# Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE)

arXiv: https://arxiv.org/abs/2603.25977 · HTML: https://mlsanity.com/paper/2603.25977/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 69 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Space-time Mixing Attention for Video Transformer](https://mlsanity.com/paper/2106.05968/) (2021)
- [Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking](https://mlsanity.com/paper/2409.19407/) (2024)
- [VideoRoPE: What Makes for Good Video Rotary Position Embedding?](https://mlsanity.com/paper/2502.05173/) (2025)
- [TractSeg - Fast and accurate white matter tract segmentation](https://mlsanity.com/paper/1805.07103/) (2018)
- [A microstructure estimation Transformer inspired by sparse representation for diffusion MRI](https://mlsanity.com/paper/2205.06450/) (2022)
- [Anatomical Foundation Models for Brain MRIs](https://mlsanity.com/paper/2408.07079/) (2024)
- [Spatio-Angular Convolutions for Super-resolution in Diffusion MRI](https://mlsanity.com/paper/2306.00854/) (2023)
- [Diffusion Tensor Estimation with Transformer Neural Networks](https://mlsanity.com/paper/2201.05701/) (2022)
- [Reproducible evaluation of diffusion MRI features for automatic classification of patients with Alzheimers disease](https://mlsanity.com/paper/1812.11183/) (2018)
- [Predicting Age from White Matter Diffusivity with Residual Learning](https://mlsanity.com/paper/2311.03500/) (2023)
- [SamRobNODDI: Q-Space Sampling-Augmented Continuous Representation Learning for Robust and Generalized NODDI](https://mlsanity.com/paper/2411.06444/) (2024)
- [An Interpretable Representation Learning Approach for Diffusion Tensor Imaging](https://mlsanity.com/paper/2505.19110/) (2025)

## Abstract (arXiv)

Diffusion Magnetic Resonance Imaging (dMRI) plays a critical role in studying microstructural changes in the brain. It is, therefore, widely used in clinical practice; yet progress in learning general-purpose representations from dMRI has been limited. A key challenge is that existing deep learning approaches are not well-suited to capture the unique properties of diffusion signals. Brain dMRI is normally composed of several brain volumes, each with different attenuation characteristics dependent on the direction and strength of the diffusion-sensitized gradients. Thus, there is a need to jointly model spatial, diffusion-weighting, and directional dependencies in dMRI. Furthermore, varying acquisition protocols (e.g., differing numbers of directions) further limit traditional models. To address these gaps, we introduce a diffusion space rotatory positional embedding (D-RoPE) plugged into our dMRI transformer to capture both the spatial structure and directional characteristics of diffusion data, enabling robust and transferable representations across diverse acquisition settings and an arbitrary number of diffusion directions. After self-supervised masked autoencoding pretraining, tests on several downstream tasks show that the learned representations and the pretrained model can provide competitive or superior performance compared to several baselines in these downstream tasks (even compared to a fully trained baseline); the finetuned features from our pretrained encoder resulted in a 6% higher accuracy in classifying mild cognitive impairment and a 0.05 increase in the correlation coefficient when predicting cognitive scores. Code is available at: github.com/gustavochau/D-RoPE.