Abstract
Coronary artery disease (CAD) is the most common cause of death globally, and its diagnosis is usually based on manual myocardial (MYO) segmentation of MRI sequences. As manual segmentation is tedious, time-consuming, and with low replicability, automatic MYO segmentation using machine learning techniques has been widely explored recently. However, almost all the existing methods treat the input MRI sequences independently, which fails to capture the temporal information between sequences, e.g., the shape and location information of the myocardium in sequences along time. In this article, we propose a MYO segmentation framework for sequence of cardiac MRI (CMR) scanning images of the left ventricular (LV) cavity, right ventricular (RV) cavity, and myocardium. Specifically, we propose to combine conventional neural networks and recurrent neural networks to incorporate temporal information between sequences to ensure temporal consistency. We evaluated our framework on the automated cardiac diagnosis challenge (ACDC) dataset. The experiment results demonstrate that our framework can improve the segmentation accuracy by up to 2% in the Dice coefficient.
Highlights
Coronary artery disease (CAD) is the most common cause of death globally
Bernard et al [3] obtained these parameters from cardiac MRI (CMR) images using an accurate segmentation of CMR image for the left ventricular (LV) cavity, right ventricular (RV) cavity, and the myocardium at end-diastolic (ED) frame and end-systolic (ES) frame can give out an accurate diagnostic of cardiac function
This is because the flow of blood in the RV cavity leads to the brightness heterogeneity in the RV area of the CMR image, which makes the image intensity of the ground truth RV region similar to the surrounding cardiac structures, and leads to segmentation failure
Summary
Coronary artery disease (CAD) is the most common cause of death globally It affects more than 100 million people, and results in about 10 million death each year [1]. Cardiac MRI image is a widely used imaging tool for the assessment of MYO micro-circulation. It utilizes the electromagnetic signal with characteristic frequency produced by the hydrogen nuclei under a strong contrasting magnetic field and weak oscillating near field as the imaging agent. Due to the high capacity for discriminating different types of tissues, CMR image is one of the most prominent standards for cardiac diagnosis through the assessment of the left and right ventricular EF and SV, the left ventricle mass and the myocardium thickness. The label shows the ground truth of segment results for different parts of the CMR image
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.