An efficient network with state space model under evidential training for fetal echocardiography standard view recognition.

Abstract

Fetal congenital heart disease (FCHD) represents a serious and prevalent congenital malformation. However, there exist notable regional disparities in the detection rates of fetal heart abnormalities. To enhance the diagnostic capabilities of ultrasound physicians in primary hospitals regarding fetal heart structures, the adoption of artificial intelligence technology to assist in acquiring high-quality, standard fetal echocardiographic images is of paramount importance. Currently, primary hospitals face challenges in recognizing standard views in fetal echocardiography, particularly under resource-constrained conditions. Efficient and accurate identification of fetal heart structures has become an urgent issue to address. Despite existing research efforts dedicated to the recognition of standard views in fetal echocardiography, current methods still suffer from limitations in computational complexity, feature extraction capabilities, and long-distance feature capturing, hindering their widespread application in ultrasound diagnosis at primary hospitals. Specifically, the literature lacks an efficient and robust model that can effectively balance high accuracy in standard view recognition with low computational complexity and fast inference times. The need for a model that can accurately capture long-distance features while maintaining efficiency is particularly acute in the context of primary hospitals, where resources are limited and the demand for accurate fetal heart assessments is high. To address these issues, the present study proposes an efficient network based on a state-space model trained with evidence for standard view recognition in fetal echocardiography. This method integrates a visual state space (VSS) model, which boasts powerful feature extraction capabilities and effective long-distance feature capturing, while significantly reducing computational complexity and facilitating efficient model inference. In the collected dataset, the proposed model achieved an accuracy of 99.32% and an F1-score of 99.29% in identifying eight standard views of fetal echocardiography. Furthermore, the model exhibited the lowest floating point operations per second (FLOPs), parameters, and inference time, while achieving the highest frames per second (FPS). This achievement not only provides a solid technical foundation for intelligent diagnosis of FCHD but also serves as an auxiliary tool for junior or novice sonographers at primary hospitals in acquiring basic views of fetal heart structures.