You have accessJournal of UrologySurgical Technology & Simulation: Artificial Intelligence I (MP07)1 May 2024MP07-09 AUTOMATED SURGICAL STEP RECOGNITION IN TRANSURETHRAL BLADDER TUMOR RESECTION USING ARTIFICIAL INTELLIGENCE: TRANSFER LEARNING ACROSS SURGICAL MODALITIES Ekamjit S. Deol, Matthew K. Tollefson, Alenka Antolin, Maya Zohar, Omri Bar, Danielle Ben-Ayoun, Lance A. Mynderse, Derek J. Lomas, Avant A. Ross, Adam A. Miller, Daniel S. Elliott, Stephen A. Boorjian, Tamir Wolf, Dotan Asselmann, and Abhinav Khanna Ekamjit S. DeolEkamjit S. Deol , Matthew K. TollefsonMatthew K. Tollefson , Alenka AntolinAlenka Antolin , Maya ZoharMaya Zohar , Omri BarOmri Bar , Danielle Ben-AyounDanielle Ben-Ayoun , Lance A. MynderseLance A. Mynderse , Derek J. LomasDerek J. Lomas , Avant A. RossAvant A. Ross , Adam A. MillerAdam A. Miller , Daniel S. ElliottDaniel S. Elliott , Stephen A. BoorjianStephen A. Boorjian , Tamir WolfTamir Wolf , Dotan AsselmannDotan Asselmann , and Abhinav KhannaAbhinav Khanna View All Author Informationhttps://doi.org/10.1097/01.JU.0001008728.41882.d7.09AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Automated surgical step recognition (SSR) using artificial intelligence (AI) has been a catalyst in the "digitization" of surgery. However, progress has been limited to laparoscopic and robotic surgeries, with relatively few SSR tools in endoscopic surgery. This study aims to create a SSR model for transurethral resection of bladder tumors (TURBT), leveraging a novel application of transfer learning to reduce video dataset requirements. METHODS: Retrospective surgical videos of TURBT were manually annotated with the following steps of surgery: primary endoscopic evaluation, resection of bladder tumor, and surface coagulation (Figure 1). Manually annotated videos were then utilized to train a novel AI computer vision algorithm to perform automated video annotation of TURBT surgical video, utilizing a transfer-learning technique to pre-train on laparoscopic procedures. Accuracy of AI SSR was determined by comparison to human annotations as the reference standard. RESULTS: A total of 300 full-length TURBT videos (median 23.96 minutes; IQR 14.13-41.31 minutes) were manually annotated with sequential steps of surgery. Of these, 179 videos served as a training dataset for algorithm development, 44 for internal validation, and 77 as a separate test cohort for evaluating algorithm accuracy. Overall accuracy of AI video analysis was 89.6%. Model accuracy was highest for the primary endoscopic evaluation step (98.2%) and lowest for the surface coagulation step (82.7%). CONCLUSIONS: We developed a fully automated computer vision algorithm for high-accuracy annotation of TURBT surgical videos. This represents the first application of transfer-learning from laparoscopy-based computer vision models into surgical endoscopy, demonstrating the promise of this approach in adapting to new procedure types. Automated surgical video analysis serves as the foundation for wide-ranging potential future applications, including quality and safety assessment, surgical education, and optimizing operating room logistics. Download PPT Source of Funding: Thomas P. and Elizabeth S. Grainger Urology Fellowship Fund © 2024 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 211Issue 5SMay 2024Page: e108 Advertisement Copyright & Permissions© 2024 by American Urological Association Education and Research, Inc.Metrics Author Information Ekamjit S. Deol More articles by this author Matthew K. Tollefson More articles by this author Alenka Antolin More articles by this author Maya Zohar More articles by this author Omri Bar More articles by this author Danielle Ben-Ayoun More articles by this author Lance A. Mynderse More articles by this author Derek J. Lomas More articles by this author Avant A. Ross More articles by this author Adam A. Miller More articles by this author Daniel S. Elliott More articles by this author Stephen A. Boorjian More articles by this author Tamir Wolf More articles by this author Dotan Asselmann More articles by this author Abhinav Khanna More articles by this author Expand All Advertisement PDF downloadLoading ...
No takes yet. Share an insight, caveat, or question.
Deol et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: