Fully automated deep learning based segmentation of normal, infarcted and edema regions from multiple cardiac MRI sequences

TL;DR

This paper presents a fully automated deep learning method for segmenting various cardiac regions and pathologies from multiple MRI sequences, improving accuracy in myocardial characterization.

Contribution

The study introduces a novel CNN-based approach with data augmentation and specialized modules for multi-sequence cardiac MRI segmentation, validated on MICCAI 2020 challenge data.

Findings

Achieved mean dice scores of 46.8% for LV scars.

Achieved mean dice scores of 55.7% for LV edema and scars.

Demonstrated improved segmentation accuracy over existing methods.

Abstract

Myocardial characterization is essential for patients with myocardial infarction and other myocardial diseases, and the assessment is often performed using cardiac magnetic resonance (CMR) sequences. In this study, we propose a fully automated approach using deep convolutional neural networks (CNN) for cardiac pathology segmentation, including left ventricular (LV) blood pool, right ventricular blood pool, LV normal myocardium, LV myocardial edema (ME) and LV myocardial scars (MS). The input to the network consists of three CMR sequences, namely, late gadolinium enhancement (LGE), T2 and balanced steady state free precession (bSSFP). The proposed approach utilized the data provided by the MyoPS challenge hosted by MICCAI 2020 in conjunction with STACOM. The training set for the CNN model consists of images acquired from 25 cases, and the gold standard labels are provided by trained raters and validated by radiologists. The proposed approach introduces a data augmentation module, linear encoder and decoder module and a network module to increase the number of training samples and improve the prediction accuracy for LV ME and MS. The proposed approach is evaluated by the challenge organizers with a test set including 20 cases and achieves a mean dice score of $46.8\%$ for LV MS and $55.7\%$ for LV ME+MS