Rotation-invariant graph message passing enables acquisition protocol generalisation in learning-based brain microstructure estimation

TL;DR

This paper introduces a rotation-invariant graph neural network for brain microstructure estimation from diffusion MRI data, capable of generalizing across different acquisition protocols without retraining, thus enabling rapid and versatile clinical applications.

Contribution

The authors develop a novel rotation-invariant graph neural network that generalizes across protocols, addressing a key limitation of existing learning-based microstructure estimation methods.

Findings

Model accurately estimates microstructure from unseen protocols.

Demonstrates domain generalization without retraining.

Enables rapid, protocol-agnostic brain microstructure mapping.

Abstract

Estimating brain microstructure has important applications in medicine and neuroscience. Diffusion-weighted magnetic resonance imaging enables measuring microstructure \textit{in vivo}. Conventional biophysical model fitting can be accurate but is slow and impractical for time-critical clinical use, where machine learning can offer a potential route to rapid estimation. We address the problem of microstructure estimation under arbitrary acquisition protocols where most existing learning-based methods fail due to protocol assumptions, requiring retraining when the protocol changes. We present a graph neural network that represents input data as a point cloud in the 3D space where diffusion-weighted measurements are made and performs rotation-invariant message passing with permutation-invariant pooling, producing fixed-size embeddings that encode microstructure. The inductive biases of our relatively small model were guided by the underlying physics and symmetries of the problem rather than by generic model architectures. Trained on randomised simulated data, our model demonstrates domain generalisation, accurately estimating microstructure from data with unseen real-world protocols without retraining. This approach represents a step towards a "train once, deploy anywhere" architecture, bringing rapid learning-based microstructure mapping closer to clinical deployment.