A Review on the Integration of Artificial Intelligence and Medical Imaging in IVF Ovarian Stimulation

AI shows promise for optimizing IVF treatment decisions: The review of 13 studies found that AI algorithms demonstrated "notable potential in predicting optimal hormonal dosages, trigger timing, and oocyte retrieval outcomes," suggesting AI could help personalize treatment protocols during ovarian stimulation.

Current AI applications use only basic imaging analysis: Most studies relied on simple two-dimensional ultrasound measurements (follicle size and number) rather than advanced image analysis techniques, meaning the full potential of AI combined with medical imaging remains largely untapped and represents a significant opportunity for improvement.

Lack of transparency threatens clinical trust and adoption: The review identifies a critical gap: "the lack of explainable AI (XAI) in most studies raises concerns about the transparency and traceability of AI-driven decisions" — essential factors for doctors and patients to understand and trust AI recommendations in clinical settings.

Limited research scope reduces real-world applicability: Many studies used "single-center designs and small datasets, which limit the generalizability of their findings," meaning results from these studies may not reliably apply to diverse patient populations or different medical settings.

Significant development needed before widespread clinical use: The review indicates that responsible integration of AI in IVF requires advances in explainability, larger multi-center studies, more sophisticated imaging techniques, and deeper feature extraction to move from promising research to trustworthy clinical tools.