Accuracy of Large Language Model–based Automatic Calculation of Ovarian-Adnexal Reporting and Data System MRI Scores from Pelvic MRI Reports
Rajesh Bhayana, Ankush Jajodia, Tanya Chawla, Yangqing Deng, Geneviève Bouchard‐Fortier, Masoom A. Haider, Satheesh Krishna
Abstract
= .01). Conclusion A hybrid LLM-based application, combining LLM feature classification with deterministic elements, accurately assigned O-RADS MRI scores from report descriptions, exceeding both an LLM-only strategy and the original reporting radiologist. © RSNA, 2025
Topics & Concepts
MedicineAdnexal DiseasesFeature (linguistics)RadiologyAdnexal massNatural language processingArtificial intelligenceMedical physicsComputer scienceLinguisticsLaparoscopyPhilosophyOvarian cancer diagnosis and treatmentRadiomics and Machine Learning in Medical ImagingEndometrial and Cervical Cancer Treatments