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

• URL: http://arxiv.org/abs/2603.25977v1
• Date: Thu, 26 Mar 2026 23:39:52 GMT
• Title: Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE)
• Abstract summary: We introduce a diffusion space rotatory positional embedding (DRoPE) plugged into our dMRI transformer to capture both the spatial structure and directional characteristics of diffusion data.<n>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.
• Score: 11.718317717365373
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• HARP: HARmonizing in-vivo diffusion MRI using Phantom-only training [5.326951221819057]
  This study aims to develop a deep learning-based dMRI harmonization framework.<n>Harp employs a voxel-wise 1D neural network trained on an easily transportable diffusion phantom.
  arXiv  Detail & Related papers  (2026-03-05T01:38:41Z)
• Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations [57.054499278843856]
  Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies.<n>Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs.<n>We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured fMRI data.
  arXiv  Detail & Related papers  (2025-10-05T12:35:01Z)
• A Steerable Deep Network for Model-Free Diffusion MRI Registration [4.813333335683418]
  We present a novel, deep learning framework for model-free, nonrigid registration of raw diffusion MRI data.<n>This work establishes a foundation for data-driven, geometry-aware dMRI registration directly in the acquisition space.
  arXiv  Detail & Related papers  (2025-01-08T19:18:44Z)
• MindFormer: Semantic Alignment of Multi-Subject fMRI for Brain Decoding [50.55024115943266]
  We introduce a novel semantic alignment method of multi-subject fMRI signals using so-called MindFormer. This model is specifically designed to generate fMRI-conditioned feature vectors that can be used for conditioning Stable Diffusion model for fMRI- to-image generation or large language model (LLM) for fMRI-to-text generation. Our experimental results demonstrate that MindFormer generates semantically consistent images and text across different subjects.
  arXiv  Detail & Related papers  (2024-05-28T00:36:25Z)
• NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation [55.51412454263856]
  This paper proposes to directly modulate the generation process of diffusion models using fMRI signals. By training with about 67,000 fMRI-image pairs from various individuals, our model enjoys superior fMRI-to-image decoding capacity.
  arXiv  Detail & Related papers  (2024-03-27T02:42:52Z)
• Source-Free Collaborative Domain Adaptation via Multi-Perspective Feature Enrichment for Functional MRI Analysis [55.03872260158717]
  Resting-state MRI functional (rs-fMRI) is increasingly employed in multi-site research to aid neurological disorder analysis. Many methods have been proposed to reduce fMRI heterogeneity between source and target domains. But acquiring source data is challenging due to concerns and/or data storage burdens in multi-site studies. We design a source-free collaborative domain adaptation framework for fMRI analysis, where only a pretrained source model and unlabeled target data are accessible.
  arXiv  Detail & Related papers  (2023-08-24T01:30:18Z)
• DreaMR: Diffusion-driven Counterfactual Explanation for Functional MRI [0.0]
  We introduce the first diffusion-driven counterfactual method, DreaMR, to enable fMRI interpretation with high specificity, plausibility and fidelity. DreaMR performs diffusion-based resampling of an input fMRI sample to alter the decision of a downstream classifier, and then computes the minimal difference between the original and counterfactual samples for explanation. Comprehensive experiments on neuroimaging datasets demonstrate the superior specificity, fidelity and efficiency of DreaMR in sample generation over state-of-the-art counterfactual methods for fMRI interpretation.
  arXiv  Detail & Related papers  (2023-07-18T18:46:07Z)
• Robust Fiber Orientation Distribution Function Estimation Using Deep Constrained Spherical Deconvolution for Diffusion MRI [9.570365838548073]
  A common practice to model the measured DW-MRI signal is via fiber orientation distribution function (fODF)<n> measurement variabilities (e.g., inter- and intra-site variability, hardware performance, and sequence design) are inevitable during the acquisition of DW-MRI.<n>Most existing model-based methods (e.g., constrained spherical deconvolution (CSD)) and learning based methods (e.g., deep learning (DL)) do not explicitly consider such variabilities in fODF modeling.<n>We propose a novel data-driven deep constrained spherical deconvolution method to
  arXiv  Detail & Related papers  (2023-06-05T14:06:40Z)
• Learning shared neural manifolds from multi-subject FMRI data [13.093635609349874]
  We propose a neural network called MRMD-AEmani that learns a common embedding from multiple subjects in an experiment. We show that our learned common space represents antemporal manifold (where new points not seen during training can be mapped), improves the classification of stimulus features of unseen timepoints. We believe this framework can be used for many downstream applications such as guided brain-computer interface (BCI) training in the future.
  arXiv  Detail & Related papers  (2021-12-22T23:08:39Z)
• Rotation-Equivariant Deep Learning for Diffusion MRI [49.321304988619865]
  Convolutional networks are successful, but they have recently been outperformed by new neural networks that are equivariant under rotations and translations. Here we generalize them to 6D diffusion MRI data, ensuring joint equivariance under 3D roto-translations in image space and the matching 3D rotations in $q$-space. Our proposed neural networks yield better results and require fewer scans for training compared to non-rotation-equivariant deep learning.
  arXiv  Detail & Related papers  (2021-02-13T15:18:34Z)
• Multifold Acceleration of Diffusion MRI via Slice-Interleaved Diffusion Encoding (SIDE) [50.65891535040752]
  We propose a diffusion encoding scheme, called Slice-Interleaved Diffusion. SIDE, that interleaves each diffusion-weighted (DW) image volume with slices encoded with different diffusion gradients. We also present a method based on deep learning for effective reconstruction of DW images from the highly slice-undersampled data.
  arXiv  Detail & Related papers  (2020-02-25T14:48:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.