Polyhedra Encoding Transformers: Enhancing Diffusion MRI Analysis Beyond Voxel and Volumetric Embedding

2025-01-23

AI Summary

Existing deep learning methods for diffusion MRI (dMRI) spherical signal modeling underutilize directional priors and neglect the intrinsic spherical geometry. Method: We propose a spherical Transformer architecture based on icosahedral polyhedral encoding. Our approach introduces a novel structured resampling and embedding mechanism that maps gradient directions onto the unit sphere, explicitly incorporating spherical geometric symmetry into both positional encoding and self-attention design, while supporting multi-shell protocol adaptation during training. Contribution/Results: Evaluated on multi-compartment model parameter estimation and fiber orientation distribution (FOD) reconstruction, our method significantly outperforms CNNs and standard Transformers, achieving 12.7%–19.3% higher accuracy. It establishes a new paradigm for dMRI spherical signal modeling that jointly ensures geometric consistency and high representational capacity.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Learning with Manifolds
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Diffusion-weighted Magnetic Resonance Imaging (dMRI) is an essential tool in neuroimaging. It is arguably the sole noninvasive technique for examining the microstructural properties and structural connectivity of the brain. Recent years have seen the emergence of machine learning and data-driven approaches that enhance the speed, accuracy, and consistency of dMRI data analysis. However, traditional deep learning models often fell short, as they typically utilize pixel-level or volumetric patch-level embeddings similar to those used in structural MRI, and do not account for the unique distribution of various gradient encodings. In this paper, we propose a novel method called Polyhedra Encoding Transformer (PE-Transformer) for dMRI, designed specifically to handle spherical signals. Our approach involves projecting an icosahedral polygon onto a unit sphere to resample signals from predetermined directions. These resampled signals are then transformed into embeddings, which are processed by a transformer encoder that incorporates orientational information reflective of the icosahedral structure. Through experimental validation with various gradient encoding protocols, our method demonstrates superior accuracy in estimating multi-compartment models and Fiber Orientation Distributions (FOD), outperforming both conventional CNN architectures and standard transformers.

Problem

• Deep Learning
• Diffusion Weighted MRI
• Signal Distribution

Innovation

• Polyhedral Encoding Transformer
• Diffusion Weighted MRI
• Spherical Signal Processing