Computational Platform Based on Deep Learning for Segmenting Ventricular Endocardium in Long-axis Cardiac MR Imaging.

This paper presents an automated computational platform based on deep learning (DL) approach for left ventricular (LV) and right ventricular (RV) endocardium segmentation in long-axis cine cardiovascular magnetic resonance (CMR). The proposed method uses modified deep U-Net convolutional networks. We trained our model using 4800 images from 40 human subjects (20 healthy volunteers, 20 patients with various cardiac diseases) and validated the technique in 6000 images from 50 subjects (10 healthy volunteers, 40 patients). An average Dice metric of 0.929 ± 0.036 along with an average Jaccard index of 0.869 ± 0.059 were achieved for all the studied subjects. In addition, a high level of correlation and agreement with the ground truth contours for LV ejection fraction (R=0.975), LV fractional area change (R=0.959 to 0.971), and RV fractional area change (R=0.927) were observed. The proposed DL-based segmentation process took less than 3 seconds per subject (or < 30 milliseconds per image over 120 images for each subject). Therefore, our proposed framework offers a promising means to achieve fully automated and rapid segmentation for both LV and RV endocardium in long-axis cine CMR images using an appropriately trained deep convolutional neural network.