Automatic Left Ventricle Segmentation from Short-Axis Cardiac MRI Images Based on Fully Convolutional Neural Network.

Zakarya Farea Shaaf,Muhammad Mahadi Abdul Jamil,Anwar Ali Yahya,Radzi Ambar,Yousef Asiri,Ahmed Abdu Alattab

doi:10.3390/diagnostics12020414

Abstract

Background: Left ventricle (LV) segmentation using a cardiac magnetic resonance imaging (MRI) dataset is critical for evaluating global and regional cardiac functions and diagnosing cardiovascular diseases. LV clinical metrics such as LV volume, LV mass and ejection fraction (EF) are frequently extracted based on the LV segmentation from short-axis MRI images. Manual segmentation to assess such functions is tedious and time-consuming for medical experts to diagnose cardiac pathologies. Therefore, a fully automated LV segmentation technique is required to assist medical experts in working more efficiently. Method: This paper proposes a fully convolutional network (FCN) architecture for automatic LV segmentation from short-axis MRI images. Several experiments were conducted in the training phase to compare the performance of the network and the U-Net model with various hyper-parameters, including optimization algorithms, epochs, learning rate, and mini-batch size. In addition, a class weighting method was introduced to avoid having a high imbalance of pixels in the classes of image’s labels since the number of background pixels was significantly higher than the number of LV and myocardium pixels. Furthermore, effective image conversion with pixel normalization was applied to obtain exact features representing target organs (LV and myocardium). The segmentation models were trained and tested on a public dataset, namely the evaluation of myocardial infarction from the delayed-enhancement cardiac MRI (EMIDEC) dataset. Results: The dice metric, Jaccard index, sensitivity, and specificity were used to evaluate the network’s performance, with values of 0.93, 0.87, 0.98, and 0.94, respectively. Based on the experimental results, the proposed network outperforms the standard U-Net model and is an advanced fully automated method in terms of segmentation performance. Conclusion: This proposed method is applicable in clinical practice for doctors to diagnose cardiac diseases from short-axis MRI images.

Highlights

Cardiovascular disease is regarded as one of the most severe threats to human health, and it has contributed to an increase in the global mortality rate
There is a growing emphasis on research and technologies that can effectively improve the diagnosis of cardiovascular diseases while lowering the mortality rate caused by those diseases
The initial experiments were conducted to select the hyper-parameters used for the training of the proposed network

Summary

Introduction

Cardiovascular disease is regarded as one of the most severe threats to human health, and it has contributed to an increase in the global mortality rate. Health Organization, 17.9 million people died from cardiovascular disease in 2016, accounting for 31% of worldwide deaths [1]. The diagnosis of cardiovascular diseases has become more accessible thanks to advancements in medical. There is a growing emphasis on research and technologies that can effectively improve the diagnosis of cardiovascular diseases while lowering the mortality rate caused by those diseases. The diagnosis of cardiovascular diseases has become more accessible thanks to advancements in medical imaging techniques such as computed tomography (CT) and cardiac imaging techniques such as computed magnetic resonance imaging (CMRI). The diagnosis of cardiovascular diseases has become more accessible thanks to advancements in medical imaging techniques such as computed tomography (CT) and cardiac imaging techniques such as computed magnetic resonance imaging (CMRI). tomography (CT) and cardiac magnetic resonance imaging (CMRI)

Objectives

Methods

Results

Conclusion