Gradient Class Activation Mapping (GradCAM) Artificial Intelligence (AI) Explainability Technique Applied to a Video-Based Deep Neural Network (DNN) Trained to Predict LVEF

We developed a video-based deep neural network (DNN) called CathEF to estimate left ventricular ejection fraction (LVEF), a measure of cardiac systolic function, from standard angiogram videos of the left coronary artery. Understanding cardiac systolic function during coronary angiography can assist patient management and therapeutic decision-making. This video shows an angiogram video from a patient with normal left ventricular ejection fraction (left) and the corresponding video of guided GradCAM saliency maps (right), which as an artificial intelligence explainability technique. The guided GradCAM saliency maps highlight pixels in each frame that contribute the most to CathEF’s prediction of low LVEF in this video. Pixels predominantly around the coronary artery tree are highlighted, mainly during the systolic phase of the cardiac cycle. This provides insight into how the video-based DNN achieves its estimation of LVEF from standard coronary angiograms. Click the Related Article link for full details.