2025/06/10 by Rinat Prochii, Prochii, Rinat, Elizaveta Dakhova +5
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Electrical engineering #Fetal and Pediatric Neurological Disorders #Image and Video Processing (eess.IV) #Prenatal Screening and Diagnostics #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2506.08623
openalex publication_date 2025/06/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Accurate classification of second-trimester fetal ultrasound images remains challenging due to low image quality, high intra-class variability, and significant class imbalance. In this work, we introduce a simple yet powerful, biologically inspired deep learning ensemble framework that-unlike prior studies focused on only a handful of anatomical targets-simultaneously distinguishes 16 fetal structures. Drawing on the hierarchical, modular organization of biological vision systems, our model stacks two complementary branches (a "shallow" path for coarse, low-resolution cues and a "detailed" path for fine, high-resolution features), concatenating their outputs for final prediction. To our knowledge, no existing method has addressed such a large number of classes with a comparably lightweight architecture. We trained and evaluated on 5,298 routinely acquired clinical images (annotated by three experts and reconciled via Dawid-Skene), reflecting real-world noise and variability rather than a "cleaned" dataset. Despite this complexity, our ensemble (EfficientNet-B0 + EfficientNet-B6 with LDAM-Focal loss) identifies 90% of organs with accuracy > 0.75 and 75% of organs with accuracy > 0.85-performance competitive with more elaborate models applied to far fewer categories. These results demonstrate that biologically inspired modular stacking can yield robust, scalable fetal anatomy recognition in challenging clinical settings.