Diffusion Coefficient

The diffusion coefficient quantifies the rate at which particles spread out in a medium, a crucial parameter in diverse fields from material science to medical imaging. Current research focuses on efficiently and accurately estimating diffusion coefficients, particularly in complex systems, using techniques like score-based diffusion models, Gaussian processes, and deep learning architectures such as convolutional neural networks and vision transformers. These advancements improve the accuracy and speed of diffusion coefficient mapping, leading to better characterization of materials and biological tissues, with applications ranging from improved medical diagnoses (e.g., glioma detection) to a more precise understanding of muscle microstructure.

Papers

November 4, 2024

Learning Controlled Stochastic Differential Equations
Luc Brogat-Motte, Riccardo Bonalli, Alessandro Rudi
Nonlinear Dynamic Stochastic Differential Equation Fokker Planck Equation Diffusion Coefficient

October 4, 2024

A Training-Free Conditional Diffusion Model for Learning Stochastic Dynamical Systems
Yanfang Liu, Yuan Chen, Dongbin Xiu, Guannan Zhang
Dynamical System Conditional Diffusion Model Score Based Diffusion Model Stochastic Dynamical System Diffusion Coefficient

July 2, 2024

Deep Learning Based Apparent Diffusion Coefficient Map Generation from Multi-parametric MR Images for Patients with Diffuse Gliomas
Zach Eidex, Mojtaba Safari, Jacob Wynne, Richard L. J. Qiu, Tonghe Wang, David Viar Hernandez, Hui-Kuo Shu, Hui Mao, Xiaofeng Yang
Deep Learning Magnetic Resonance Imaging Patient Friendly Language ViT Model Diffuse Glioma Residual Transformer Diffusion Coefficient

June 19, 2023

Accelerated, physics-inspired inference of skeletal muscle microstructure from diffusion-weighted MRI
Noel Naughton, Stacey Cahoon, Brad Sutton, John G. Georgiadis
Physic Informed Diffusion Based Low Rate ACCELERATION Microstructure Model Diffusion Weighted MRI Diffusion Coefficient

May 24, 2023

Non-Parametric Learning of Stochastic Differential Equations with Non-asymptotic Fast Rates of Convergence
Riccardo Bonalli, Alessandro Rudi
Early Stage Convergence Learning Rate Stochastic Differential Equation Non Asymptotic Fokker Planck Equation Non Parametric Learning Diffusion Coefficient

October 6, 2022

Deep Learning Mixture-of-Experts Approach for Cytotoxic Edema Assessment in Infants and Children
Henok Ghebrechristos, Stence Nicholas, David Mirsky, Gita Alaghband, Manh Huynh, Zackary Kromer, Ligia Batista, Brent ONeill, Steven Moulton, Daniel M. Lindberg
Deep Learning Constructive Approach Deep Learning Framework Nine Year Old Child Magnetic Resonance Imaging Data Diffusion Weighted Young Infant Diffusion Coefficient Perihematomal Edema

July 6, 2022

Learning Apparent Diffusion Coefficient Maps from Accelerated Radial k-Space Diffusion-Weighted MRI in Mice using a Deep CNN-Transformer Model
Yuemeng Li, Miguel Romanello Joaquim, Stephen Pickup, Hee Kwon Song, Rong Zhou, Yong Fan
K Space CNN Transformer Mouse Data Diffusion Weighted MRI Diffusion Coefficient

Diffusion Coefficient

Papers

Learning Controlled Stochastic Differential Equations

A Training-Free Conditional Diffusion Model for Learning Stochastic Dynamical Systems

Deep Learning Based Apparent Diffusion Coefficient Map Generation from Multi-parametric MR Images for Patients with Diffuse Gliomas

Accelerated, physics-inspired inference of skeletal muscle microstructure from diffusion-weighted MRI

Non-Parametric Learning of Stochastic Differential Equations with Non-asymptotic Fast Rates of Convergence

Deep Learning Mixture-of-Experts Approach for Cytotoxic Edema Assessment in Infants and Children

Learning Apparent Diffusion Coefficient Maps from Accelerated Radial k-Space Diffusion-Weighted MRI in Mice using a Deep CNN-Transformer Model