Three-Dimensional Diffusion-Weighted Multi-Slab MRI With Slice Profile Compensation Using Deep Energy Model

2025-01-28

AI Summary

In high-resolution 3D multislab diffusion MRI, intensity fluctuations and inter-slab aliasing artifacts at slab boundaries severely distort anatomical fidelity. To address this, we propose a reconstruction framework integrating Profile-Encoding Network (PEN) with Multi-Scale Energy (MuSE) regularization. For the first time, we embed a deep energy-based prior into a Plug-and-Play ADMM framework, enabling end-to-end slab fusion optimization. Our method effectively suppresses boundary artifacts while preserving fine structural details, significantly improving both signal-to-noise ratio (SNR) and structural similarity (SSIM). Quantitative evaluations and visual assessments demonstrate superior performance over non-regularized and total-variation (TV)-regularized PEN variants. The proposed approach exhibits enhanced robustness and reconstruction fidelity in high-resolution diffusion-weighted imaging, particularly under challenging acquisition conditions.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Content-based information diffusion
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Three-dimensional (3D) multi-slab acquisition is a technique frequently employed in high-resolution diffusion-weighted MRI in order to achieve the best signal-to-noise ratio (SNR) efficiency. However, this technique is limited by slab boundary artifacts that cause intensity fluctuations and aliasing between slabs which reduces the accuracy of anatomical imaging. Addressing this issue is crucial for advancing diffusion MRI quality and making high-resolution imaging more feasible for clinical and research applications. In this work, we propose a regularized slab profile encoding (PEN) method within a Plug-and-Play ADMM framework, incorporating multi-scale energy (MuSE) regularization to effectively improve the slab combined reconstruction. Experimental results demonstrate that the proposed method significantly improves image quality compared to non-regularized and TV-regularized PEN approaches. The regularized PEN framework provides a more robust and efficient solution for high-resolution 3D diffusion MRI, potentially enabling clearer, more reliable anatomical imaging across various applications.

Problem

• High-resolution Diffusion MRI
• 3D Multishell Acquisition
• Image Artifact

Innovation

• Regularized Layered Contour Coding
• Multi-scale Energy Regularization
• High-resolution Diffusion MRI Reconstruction