Anatomy-Aware Deep Unrolling for Task-Oriented Acceleration of Multi-Contrast MRI

• Published in: IEEE transactions on medical imaging Vol. 44; no. 9; pp. 3832 - 3844
• Main Authors: He, Yuzhu, Lian, Chunfeng, Xiao, Ruyi, Ju, Fangmao, Zou, Chao, Xu, Zongben, Ma, Jianhua
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2025
• Subjects: Algorithms; Brain - diagnostic imaging; Deep Learning; Humans; Image Processing, Computer-Assisted - methods; Image quality; Image reconstruction; Image segmentation; Imaging; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; model-based deep learning; MRI; multi-contrast; Noise reduction; Pathology; Protocols; task-oriented imaging; Training; Trajectory optimization
• ISSN: 0278-0062; 1558-254X; 1558-254X
• DOI: 10.1109/TMI.2025.3568157

Multi-contrast magnetic resonance imaging (MC-MRI) plays a crucial role in clinical practice. However, its performance is hindered by long scanning times and the isolation between image acquisition and downstream clinical diagnoses/treatments. Despite the activated research on accelerated MC-MRI, few existing studies prioritize personalized imaging tailored to individual patient characteristics and clinical needs. That is, the current approach often aims to enhance overall image quality, disregarding the specific pathologies or anatomical regions that are of particular interest to clinicians. To tackle this challenge, we propose an anatomy-aware unrolling-based deep network, dubbed as <inline-formula> <tex-math notation="LaTeX">\text {A}^{{2}} </tex-math></inline-formula> MC-MRI, offering promising interpretability and learning capacity for fast MC-MRI catering to downstream clinical needs. The network is unfolded from the iterative algorithm designed for a task-oriented MC-MRI reconstruction model. Specifically, to enhance concurrent MC-MRI of specific targets of interest (TOIs), the model integrates a learnable group sparsity with an anatomy-aware denoising prior. Within the anatomy-aware denoising prior, a segmentation network is involved to provide critical location information for TOI-enhanced denoising. Finally, such an unrolled network is jointly learned with k-space sampling patterns for task-oriented MC-MR reconstruction. Comprehensive evaluations on two public benchmarks as well as an in-house dataset demonstrate that our <inline-formula> <tex-math notation="LaTeX">{A}^{{2}} </tex-math></inline-formula> MC-MRI led to state-of-the-art performance in MC-MRI reconstruction under high acceleration rates, featuring notable enhancements in TOI imaging quality. The code will be available at https://github.com/ladderlab-xjtu/A2MC-MRI