This article introduces Female-RHINO, a real-time AI-assisted framework that integrates with MRI scanners to perform automated quantitative uterine analysis and structured reporting during image acquisition. The system combines deep learning models for segmentation and landmark detection to derive biomarkers from sagittal T2-weighted pelvic MRI without manual interaction.
- Integrates inline communication with the MRI scanner for real-time processing, completing end-to-end analysis in under 70 seconds.
- Trained on over 500 multi-center datasets, achieving mean Dice similarity coefficients of 0.82 for the uterus and 0.80 for fibroids.
- Detects and quantifies incidental findings such as fibroids and Nabothian cysts while extracting six anatomical landmarks with a mean radial error of 3.7 mm.
- Generates clinician-oriented reports with integrated visualizations, demonstrating robust performance across diverse protocols, vendors, and patient populations in retrospective and prospective evaluations.
The system enables immediate, standardized, and reproducible uterine MRI analysis during scans, potentially improving standardization, efficiency, and clinical workflow in pelvic imaging.