Deep Learning Model for Estimation of LV Ejection Fraction from Echocardiogram

Abstract

Heart failure, a leading global cause of death, poses challenges for early prediction of cardiac dysfunction, especially ejection fraction (EF). This study employs Convolutional Neural Networks (CNNs), utilizing ResNet and MobileNet architectures, on the CAMUS dataset with 500 patient records (2CH and 4CH). The goal is to aid healthcare professionals in accurately measuring EF. The CAMUS dataset, comprising multi-modality cardiac imaging and segmentation data, serves as the foundation. The CNN, ResNet, and MobileNet models are fine-tuned through transfer learning and their performance is evaluated based on accuracy. This comparative analysis identifies the model with the best predictive capabilities for EF, showcasing their potential for earlier diagnosis and intervention. Deep learning techniques enhance cardiac healthcare by providing reliable, noninvasive means of predicting heart failure, reducing its impact on patients and healthcare systems.