Keywords:
Computer Applications-Detection, diagnosis, MR, Cardiovascular system, Cardiac, Ischaemia / Infarction
Authors:
T. Gassenmaier, J. Heidenreich, T. A. Bley, T. Wech; Würzburg/DE
Methods and Materials
A convolutional neural network for semantic segmentation of endo- and epicardial borders was pre-trained using 100.248 cardiac cine MR images from the public Kaggle second annual data-science-bowl-database [1], and labels obtained using the method presented in [2]. Transfer learning was then used to qualify the network for the segmentation of left-ventricular images with LE contrast in short axis. LE images and manual segmentation labels from 216 patients with history of acute myocardial infarction of our local database were used for this purpose (~2.200 images in total).
The obtained network was then applied to the LE image stacks of 26 patients with history of acute myocardial infarction which were not part of the training dataset, and the obtained segments were compared to the segments obtained manually by an experienced operator using the Sørensen–Dice coefficient.