Cardiac magnetic resonance (CMR) imaging is commonly performed using ECG-triggering to restrain acquisition to a quiescent phase of the cardiac cycle (i.e. end-systole or mid-diastole). Identification of the rest periods is commonly performed by visual inspection on CINE images and is thus operator dependent, time consuming and requires a trained operator. In this study, a fully automated method was developed to detect the quiescent cardiac periods of the cardiac cycle from CINE images using an integrated convolutional neural network (CNN) and long short-term memory (CNN-LSTM) network.
This abstract and the presentation materials are available to members only; a login is required.