A fully automated deep learning pipeline achieved a mean Dice coefficient of 0.63 for left ventricular trabeculation segmentation, significantly outperforming human interobserver measures.
Observational (n=449)
Single-blind
Yes
Does a deep learning-based automated segmentation pipeline improve the accuracy and reproducibility of left ventricular trabeculation and myocardium segmentation on cardiac MR images compared to manual segmentation?
A fully automated deep learning pipeline provides fast, reproducible, and accurate segmentation of left ventricular trabeculations on cardiac MRI, outperforming human intra- and interobserver reliability.
Absolute Event Rate: 0.63% vs 0.44%
p-value: p=<0.01
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. Supplemental material is available for this article. Keywords: Cardiac, Convolutional Neural Network (CNN), Segmentation © RSNA, 2020
Bartoli et al. (2020) conducted an observational in Excessive trabeculation cardiomyopathy (ETCM) and other cardiomyopathies (n=449). Deep learning-based automated segmentation pipeline vs. Manual segmentation by human observers was evaluated on Mean Dice coefficient for left ventricular trabeculation segmentation (p=<0.01). A fully automated deep learning pipeline achieved a mean Dice coefficient of 0.63 for left ventricular trabeculation segmentation, significantly outperforming human interobserver measures.