This study compared AI-based ultrasound assessment with expert ultrasonographers in predicting ovarian response and estimating MII oocyte numbers. AI measured antral follicle count consistently and predicted low ovarian response nearly as accurately as human experts. However, during ovulation trigger monitoring, AI tended to detect fewer large follicles and slightly underestimated MII oocyte numbers. These findings suggest AI can be a reliable tool for planning ovarian stimulation, especially where experienced ultrasonographers are unavailable. Still, caution is needed for trigger day decisions, and further validation in larger studies is recommended to improve confidence in AI performance.