Fiber-Resolved Microstructure Quantification from Multi-Shell Diffusion MRI using Detection Transformers
Abstract
Fiber orientation and compartmental microstructure are central to the characterization of white matter tissue in diffusion MRI, yet existing methods either resolve fiber orientations without quantifying microstructure, or quantify microstructure while assuming a fixed number of compartments and a single fiber direction. Nonparametric approaches that recover both require tensor-valued diffusion encoding and computationally expensive Monte-Carlo inversion of an ill-posed inverse Laplace transform. We propose to reframe this problem as an object detection-like task, adopting the Detection Transformer (DETR) architecture to jointly predict mean diffusivity (MD), fractional anisotropy (FA), main fiber direction, and signal fraction for a variable number of compartments per voxel from standard multi-shell diffusion MRI with linear encoding. Hungarian matching during training resolves permutation invariance across compartments. We introduce mean Average Precision as a reproducible benchmark metric. Evaluated on synthetic test data with up to five compartments per voxel, our model achieves R2=0.95 for MD, R2=0.88 for FA, and a median angular error of 4.2°, with performance scaling naturally with compartmental signal fraction.
Related
- Detection Instead of Inversion: T1-T2 Microstructure Quantification With Detection Transformers
- Microstructure-Resolved Impedance Modeling of Solid-State Batteries
- Imaging cellular-level brain microstructure with diffusion MRI
- Effect of Al-Zn alloy wafer grain boundary diffusion on the magnetism and microstructure of sintered NdFeB magnets
- Transformers with Physics-Informed Encodings and Simulation-Based Inference for Robust Detection of Eccentric Binary Black Holes in Pulsar Timing Array Data
BibTeX
@misc{endt2026fiberresolved,
title = {{Fiber-Resolved Microstructure Quantification from Multi-Shell Diffusion MRI using Detection Transformers}},
author = {Sebastian Endt and Marcus Wirth and Johannes Reinhold Schlund and Marion Irene Menzel},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.39184},
eprint = {2609.39184},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.39184},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Fiber-Resolved Microstructure Quantification from Multi-Shell Diffusion MRI using Detection Transformers
AU - Sebastian Endt
AU - Marcus Wirth
AU - Johannes Reinhold Schlund
AU - Marion Irene Menzel
PY - 2026
DA - 2026/09/30
PB - arXiv
DO - 10.48550/arxiv.2609.39184
UR - https://arxiv.org/abs/2609.39184
AB - Fiber orientation and compartmental microstructure are central to the characterization of white matter tissue in diffusion MRI, yet existing methods either resolve fiber orientations without quantifying microstructure, or quantify microstructure while assuming a fixed number of compartments and a single fiber direction. Nonparametric approaches that recover both require tensor-valued diffusion encoding and computationally expensive Monte-Carlo inversion of an ill-posed inverse Laplace transform. We propose to reframe this problem as an object detection-like task, adopting the Detection Transformer (DETR) architecture to jointly predict mean diffusivity (MD), fractional anisotropy (FA), main fiber direction, and signal fraction for a variable number of compartments per voxel from standard multi-shell diffusion MRI with linear encoding. Hungarian matching during training resolves permutation invariance across compartments. We introduce mean Average Precision as a reproducible benchmark metric. Evaluated on synthetic test data with up to five compartments per voxel, our model achieves R^2=0.95 for MD, R^2=0.88 for FA, and a median angular error of 4.2°, with performance scaling naturally with compartmental signal fraction.
ER -