Title
Automatic ventricular nuclear magnetic resonance image processing with deep learning
Publication Name
Multimedia Tools and Applications
Abstract
Cardiovascular diseases (CVD) seriously threaten the health of human beings, and they have caused widespread concern in recent years. At present, the diagnosis of CVD is mainly conducted by computed tomography (CT), echocardiography and nuclear magnetic resonance (NMR) technologies. NMR imaging technology is widely used in medical applications owing to its characteristics of high resolution and very low radiation. However, manual NMR image segmentation is time-consuming and error-prone, which has led to the research on automatic NMR image segmentation technologies. Researchers tend to explore the ventricular NRM image segmentation to improve the accuracy of CVD diagnosis. In this study, based on deep learning technology, we propose a layered Mask R-CNN segmentation method to segment ventricular NMR images. The experimental results show that the mean dice metrics (DM) of left ventricular segmentation and right ventricular segmentation are 0.92 and 0.89, and the Hausdorff distance (HD) metrics are 4.78 mm and 7.03 mm. Our research indicates that the proposed novel method has great potential to automate the ventricular NMR image segmentation. We also discuss the automatic abnormal ventricular systolic function detection method based on the proposed layered segmentation model.
Open Access Status
This publication may be available as open access
Volume
80
Issue
26-27
First Page
34103
Last Page
34119
Funding Number
227000-560001
Funding Sponsor
National Natural Science Foundation of China