Biologically Inspired Deep Learning Approaches for Fetal Ultrasound Image Classification
This addresses the challenge of accurate fetal anatomy recognition in clinical settings with low image quality and variability, though it is incremental as it builds on existing deep learning methods.
The paper tackled the problem of classifying second-trimester fetal ultrasound images by introducing a biologically inspired deep learning ensemble framework that simultaneously distinguishes 16 fetal structures, achieving accuracy > 0.75 for 90% of organs and > 0.85 for 75% of organs on a dataset of 5,298 clinical images.
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.