Learning-Based Heart Coverage Estimation for Short-Axis Cine Cardiac MR Images.

The correct acquisition of short axis (SA) cine cardiac MR image stacks requires the imaging of the full cardiac anatomy between the apex and the mitral valve plane via multiple 2D slices. While in the clinical practice the SA stacks are usually checked qualitatively to ensure full heart coverage, visual inspection can become infeasible for large amounts of imaging data that is routinely acquired, e.g. in population studies such as the UK Biobank (UKBB). Accordingly, we propose a learning-based technique for the fully-automated estimation of the heart coverage for SA image stacks. The technique relies on the identification of cardiac landmarks (i.e. the apex and the mitral valve sides) on two chamber view long axis images and on the comparison of the landmarks' positions to the volume covered by the SA stack. Landmark detection is performed using a hybrid random forest approach integrating both regression and structured classification models. The technique was applied on 3000 cases from the UKBB and compared to visual assessment. The obtained results (error rate = 2.3%, sens. = 73%, spec. = 90%) indicate that the proposed technique is able to correctly detect the vast majority of the cases with insufficient coverage, suggesting that it could be used as a fully-automated quality control step for CMR SA image stacks.