Groupwise image registration with edge‐based loss for low‐SNR cardiac MRI

• Published in: Magnetic resonance in medicine Vol. 94; no. 3; pp. 1257 - 1268
• Main Authors: Lei, Xuan, Schniter, Philip, Chen, Chong, Ahmad, Rizwan
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.09.2025; John Wiley and Sons Inc
• Subjects: Ablation; Algorithms; cardiovascular MRI; Computer Processing and Modeling; Contrast Media; Deep Learning; Edge detection; Gadolinium; Heart; Heart - diagnostic imaging; Humans; Image Interpretation, Computer-Assisted - methods; Image Processing, Computer-Assisted - methods; Image quality; Image registration; LGE; Magnetic Resonance Imaging - methods; Medical imaging; Noise levels; Phantoms, Imaging; Registration; Robustness; Signal-To-Noise Ratio; Torso; VoxelMorph; cardiovascular MRI; LGE; edge detection; VoxelMorph; image registration
• ISSN: 0740-3194; 1522-2594; 1522-2594
• DOI: 10.1002/mrm.30486

ABSTRACT Purpose The purpose of this study is to perform image registration and averaging of multiple free‐breathing single‐shot cardiac images, where the individual images may have a low signal‐to‐noise ratio (SNR). Methods To address low SNR encountered in single‐shot imaging, especially at low field strengths, we propose a fast deep learning (DL)‐based image registration method, called Averaging Morph with Edge Detection (AiM‐ED). AiM‐ED jointly registers multiple noisy source images to a noisy target image and utilizes a noise‐robust pre‐trained edge detector to define the training loss. We validate AiM‐ED using synthetic late gadolinium enhanced (LGE) images from the MR extended cardiac‐torso (MRXCAT) phantom and free‐breathing single‐shot LGE images from healthy subjects (24 slices) and patients (5 slices) under various levels of added noise. Additionally, we demonstrate the clinical feasibility of AiM‐ED by applying it to data from patients (6 slices) scanned on a 0.55T scanner. Results Compared with a traditional energy‐minimization‐based image registration method and DL‐based VoxelMorph, images registered using AiM‐ED exhibit higher values of recovery SNR and three perceptual image quality metrics. An ablation study shows the benefit of both jointly processing multiple source images and using an edge map in AiM‐ED. Conclusion For single‐shot LGE imaging, AiM‐ED outperforms existing image registration methods in terms of image quality. With fast inference, minimal training data requirements, and robust performance at various noise levels, AiM‐ED has the potential to benefit single‐shot CMR applications.