A Deep Nonlinear Subspace Modeling and Reconstruction for Diffusion‐Weighted Imaging Using Denoising Auto‐Encoder
Open Access
- 4 August 2026
- journal article
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 96 (5) , 2359-2369
Abstract
Purpose: To present a novel, nonlinear subspace modeling and joint k–q‐space reconstruction technique for high‐resolution, multi‐band, multi‐shell diffusion‐weighted imaging (DWI). Methods: High b ‐value (> 1000 s/mm 2 ), high resolution DWI has the drawback of generally low signal‐to‐noise ratios (SNRs). We present an approach that leverages a denoising autoencoder (DAE) to learn a latent subspace from biophysically simulated diffusion‐weighted signals. The decoder of this network is then used in the forward operator of the image reconstruction process. The decoded latent images are scaled by the image, phase is added and processed as regular DWI images with the forward operator for multi‐shot, multicoil, multi‐slice, k–q‐undersampled acquisition schemes. The performance is investigated with a multi‐shell, multi‐direction imaging brain scan and compared to the results of the multiplexed sensitivity‐encoding (MUSE) reconstruction and locally low‐rank (LLR) regularized reconstruction. The results are further validated by a bias and precision analysis of reconstructed fiber directions. Results: Comparing the reconstructed data using the proposed method shows improved noise suppression compared to MUSE and more details than LLR‐reconstructed images. Specifically, in the higher b ‐value domain, the reconstruction results show improved detectability of small structures. This bias and precision analysis showed minimal bias introduction, but higher precision with the proposed method. Conclusion: Our method combines deep learning, latent signal modeling, joint k–q‐space reconstruction, and biophysical simulation for diffusion data and shows strong noise suppression and a high degree of detail in reconstructed diffusion‐weighted images.Keywords
Funding Information
- Friedrich-Alexander-Universität Erlangen-Nürnberg (b143dc)
- Deutsche Forschungsgemeinschaft (440719683)
- Deutsche Forschungsgemeinschaft (500888779)
- Deutsche Forschungsgemeinschaft (512819079)
- Deutsche Forschungsgemeinschaft (513220538)
This publication has 41 references indexed in Scilit:
- Diffusional kurtosis imaging: The quantification of non‐gaussian water diffusion by means of magnetic resonance imagingMagnetic Resonance in Medicine, 2005
- Determining and visualizing uncertainty in estimates of fiber orientation from diffusion tensor MRIMagnetic Resonance in Medicine, 2002
- Reduction of eddy‐current‐induced distortion in diffusion MRI using a twice‐refocused spin echoMagnetic Resonance in Medicine, 2002
- Generalized autocalibrating partially parallel acquisitions (GRAPPA)Magnetic Resonance in Medicine, 2002
- Statistical artifacts in diffusion tensor MRI (DT-MRI) caused by background noiseMagnetic Resonance in Medicine, 2000
- SENSE: Sensitivity encoding for fast MRIMagnetic Resonance in Medicine, 1999
- Characterization of and correction for eddy current artifacts in echo planar diffusion imagingMagnetic Resonance in Medicine, 1998
- Interleaved echo planar imaging on a standard MRI systemMagnetic Resonance in Medicine, 1994
- Fast imaging using subencoding data sets from multiple detectorsMagnetic Resonance in Medicine, 1993
- The NMR phased arrayMagnetic Resonance in Medicine, 1990