English

QID$^2$: An Image-Conditioned Diffusion Model for Q-space Up-sampling of DWI Data

Image and Video Processing 2024-09-05 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

We propose an image-conditioned diffusion model to estimate high angular resolution diffusion weighted imaging (DWI) from a low angular resolution acquisition. Our model, which we call QID2^2, takes as input a set of low angular resolution DWI data and uses this information to estimate the DWI data associated with a target gradient direction. We leverage a U-Net architecture with cross-attention to preserve the positional information of the reference images, further guiding the target image generation. We train and evaluate QID2^2 on single-shell DWI samples curated from the Human Connectome Project (HCP) dataset. Specifically, we sub-sample the HCP gradient directions to produce low angular resolution DWI data and train QID2^2 to reconstruct the missing high angular resolution samples. We compare QID2^2 with two state-of-the-art GAN models. Our results demonstrate that QID2^2 not only achieves higher-quality generated images, but it consistently outperforms the GAN models in downstream tensor estimation across multiple metrics. Taken together, this study highlights the potential of diffusion models, and QID2^2 in particular, for q-space up-sampling, thus offering a promising toolkit for clinical and research applications.

Keywords

Cite

@article{arxiv.2409.02309,
  title  = {QID$^2$: An Image-Conditioned Diffusion Model for Q-space Up-sampling of DWI Data},
  author = {Zijian Chen and Jueqi Wang and Archana Venkataraman},
  journal= {arXiv preprint arXiv:2409.02309},
  year   = {2024}
}

Comments

Accepted at MICCAI 2024 International Workshop on Computational Diffusion MRI. Zijian Chen and Jueqi Wang contributed equally to this work

R2 v1 2026-06-28T18:33:20.158Z