Detection of fetal congenital heart defects on three-vessel view ultrasound videos

Detecting congenital heart defects (CHDs) is challenging due to the difficulty of identifying subtle abnormalities in fetal heart structures. To develop a deep learning-based method for segmenting vessels in the three-vessel view (3VV) to characterise the vessels by size and spatial relationships to detect abnormal fetal hearts. We present a deep learning-based method that takes as input a fetal heart ultrasound (US) video of the three vessels view (3VV) and an anchor frame, which contains the segmentation of the pulmonary artery (PA), aorta (Ao), and superior vena cava (SVC) in the 3VV. The method automatically segments the anatomical structures subsequent to the anchor frame and classifies the US video as normal or abnormal. The method consists of two phases. The first phase combines three residual networks (ResNets) extended with a self-attention block and a refinement module. The second phase extends a ResNet with two CoordConv layers integrating spatial coordinates. We assess segmentation performance using the intersection over union (IoU) and dice similarity coefficient (DSC) metrics and classification of US videos using sensitivity and specificity. We also investigate the tolerance to failure of the method by introducing mislabelled anchor frames. The dataset used in this study consists of 150 US videos of the 3VV; 50 videos were used for training, and 100 videos (50 normal videos, 50 abnormal videos) for testing. In terms of anatomical structure segmentation accuracy, the method achieves an average IoU of 89.5% (99.5% for PA, 85.0% for Ao, and 84.1% for SVC), and an average DSC of 0.950% (0.946% for PA, 0.969% for Ao, and 0.934% for SVC). Detection of abnormal videos achieved a sensitivity of 0.99 and specificity of 1.0. The tolerance to failure analysis shows a decrease in the sensitivity of 0.023 and 0.015 for normal and abnormal case videos, respectively. The initial evaluation of our approach to fetal CHDs on 3VV ultrasound videos is promising but requires further refinement and evaluation on a larger dataset to assess clinical utility. The approach is designed to be translatable to low-resource settings where fetal echocardiography experts are unavailable due to the simple acquisition protocol. • First work on segmenting vessels in 3VV of ultrasound videos to detect CHDs. • Two-phase method segments frames and characterises vessels to detect abnormalities. • Method refines segmentation across frames to classify normal and abnormal hearts.