You have accessJournal of UrologyCME1 Apr 2023LBA01-17 AI-POWERED REAL-TIME ANNOTATIONS DURING UROLOGIC SURGERY: THE FUTURE OF TRAINING AND QUALITY METRICS Laura Zuluaga, Jordan M. Rich, Raghav Gupta, Adriana Pedraza, Burak Ucpinar, Kennedy E. Okhawere, Indu Saini, Mani Menon, Ashutosh Tewari, and Ketan K Badani Laura ZuluagaLaura Zuluaga More articles by this author , Jordan M. RichJordan M. Rich More articles by this author , Raghav GuptaRaghav Gupta More articles by this author , Adriana PedrazaAdriana Pedraza More articles by this author , Burak UcpinarBurak Ucpinar More articles by this author , Kennedy E. OkhawereKennedy E. Okhawere More articles by this author , Indu SainiIndu Saini More articles by this author , Mani MenonMani Menon More articles by this author , Ashutosh TewariAshutosh Tewari More articles by this author , and Ketan K BadaniKetan K Badani More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003360.17AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Real-time artificial intelligence (AI) annotation of the surgical field has the potential to automatically extract information from surgical videos, helping to create a robust surgical atlas. This content can be used for surgical education and qualitative initiatives. We demonstrate the first use of AI in urologic robotic surgery to capture live surgical video and annotate key surgical steps and safety milestones in real-time. METHODS: We conducted an educational symposium, which broadcasted two live procedures, a robotic-assisted radical prostatectomy (RARP) and robotic-assisted partial nephrectomy (RAPN). A surgical AI platform system (Theator, Palo Alto, CA) generated real-time annotations and identified operative safety milestones (Image 1). This was achieved through trained algorithms, conventional video recognition, and novel technology called Video Transfer Network which captures clips in full context, enabling automatic recognition and surgical mapping in real-time. RESULTS: Real-time AI annotations for procedure #1, RARP, are found in Table 1. Safety milestone annotations included the apical safety maneuver and structures identification such as the external iliac vessels and the obturator nerve. Real-time AI annotations for procedure #2, RAPN, are found in Table 1. Safety milestones included deliberate views of structures such as the gonadal vessels and the ureter. AI annotated surgical events included intraoperative ultrasound and notable hemorrhage among others. CONCLUSIONS: Surgical intelligence successfully showcased real-time AI annotations of two separate urologic robotic procedures during live telecast for the first time. These annotations may provide the technological framework to send automatic notifications to clinical or operational stakeholders. This technology is a first step in real-time intraoperative decision support; leveraging big data to improve the quality of surgical care, potentially improve surgical outcomes and, support training and education. Source of Funding: N/A © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e1183 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Laura Zuluaga More articles by this author Jordan M. Rich More articles by this author Raghav Gupta More articles by this author Adriana Pedraza More articles by this author Burak Ucpinar More articles by this author Kennedy E. Okhawere More articles by this author Indu Saini More articles by this author Mani Menon More articles by this author Ashutosh Tewari More articles by this author Ketan K Badani More articles by this author Expand All Advertisement PDF downloadLoading ...
Read full abstract