mlsanityData to 7 Oct 2026

QID2: An Image-Conditioned Diffusion Model for Q-space Up-sampling of DWI Data

arXiv 2409.02309 ↗First posted 3 Sep 2024eess.IV cs.CV cs.LGcited by 1

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

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, 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 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 to reconstruct the missing high angular resolution samples. We compare QID2 with two state-of-the-art GAN models. Our results demonstrate that QID2 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 in particular, for q-space up-sampling, thus offering a promising toolkit for clinical and research applications.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 24 of its 39 references that are in the map. First posted on arXiv 3 Sep 2024.

Builds on

24 of 39 references.

Closest ancestors · 13

Same direction, newest first

  1. 2023InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model23 Aug
  2. 2023Ambiguous Medical Image Segmentation using Diffusion Models10 Apr
  3. 2023Zero-shot Medical Image Translation via Frequency-Guided Diffusion Models5 Apr
  4. 2023Memory-Efficient 3D Denoising Diffusion Models for Medical Image Processing27 Mar
  5. 2023Diffusion Models for Contrast Harmonization of Magnetic Resonance Images14 Mar
  6. 2023DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models6 Feb
  7. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Survey14 Nov
  8. 2022Brain Imaging Generation with Latent Diffusion Models15 Sep
  9. 2022A Diffusion Model Predicts 3D Shapes from 2D Microscopy Images30 Aug
  10. 2022A Novel Unified Conditional Score-based Generative Framework for Multi-modal Medical Image Completion7 Jul
  11. 2021DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model9 Dec
  12. 2021Diffusion Models for Implicit Image Segmentation Ensembles6 Dec
1 more
  1. 2021Score-based diffusion models for accelerated MRI8 Oct

Other references · 11

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  7. 2020A U-Net Based Discriminator for Generative Adversarial Networkscited by 128
  8. 2022Conversion Between CT and MRI Images Using Diffusion and Score-Matching Modelscited by 69
  9. 2023A Unified Framework for U-Net Design and Analysiscited by 27
  10. 2021Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRIcited by 10
  11. 2017Single- and Multiple-Shell Uniform Sampling Schemes for Diffusion MRI Using Spherical Codescited by 8

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Physics-Guided Diffusion Transformer with Spherical Harmonic Posterior Sampling for High-Fidelity Angular Super-Resolution in Diffusion MRIcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2020Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning
  2. 2022Physics-informed Deep Diffusion MRI Reconstruction with Synthetic Data: Break Training Data Bottleneck in Artificial Intelligence
  3. 2026TensorLDM: A Component-Wise Latent Diffusion Model for Volumetric DTI Reconstruction from Sparse DWIs
  4. 2025Benchmarking GANs, Diffusion Models, and Flow Matching for T1w-to-T2w MRI Translation
  5. 2021Cascaded Diffusion Models for High Fidelity Image Generation
  6. 2024Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion
  7. 2024Phy-Diff: Physics-guided Hourglass Diffusion Model for Diffusion MRI Synthesis
  8. 2022Unsupervised Medical Image Translation with Adversarial Diffusion Models