Automatic left ventricular outflow tract classification for accurate cardiac MR planning

Cardiac MR planning is important to ensure high quality image data and to enable accurate quantification of cardiac function. One result of inaccurate planning is an 'off-axis' orientation of the 4-chamber view, often recognized by the presence of the left ventricular outflow tract (LVOT). This can lead to difficulties in assessment of atrial volumes and septal wall motion, either manually by experts or by automated image analysis algorithms. For large datasets such as the UK biobank, manual labelling is tedious and automated analysis pipelines including automatic image quality assessment need to be developed. In this paper, we propose a method to automatically detect the presence of the LVOT in cardiac MRI, which can aid identifying poorly planned 4-chamber images. Our method is based on Convolutional Neural Networks (CNNs) and is able to detect LVOT in 4-chamber images in less than 1ms. We test our algorithm on a subset of the UK biobank dataset (246 cardiac MR images) and achieve an average accuracy of 83%. We compare our approach to a range of state of the art classification methods.