Trusted Multi-View Deep Learning Classification of Fetal Congenital Heart Disease with Feature-level and Decision-level Fusion
For clinicians diagnosing congenital heart disease, this framework offers a robust tool for early detection, potentially improving diagnostic accuracy and efficiency.
This study develops a multi-view deep learning framework for binary classification of fetal congenital heart disease using echocardiographic images, achieving top-tier performance on a large-scale dataset with five views. The method integrates feature extraction, attention mechanisms, and uncertainty-based decision-making to handle low-quality images.
Congenital heart disease (CHD) refers to the abnormal anatomical structure caused by the abnormal development of the heart and great vessels during embryonic development. Traditional diagnostics often fail to achieve high accuracy and efficiency, especially given the complexity of cardiac anatomy. This study presents a specialized multi-view deep learning framework for CHD binary classification using echocardiographic images. A large-scale CHD dataset, including five views, was used to train the model, enabling it to integrate multi-angle image data. The framework utilizes advanced feature extraction and attention mechanisms to improve diagnostic precision and reliability. An uncertainty-based decision-making component is also integrated to handle low-quality images, enhancing diagnostic outcomes. Experimental results show that this method achieves top-tier performance on our dataset and provides a robust tool for early CHD detection, underscoring its potential for clinical use. The dataset and source code will be released upon paper acceptance.