second pipeline, in which the feature selection was performed on the training data only, obtained an average ROC AUC score of 0.62±0.17. In both cases, 8 of the top 10 selected features were tumor ZOT features. CONCLUSIONS: The obtained results highlight the efficiency of tumor ZOT radiomic features in capturing the characteristics of pT1a renal tumors, and particularly in discriminating RO from ccRCC. The use of tumor ZOT features in radiomic analyses should be further investigated, as it may lead to important clinic implication with regards of better selection of patients for active treatment (surgery or ablation) vs. active surveillance. Source of Funding: None. © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e565 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Lorenzo Bianchi More articles by this author Elena Tonin More articles by this author Pietro Piazza More articles by this author Gianluca Carlini More articles by this author Caterina Gaudiano More articles by this author Rita Golfieri More articles by this author Nico Curti More articles by this author Riccardo Schiavina More articles by this author Francesca Giunchi More articles by this author Riccardo Biondi More articles by this author Damiano Caruso More articles by this author Enrico Giampieri More articles by this author Alessandra Merlotti More articles by this author Daniele Dall'Olio More articles by this author Claudia Sala More articles by this author Sara Pandolfi More articles by this author Daniel Remondini More articles by this author Arianna Rustici More articles by this author Luigi Vincenzo Pastore More articles by this author Leonardo Scarpetti More articles by this author Barbara Bortolani More articles by this author Eugenio Brunocilla More articles by this author Emanuela Marcelli More articles by this author Francesca Coppola More articles by this author Gastone Castellani More articles by this author Expand All Advertisement PDF downloadLoading ...