The classification of fetal ultrasound images represents a major challenge in prenatal care, essential for the early detection of anomalies and accurate fetal health assessment. While traditional Convolutional Neural Networks (CNNs) have demonstrated effectiveness, they often face significant limitations due to the high-dimensional and complex nature of ultrasound data, leading to increased computational costs and longer training times. In this study, we propose a novel classification framework based on Quantum Neural Networks (QNNs), leveraging the principles of quantum computing to address the intrinsic limitations of classical deep learning approaches. Unlike conventional CNNs, QNNs are inherently better equipped to handle high-dimensional data spaces, enabling faster convergence and more efficient computation. Our experimental evaluation, conducted on a comprehensive dataset of annotated fetal ultrasound videos collected from four healthcare centers across Morocco, highlights the superiority of the QNN-based model. It achieves a classification accuracy of up to 0.99 while reducing training time to approximately 4 s per epoch—a significant improvement compared to classical architectures. These results not only underscore the effectiveness of QNNs in complex medical imaging tasks, but also pave the way for future development of quantum-enhanced diagnostic tools in prenatal care, offering a promising step toward faster, more precise, and resource-efficient fetal health screening.