Journal
FRONTIERS IN CARDIOVASCULAR MEDICINE
Volume 8, Issue -, Pages -Publisher
FRONTIERS MEDIA SA
DOI: 10.3389/fcvm.2021.807728
Keywords
cardiac anatomy; machine learning; left ventricle; MRI; deep learning
Categories
Funding
- Health Research Council of New Zealand [17/608, 17/234]
- National Heart, Lung, and Blood Institute (NHLBI)
- MESA [N01-HC-95159, N01-HC-95160, N01-HC-95161, N01-HC-95162, N01-HC-95163, N01-HC-95164, N01-HC-95165, N01-HC-95166, N01-HC-95167, N01-HC-95168, N01-HC-95169, CTSA UL1-RR-024156]
Ask authors/readers for more resources
The study aimed to develop a fully automated CMR analysis pipeline that leverages machine learning algorithms to extract additional information from a large-scale legacy dataset. The results showed that the proposed pipeline not only enables the automated assessment of additional measures of ventricular function but also allows the study of relationships between cardiac morphologies and future cardiac events in a large-scale population study.
The Multi-Ethnic Study of Atherosclerosis (MESA), begun in 2000, was the first large cohort study to incorporate cardiovascular magnetic resonance (CMR) to study the mechanisms of cardiovascular disease in over 5,000 initially asymptomatic participants, and there is now a wealth of follow-up data over 20 years. However, the imaging technology used to generate the CMR images is no longer in routine use, and methods trained on modern data fail when applied to such legacy datasets. This study aimed to develop a fully automated CMR analysis pipeline that leverages the ability of machine learning algorithms to enable extraction of additional information from such a large-scale legacy dataset, expanding on the original manual analyses. We combined the original study analyses with new annotations to develop a set of automated methods for customizing 3D left ventricular (LV) shape models to each CMR exam and build a statistical shape atlas. We trained VGGNet convolutional neural networks using a transfer learning sequence between two-chamber, four-chamber, and short-axis MRI views to detect landmarks. A U-Net architecture was used to detect the endocardial and epicardial boundaries in short-axis images. The landmark detection network accurately predicted mitral valve and right ventricular insertion points with average error distance <2.5 mm. The agreement of the network with two observers was excellent (intraclass correlation coefficient >0.9). The segmentation network produced average Dice score of 0.9 for both myocardium and LV cavity. Differences between the manual and automated analyses were small, i.e., <1.0 +/- 2.6 mL/m(2) for indexed LV volume, 3.0 +/- 6.4 g/m(2) for indexed LV mass, and 0.6 +/- 3.3% for ejection fraction. In an independent atlas validation dataset, the LV atlas built from the fully automated pipeline showed similar statistical relationships to an atlas built from the manual analysis. Hence, the proposed pipeline is not only a promising framework to automatically assess additional measures of ventricular function, but also to study relationships between cardiac morphologies and future cardiac events, in a large-scale population study.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available