Joint Deep Learning for Improved Myocardial Scar Detection from Cardiac MRI

TL;DR

This paper introduces a joint deep learning framework that enhances myocardial scar detection from cardiac MRI by integrating myocardium segmentation to reduce noise and artifacts, outperforming existing methods.

Contribution

The novel message passing module enables direct information exchange between myocardium segmentation and scar detection tasks, improving accuracy over previous approaches.

Findings

Outperforms state-of-the-art methods in scar detection accuracy

Effectively reduces noise and artifacts in MRI images

Enhances risk prediction and therapy response in heart disease patients

Abstract

Automated identification of myocardial scar from late gadolinium enhancement cardiac magnetic resonance images (LGE-CMR) is limited by image noise and artifacts such as those related to motion and partial volume effect. This paper presents a novel joint deep learning (JDL) framework that improves such tasks by utilizing simultaneously learned myocardium segmentations to eliminate negative effects from non-region-of-interest areas. In contrast to previous approaches treating scar detection and myocardium segmentation as separate or parallel tasks, our proposed method introduces a message passing module where the information of myocardium segmentation is directly passed to guide scar detectors. This newly designed network will efficiently exploit joint information from the two related tasks and use all available sources of myocardium segmentation to benefit scar identification. We demonstrate the effectiveness of JDL on LGE-CMR images for automated left ventricular (LV) scar detection, with great potential to improve risk prediction in patients with both ischemic and non-ischemic heart disease and to improve response rates to cardiac resynchronization therapy (CRT) for heart failure patients. Experimental results show that our proposed approach outperforms multiple state-of-the-art methods, including commonly used two-step segmentation-classification networks, and multitask learning schemes where subtasks are indirectly interacted.