Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enhancing Angular Resolution via Directionality Encoding and Geometric Constraints in Brain Diffusion Tensor Imaging

Sheng Chen, Zihao Tang, Mariano Cabezas, Xinyi Wang, Arkiev D'Souza, Michael Barnett, Fernando Calamante, Weidong Cai, Chenyu Wang

TL;DR

DirGeo-DTI is proposed, a deep learning-based method to estimate reliable DTI metrics even from a set of DWIs acquired with the minimum theoretical number of gradient directions, which leverages directional encoding and geometric constraints to facilitate the training process.

Abstract

Diffusion-weighted imaging (DWI) is a type of Magnetic Resonance Imaging (MRI) technique sensitised to the diffusivity of water molecules, offering the capability to inspect tissue microstructures and is the only in-vivo method to reconstruct white matter fiber tracts non-invasively. The DWI signal can be analysed with the diffusion tensor imaging (DTI) model to estimate the directionality of water diffusion within voxels. Several scalar metrics, including axial diffusivity (AD), mean diffusivity (MD), radial diffusivity (RD), and fractional anisotropy (FA), can be further derived from DTI to quantitatively summarise the microstructural integrity of brain tissue. These scalar metrics have played an important role in understanding the organisation and health of brain tissue at a microscopic level in clinical studies. However, reliable DTI metrics rely on DWI acquisitions with high gradient directions, which often go beyond the commonly used clinical protocols. To enhance the utility of clinically acquired DWI and save scanning time for robust DTI analysis, this work proposes DirGeo-DTI, a deep learning-based method to estimate reliable DTI metrics even from a set of DWIs acquired with the minimum theoretical number (6) of gradient directions. DirGeo-DTI leverages directional encoding and geometric constraints to facilitate the training process. Two public DWI datasets were used for evaluation, demonstrating the effectiveness of the proposed method. Extensive experimental results show that the proposed method achieves the best performance compared to existing DTI enhancement methods and potentially reveals further clinical insights with routine clinical DWI scans.

Enhancing Angular Resolution via Directionality Encoding and Geometric Constraints in Brain Diffusion Tensor Imaging

TL;DR

DirGeo-DTI is proposed, a deep learning-based method to estimate reliable DTI metrics even from a set of DWIs acquired with the minimum theoretical number of gradient directions, which leverages directional encoding and geometric constraints to facilitate the training process.

Abstract

Diffusion-weighted imaging (DWI) is a type of Magnetic Resonance Imaging (MRI) technique sensitised to the diffusivity of water molecules, offering the capability to inspect tissue microstructures and is the only in-vivo method to reconstruct white matter fiber tracts non-invasively. The DWI signal can be analysed with the diffusion tensor imaging (DTI) model to estimate the directionality of water diffusion within voxels. Several scalar metrics, including axial diffusivity (AD), mean diffusivity (MD), radial diffusivity (RD), and fractional anisotropy (FA), can be further derived from DTI to quantitatively summarise the microstructural integrity of brain tissue. These scalar metrics have played an important role in understanding the organisation and health of brain tissue at a microscopic level in clinical studies. However, reliable DTI metrics rely on DWI acquisitions with high gradient directions, which often go beyond the commonly used clinical protocols. To enhance the utility of clinically acquired DWI and save scanning time for robust DTI analysis, this work proposes DirGeo-DTI, a deep learning-based method to estimate reliable DTI metrics even from a set of DWIs acquired with the minimum theoretical number (6) of gradient directions. DirGeo-DTI leverages directional encoding and geometric constraints to facilitate the training process. Two public DWI datasets were used for evaluation, demonstrating the effectiveness of the proposed method. Extensive experimental results show that the proposed method achieves the best performance compared to existing DTI enhancement methods and potentially reveals further clinical insights with routine clinical DWI scans.
Paper Structure (17 sections, 16 equations, 5 figures, 2 tables)

This paper contains 17 sections, 16 equations, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Related Works
  4. Datasets
  5. Data Preparation
  6. DirGeo-DTI
  7. Directionality Encoding
  8. Geometric Learning
  9. Stress Invariants
  10. Relative Diffusivity
  11. Geometry-constrained Loss
  12. Implementation Details
  13. Experimental Results
  14. Tensor Evaluation
  15. WM Tracts Analysis
  16. ...and 2 more sections

Figures (5)

  • Figure 1: The preprocessing pipeline of raw diffusion and T1 images. Image preprocessing including denoising, unring, and corrections of bias field, motion, and distortion were performed using MRtrix3 tournier2019mrtrix3. Tissue and WM tract segmentation were conducted with fischl2012freesurfer and wasserthal2018tractseg, respectively.
  • Figure 2: Detailed framework of the proposed DirGeo-DTI.
  • Figure 3: Axial visualisations of DTI tensors by different approaches: (a) 6-dir DTI, (b) ground truth, enhanced DTI by (c) DeepDTI, (d) HADTI-Net, and the proposed (e) DirGeo-DTI using the same set of inputs ($b_0$ + 6dir DWIs) for a testing subject in the HCP and PPMI dataset. The first and second rows represent results from the HCP and PPMI, respectively.
  • Figure 4: Mean absolute FA differences for 6-dir DTI and enhanced DTI by different methods in specific WM tracts of PPMI testing subjects. * denotes no statistically significant difference from the ground truth with $p$-value $>$ 0.05.
  • Figure 5: Mean absolute FA differences for 6-dir DTI and enhanced DTI by different methods in specific WM tracts of HCP testing subjects. * denotes no statistically significant difference from the ground truth with $p$-value $>$ 0.05.