Journal
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Volume 84, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.bspc.2023.104821
Keywords
Deep learning; CS-MRI reconstruction; Unfolding explainable network; Two-grid-cycle correction; Geometric prior distillation; Multi-sampling-ratio reconstruction
Categories
Ask authors/readers for more resources
In this study, a unified and interpretable deep unfolding multi-sampling-ratio CS-MRI framework is proposed to address the challenges of explainability and generalizability in existing CS-MRI methods. The model not only compensates for lost contextual information but also combines the theoretical guarantee of model-based methods and the superior reconstruction performance of deep learning-based methods.
Although existing deep learning compressed-sensing-based Magnetic Resonance Imaging (CS-MRI) methods have achieved considerably impressive performance, explainability and generalizability continue to be challenging for such methods since the transition from mathematical analysis to network design not always natural enough, often most of them are not flexible enough to handle multi-sampling-ratio reconstruction assignments. In this work, to tackle explainability and generalizability, we propose a unifying deep unfolding multi-sampling-ratio interpretable CS-MRI framework. The combined approach offers more generalizability than previous works whereas deep learning gains explainability through a geometric prior module. Inspired by the multigrid algorithm, we first embed the CS-MRI-based optimization algorithm into correction-distillation scheme that consists of three ingredients: pre-relaxation module, correction module and geometric prior distillation module. Furthermore, we employ a condition module to learn adaptively step-length and noise level, which enables the proposed framework to jointly train multi-ratio tasks through a single model. The proposed model not only compensates for the lost contextual information of reconstructed image which is refined from low frequency error in geometric characteristic k-space, but also integrates the theoretical guarantee of model-based methods and the superior reconstruction performances of deep learning-based methods. Therefore, it can give us a novel perspective to design biomedical imaging networks. Numerical experiments show that our framework outperforms state-of-the-art methods in terms of qualitative and quantitative evaluations. Our method achieves 3.18 dB improvement at low CS ratio 10% and average 1.42 dB improvement over other comparison methods on brain dataset using Cartesian sampling mask.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available