Nonlinear inversion model-driven deep learning method for magnetic resonance imaging (MRI) quantitative susceptibility mapping imaging

基于非线性反演模型的深度学习方法用于磁共振成像(MRI)定量磁化率映射成像

阅读:1

Abstract

BACKGROUND: Quantitative susceptibility mapping (QSM) has great advantages in evaluating tissue susceptibility across diverse cerebral conditions. However, conventional reconstruction methods are often affected by streaking artifacts and noise amplification, while purely data-driven deep learning approaches frequently lack physical constraints, resulting in deviations from the underlying dipole physics. To address these issues, we aimed to develop a model-driven deep learning approach that explicitly enforces dipole model data fidelity within the network, aiming to enhance quantitative accuracy and suppress artifacts. METHODS: We propose a nonlinear susceptibility inversion deep learning model (NSIDL), which integrates a nonlinear susceptibility inversion (NSI) model into a convolutional neural network and employs the proximal gradient descent (PGD) method to solve the optimization problem. The method was trained and validated using a multi-orientation gradient echo magnetic resonance imaging (MRI) dataset. Quantitative performance of NSIDL was evaluated using the reconstruction challenge (RC-1 and RC-2) datasets and in vivo data, and compared with state-of-the-art iterative methods and deep learning approaches. Clinical feasibility was assessed in patients with hemorrhage, calcification, and multiple sclerosis (MS). RESULTS: The quantitative evaluation results showed that NSIDL achieved the highest quantitative accuracy on multi-orientation test datasets, with a fitted slope of 0.716 and an R(2) of 0.6140, significantly outperforming other competing methods (slope range, 0.511-0.676; R(2) range, 0.3677-0.5714). On the RC-1 dataset, NSIDL demonstrated superior image fidelity, exhibiting the lowest normalized root mean square error (NRMSE) (63.267±0.575) and high-frequency error norm (HFEN) (58.300±0.668), and the highest peak signal-to-noise ratio (PSNR) (42.39±0.311), consistently outperforming other methods across all three metrics (P<0.05). Analysis of deep gray matter regions of interest confirmed that NSIDL estimates most closely matched the susceptibility labels. Clinical evaluation indicated that, compared with baseline reconstructions, NSIDL effectively suppressed artifacts in hemorrhagic lesions and enhanced the clarity of small MS lesions. CONCLUSIONS: By combining a nonlinear physical model with data-driven regularization, NSIDL substantially improves quantitative susceptibility estimation and image quality. This method demonstrates robust artifact suppression and high-fidelity measurements, showing great potential for precise clinical QSM applications.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。