The Folliscan AI model’s ability to measure ovarian follicle diameters was assessed and its performance was compared with expert sonographers across four international IVF clinics. The study showed exceptionally high agreement between AI and clinicians, with ICC values consistently above 0.95 and error levels comparable to, and in some cases lower than inter-physician variability. Folliscan maintained robust accuracy across different ultrasound systems and scanning conditions, demonstrating strong generalizability in real-world clinical settings. These results confirm that AI can match expert-level performance in follicle measurement, supporting more standardized and reliable IVF monitoring. By reducing variability and streamlining the measurement process, Folliscan has the potential to enhance both clinical decision-making and large-scale research.