Deep Learning-based Automated Segmentation of Left Ventricular Trabeculations and Myocardium on Cardiac MR Images: A Feasibility Study

Purpose: To develop and evaluate a complete deep learning pipeline that allows fully automated end-diastolic left ventricle (LV) cardiac MRI segmentation, including trabeculations and automatic quality control of the predicted segmentation. Materials and Methods: This multicenter retrospective study includes training, validation, and testing datasets of 272, 27, and 150 cardiac MR images, respectively, collected between 2012 and 2018. The reference standard was the manual segmentation of four LV anatomic structures performed on end-diastolic short-axis cine cardiac MRI: LV trabeculations, LV myocardium, LV papillary muscles, and the LV blood cavity. The automatic pipeline was composed of five steps with a DenseNet architecture. Intraobserver agreement, interobserver agreement, and interaction time were recorded. The analysis includes the correlation between the manual and automated segmentation, a reproducibility comparison, and Bland-Altman plots. Results: The automated method achieved mean Dice coefficients of 0.96 +/- 0.01 (standard deviation) for LV blood cavity, 0.89 +/- 0.03 for LV myocardium, and 0.62 +/- 0.08 for LV trabeculation (mean absolute error, 3.63 g +/- 3.4). Automatic quantification of LV end-diastolic volume, LV myocardium mass, LV trabeculation, and trabeculation mass-to-total myocardial mass (TMM) ratio showed a significant correlation with the manual measures (r = 0.99, 0.99, 0.90, and 0.83, respectively; all P<.01). On a subset of 48 patients, the mean Dice value for LV trabeculation was 0.63 +/- 0.10 or higher compared with the human interobserver (0.44 +/- 0.09; P<.01) and intraobserver measures (0.58 +/- 0.09; P<.01). Automatic quantification of the trabeculation mass-to-TMM ratio had a higher correlation (0.92) compared with the intra- and interobserver measures (0.74 and 0.39, respectively; both P<.01). Conclusion: Automated deep learning framework can achieve reproducible and quality-controlled segmentation of cardiac trabeculations, outperforming inter- and intraobserver analyses. (C) RSNA, 2020

Automated summary

The study developed and evaluated a complete deep learning pipeline for the fully automated end-diastolic left ventricle cardiac MRI segmentation, including trabeculations and automatic quality control. The automated method achieved high segmentation accuracy and showed significant correlation with manual segmentation. The automated segmentation technology holds promise for potential applications in cardiac MRI image processing.