Fetal growth disorders such as fetal growth restriction and macrosomia contribute to perinatal morbidity and long-term health risks in adulthood. Ultrasound is the most common method of diagnosing intrauterine growth abnormalities, but its effectiveness is limited by operator experience and variable accuracy. The review explores the role of artificial intelligence (AI) in the diagnosis and management of these disorders based on database searches. AI models combining maternal, fetal and imaging data achieve accuracy comparable to experienced clinicians, increasing efficiency and reducing variability. These include automated biometrics, predictive models based on biomarkers and Doppler indices, as well as deep learning algorithms on ultrasound scans. These methods improve diagnostic accuracy and access to prenatal care, especially in low-resource settings. However, most studies are retrospective, with small samples and without external validation. AI has potential for earlier diagnosis and individualized monitoring in perinatal medicine.