Saved in:
Bibliographic Details
Main Authors: Chen, Zijian, Wang, Jueqi, Venkataraman, Archana
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.02309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929485045039104
author Chen, Zijian
Wang, Jueqi
Venkataraman, Archana
author_facet Chen, Zijian
Wang, Jueqi
Venkataraman, Archana
contents 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 QID$^2$, 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 QID$^2$ 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 QID$^2$ to reconstruct the missing high angular resolution samples. We compare QID$^2$ with two state-of-the-art GAN models. Our results demonstrate that QID$^2$ 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 QID$^2$ in particular, for q-space up-sampling, thus offering a promising toolkit for clinical and research applications.
format Preprint
id arxiv_https___arxiv_org_abs_2409_02309
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle QID$^2$: An Image-Conditioned Diffusion Model for Q-space Up-sampling of DWI Data
Chen, Zijian
Wang, Jueqi
Venkataraman, Archana
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
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 QID$^2$, 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 QID$^2$ 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 QID$^2$ to reconstruct the missing high angular resolution samples. We compare QID$^2$ with two state-of-the-art GAN models. Our results demonstrate that QID$^2$ 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 QID$^2$ in particular, for q-space up-sampling, thus offering a promising toolkit for clinical and research applications.
title QID$^2$: An Image-Conditioned Diffusion Model for Q-space Up-sampling of DWI Data
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2409.02309