Cascaded Convolutional Neural Network for Automatic Myocardial Infarction Segmentation from Delayed-Enhancement Cardiac MRI
This work provides an improved automatic segmentation method for myocardial infarction, which is crucial for quantitative evaluation in cardiac patients.
This paper addresses the automatic segmentation of myocardial infarction from delayed-enhancement cardiac MRI, achieving average Dice scores of 0.8786 for myocardium, 0.7124 for infarction, and 0.7851 for no-reflow on the MICCAI 2020 EMIDEC challenge dataset, outperforming all other teams.
Automatic segmentation of myocardial contours and relevant areas like infraction and no-reflow is an important step for the quantitative evaluation of myocardial infarction. In this work, we propose a cascaded convolutional neural network for automatic myocardial infarction segmentation from delayed-enhancement cardiac MRI. We first use a 2D U-Net to focus on the intra-slice information to perform a preliminary segmentation. After that, we use a 3D U-Net to utilize the volumetric spatial information for a subtle segmentation. Our method is evaluated on the MICCAI 2020 EMIDEC challenge dataset and achieves average Dice score of 0.8786, 0.7124 and 0.7851 for myocardium, infarction and no-reflow respectively, outperforms all the other teams of the segmentation contest.