Islam Umar, Ali Yasser A, Al-Razgan Muna, Ullah Hanif, Almaiah Mohmmed Amin, Tariq Zeeshan, Wazir Khalid Mohammad
Department of Computer Science, IQRA National University, Swat Campus, KPK, Peshawar, Pakistan.
Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, P.O. Box 51178, Riyadh 11543, Saudi Arabia.
Sci Rep. 2025 Jul 15;15(1):25665. doi: 10.1038/s41598-025-06526-4.
Ultrasound imaging plays an important role in fetal growth and maternal-fetal health evaluation, but due to the complicated anatomy of the fetus and image quality fluctuation, its interpretation is quite challenging. Although deep learning include Convolution Neural Networks (CNNs) have been promising, they have largely been limited to one task or the other, such as the segmentation or detection of fetal structures, thus lacking an integrated solution that accounts for the intricate interplay between anatomical structures. To overcome these limitations, Fetal-Net-a new deep learning architecture that integrates Multi-Scale-CNNs and transformer layers-was developed. The model was trained on a large, expertly annotated set of more than 12,000 ultrasound images across different anatomical planes for effective identification of fetal structures and anomaly detection. Fetal-Net achieved excellent performance in anomaly detection, with precision (96.5%), accuracy (97.5%), and recall (97.8%) showed robustness factor against various imaging settings, making it a potent means of augmenting prenatal care through refined ultrasound image interpretation.
超声成像在胎儿生长和母胎健康评估中发挥着重要作用，但由于胎儿解剖结构复杂且图像质量波动，其解读颇具挑战性。尽管包括卷积神经网络（CNNs）在内的深度学习一直很有前景，但它们在很大程度上局限于某一项任务，比如胎儿结构的分割或检测，因此缺乏一种能解释解剖结构之间复杂相互作用的综合解决方案。为克服这些局限性，研发了Fetal-Net——一种整合了多尺度卷积神经网络和变压器层的新型深度学习架构。该模型在一组经过专家精心标注的、超过12000张跨越不同解剖平面的超声图像上进行训练，以有效识别胎儿结构并检测异常。Fetal-Net在异常检测方面表现出色，其精确率（96.5%）、准确率（97.5%）和召回率（97.8%）显示出对各种成像设置的稳健性，使其成为通过精细的超声图像解读来加强产前护理的有力手段。
