Physics-Assisted Deep Learning Denoising for Stabilized IMPULSED dMRI Microenvironment Parameter Fitting
Abstract
Diffusion-weighted MRI (dMRI) is a powerful tool for quantifying cellular microenvironment parameters. This study proposes a physics-assisted deep learning (DL)-based denoising framework designed to enhance dMRI signal quality and improve the robustness of subsequent biophysical model fitting. A dataset of paired noise-free and Rician-noise-corrupted dMRI signals was generated using the IMPULSED-dMRI signal model. Three denoising architectures were evaluated: Convolutional Neural Networks (CNN), Multilayer Perceptron (MLP), and Long Short-Term Memory (LSTM) networks. Denoised signals were then fitted to estimate cell diameter d, intracellular volume fraction Vin, and extracellular apparent diffusion coefficient Dex. DL-based processing substantially improved dMRI signal denoising. The MLP and LSTM achieved similar performance, with the LSTM slightly better overall, and both outperformed the CNN. In the subsequent model fitting step, the LSTM produced modest reductions in parameter MAE. The dominant benefit was fitting stabilization, with the overall fitting failure rate reduced from 57.6\% to 17.7\%. The proposed framework improves dMRI signal quality and stabilizes subsequent IMPULSED-based microenvironmental parameter fitting.
Related
- Library-learning-assisted robust principal component analysis for denoising severely corrupted flow fields
- Survey of Novel Deep Learning Architectures for Denoising Gravitational-wave Signals
- Toward fully stabilized flow control using deep reinforcement learning
- Machine Learning Guided CALPHAD Design of Ru-Stabilized BCC B2 Refractory Alloys
- Quantum Sensing and Hamiltonian Learning under Stochastic Parameter Evolution
BibTeX
@misc{li2026physicsassisted,
title = {{Physics-Assisted Deep Learning Denoising for Stabilized IMPULSED dMRI Microenvironment Parameter Fitting}},
author = {Wen Li and Yan Dai and Arely Perez Rodriguez and Todd Aguilera and Jie Deng and Xun Jia},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.27681},
eprint = {2608.27681},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.27681},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Physics-Assisted Deep Learning Denoising for Stabilized IMPULSED dMRI Microenvironment Parameter Fitting
AU - Wen Li
AU - Yan Dai
AU - Arely Perez Rodriguez
AU - Todd Aguilera
AU - Jie Deng
AU - Xun Jia
PY - 2026
DA - 2026/08/27
PB - arXiv
DO - 10.48550/arxiv.2608.27681
UR - https://arxiv.org/abs/2608.27681
AB - Diffusion-weighted MRI (dMRI) is a powerful tool for quantifying cellular microenvironment parameters. This study proposes a physics-assisted deep learning (DL)-based denoising framework designed to enhance dMRI signal quality and improve the robustness of subsequent biophysical model fitting. A dataset of paired noise-free and Rician-noise-corrupted dMRI signals was generated using the IMPULSED-dMRI signal model. Three denoising architectures were evaluated: Convolutional Neural Networks (CNN), Multilayer Perceptron (MLP), and Long Short-Term Memory (LSTM) networks. Denoised signals were then fitted to estimate cell diameter d, intracellular volume fraction V_in, and extracellular apparent diffusion coefficient D_ex. DL-based processing substantially improved dMRI signal denoising. The MLP and LSTM achieved similar performance, with the LSTM slightly better overall, and both outperformed the CNN. In the subsequent model fitting step, the LSTM produced modest reductions in parameter MAE. The dominant benefit was fitting stabilization, with the overall fitting failure rate reduced from 57.6\% to 17.7\%. The proposed framework improves dMRI signal quality and stabilizes subsequent IMPULSED-based microenvironmental parameter fitting.
ER -