Q-space Guided Collaborative Attention Translation Network for Flexible Diffusion-Weighted Images Synthesis

TL;DR

This paper introduces Q-CATN, a novel neural network that synthesizes high-quality diffusion-weighted images from flexible q-space sampling, leveraging multi-modal data and task-specific constraints to improve accuracy and anatomical fidelity.

Contribution

Q-CATN is the first model to effectively handle flexible q-space sampling in DWI synthesis using collaborative attention and adaptive representations.

Findings

Q-CATN outperforms existing methods in parameter map estimation.

It accurately preserves anatomical details in synthesized images.

Demonstrates robustness across diverse q-space sampling schemes.

Abstract

This study, we propose a novel Q-space Guided Collaborative Attention Translation Networks (Q-CATN) for multi-shell, high-angular resolution DWI (MS-HARDI) synthesis from flexible q-space sampling, leveraging the commonly acquired structural MRI data. Q-CATN employs a collaborative attention mechanism to effectively extract complementary information from multiple modalities and dynamically adjust its internal representations based on flexible q-space information, eliminating the need for fixed sampling schemes. Additionally, we introduce a range of task-specific constraints to preserve anatomical fidelity in DWI, enabling Q-CATN to accurately learn the intrinsic relationships between directional DWI signal distributions and q-space. Extensive experiments on the Human Connectome Project (HCP) dataset demonstrate that Q-CATN outperforms existing methods, including 1D-qDL, 2D-qDL, MESC-SD, and QGAN, in estimating parameter maps and fiber tracts both quantitatively and qualitatively, while preserving fine-grained details. Notably, its ability to accommodate flexible q-space sampling highlights its potential as a promising toolkit for clinical and research applications. Our code is available at https://github.com/Idea89560041/Q-CATN.