# Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI

arXiv: https://arxiv.org/abs/2106.13188 · HTML: https://mlsanity.com/paper/2106.13188/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 24 Jun 2021.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [cGANs with Projection Discriminator](https://mlsanity.com/paper/1802.05637/) (2018)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [Understanding SSIM](https://mlsanity.com/paper/2006.13846/) (2020)
- [Segmentation-Renormalized Deep Feature Modulation for Unpaired Image Harmonization](https://mlsanity.com/paper/2102.06315/) (2021)
- [Generating Diffusion MRI scalar maps from T1 weighted images using generative adversarial networks](https://mlsanity.com/paper/1810.02683/) (2018)
- [INSIDE: Steering Spatial Attention with Non-Imaging Information in CNNs](https://mlsanity.com/paper/2008.10418/) (2020)
- [Manifold-Aware CycleGAN for High-Resolution Structural-to-DTI Synthesis](https://mlsanity.com/paper/2004.00173/) (2020)

## Built on by (most cited first, 11 of 11)

- [Spatio-Angular Convolutions for Super-resolution in Diffusion MRI](https://mlsanity.com/paper/2306.00854/) (2023)
- [Diffusion MRI with Machine Learning](https://mlsanity.com/paper/2402.00019/) (2024)
- [Phy-Diff: Physics-guided Hourglass Diffusion Model for Diffusion MRI Synthesis](https://mlsanity.com/paper/2406.03002/) (2024)
- [QID2: An Image-Conditioned Diffusion Model for Q-space Up-sampling of DWI Data](https://mlsanity.com/paper/2409.02309/) (2024)
- [Identity Preserving Latent Diffusion for Brain Aging Modeling](https://mlsanity.com/paper/2503.09634/) (2025)
- [Q-space Guided Collaborative Attention Translation Network for Flexible Diffusion-Weighted Images Synthesis](https://mlsanity.com/paper/2505.09323/) (2025)
- [Physics-Guided Diffusion Transformer with Spherical Harmonic Posterior Sampling for High-Fidelity Angular Super-Resolution in Diffusion MRI](https://mlsanity.com/paper/2509.07020/) (2025)
- [Eddeep: a deep-learning framework for fast eddy-current distortion correction in diffusion MRI](https://mlsanity.com/paper/2607.26292/) (2026)
- [Pattern-Aware Diffusion Synthesis of fMRI/dMRI with Tissue and Microstructural Refinement](https://mlsanity.com/paper/2511.04963/) (2025)
- [Layer Selection in Feature-Based Losses Affects Image Quality and Microstructural Consistency in Deep Learning Super-Resolution of Brain Diffusion MRI](https://mlsanity.com/paper/2605.15895/) (2026)
- [dMRI-F: A Foundation Model for Generalizable Diffusion MRI Analysis from Sparse Acquisitions](https://mlsanity.com/paper/2610.17968/) (2026)

## Abstract (arXiv)

Current deep learning approaches for diffusion MRI modeling circumvent the need for densely-sampled diffusion-weighted images (DWIs) by directly predicting microstructural indices from sparsely-sampled DWIs. However, they implicitly make unrealistic assumptions of static q-space sampling during training and reconstruction. Further, such approaches can restrict downstream usage of variably sampled DWIs for usages including the estimation of microstructural indices or tractography. We propose a generative adversarial translation framework for high-quality DWI synthesis with arbitrary q-space sampling given commonly acquired structural images (e.g., B0, T1, T2). Our translation network linearly modulates its internal representations conditioned on continuous q-space information, thus removing the need for fixed sampling schemes. Moreover, this approach enables downstream estimation of high-quality microstructural maps from arbitrarily subsampled DWIs, which may be particularly important in cases with sparsely sampled DWIs. Across several recent methodologies, the proposed approach yields improved DWI synthesis accuracy and fidelity with enhanced downstream utility as quantified by the accuracy of scalar microstructure indices estimated from the synthesized images. Code is available at https://github.com/mengweiren/q-space-conditioned-dwi-synthesis.