Nurmaini Siti, Sapitri Ade Iriani, Roseno Muhammad Taufik, Rachmatullah Muhammad Naufal, Mirani Putri, Bernolian Nuswil, Darmawahyuni Annisa, Tutuko Bambang, Firdaus Firdaus, Islami Anggun, Arum Akhiar Wista, Bastian Rio
Intelligent System Research Group, Universitas Sriwijaya, Palembang, Indonesia.
Computer Science Department, Universitas Sumatera Selatan, Palembang, Indonesia.
iScience. 2025 Mar 27;28(5):112288. doi: 10.1016/j.isci.2025.112288. eCollection 2025 May 16.
Enlarged fetal heart conditions may indicate congenital heart diseases or other complications, making early detection through prenatal ultrasound essential. However, manual assessments by sonographers are often subjective, time-consuming, and inconsistent. This paper proposes a deep learning approach using the You Only Look Once (YOLO) architecture to automate fetal heart enlargement assessment. Using a set of ultrasound videos, YOLOv8 with a CBAM module demonstrated superior performance compared to YOLOv11 with self-attention. Incorporating the ResNeXtBlock-a residual network with cardinality-additionally enhanced accuracy and prediction consistency. The model exhibits strong capability in detecting fetal heart enlargement, offering a reliable computer-aided tool for sonographers during prenatal screenings. Further validation is required to confirm its clinical applicability. By improving early and accurate detection, this approach has the potential to enhance prenatal care, facilitate timely interventions, and contribute to better neonatal health outcomes.
胎儿心脏增大情况可能表明患有先天性心脏病或其他并发症，因此通过产前超声进行早期检测至关重要。然而，超声检查人员的手动评估往往具有主观性、耗时且不一致。本文提出一种使用You Only Look Once（YOLO）架构的深度学习方法，以实现胎儿心脏增大评估的自动化。使用一组超声视频，带有CBAM模块的YOLOv8与带有自注意力机制的YOLOv11相比表现出更优的性能。结合ResNeXtBlock（一种具有基数的残差网络）进一步提高了准确性和预测一致性。该模型在检测胎儿心脏增大方面表现出强大的能力，为超声检查人员在产前筛查期间提供了一个可靠的计算机辅助工具。需要进一步验证以确认其临床适用性。通过改进早期和准确检测，这种方法有可能加强产前护理，促进及时干预，并有助于改善新生儿健康结局。
