Multitask Learning for Improved Late Mechanical Activation Detection of Heart from Cine DENSE MRI

TL;DR

This paper presents a multi-task deep learning approach for detecting late mechanical activation in the heart from cine DENSE MRI, improving accuracy especially in scarred myocardium by joint LMA estimation and scar classification.

Contribution

The study introduces a novel multi-task deep learning framework with an auxiliary classification network to enhance LMA detection accuracy and robustness against myocardial scarring.

Findings

Significantly improved LMA detection accuracy over state-of-the-art methods

Enhanced robustness to myocardial scar effects in LMA detection

Better visualization of LMA regions using Grad-CAM

Abstract

The selection of an optimal pacing site, which is ideally scar-free and late activated, is critical to the response of cardiac resynchronization therapy (CRT). Despite the success of current approaches formulating the detection of such late mechanical activation (LMA) regions as a problem of activation time regression, their accuracy remains unsatisfactory, particularly in cases where myocardial scar exists. To address this issue, this paper introduces a multi-task deep learning framework that simultaneously estimates LMA amount and classify the scar-free LMA regions based on cine displacement encoding with stimulated echoes (DENSE) magnetic resonance imaging (MRI). With a newly introduced auxiliary LMA region classification sub-network, our proposed model shows more robustness to the complex pattern cause by myocardial scar, significantly eliminates their negative effects in LMA detection, and in turn improves the performance of scar classification. To evaluate the effectiveness of our method, we tests our model on real cardiac MR images and compare the predicted LMA with the state-of-the-art approaches. It shows that our approach achieves substantially increased accuracy. In addition, we employ the gradient-weighted class activation mapping (Grad-CAM) to visualize the feature maps learned by all methods. Experimental results suggest that our proposed model better recognizes the LMA region pattern.