English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Diffusion magnetic resonance imaging is sensitive to the microstructuralproperties of brain tissue. However, estimating clinically and scientificallyrelevant microstructural properties from the measured signals remains a highlychallenging inverse problem that machine learning may help solve. This studyinvestigated if recently developed rotationally invariant sphericalconvolutional neural networks can improve microstructural parameter estimation.We trained a spherical convolutional neural network to predict the ground-truthparameter values from efficiently simulated noisy data and applied the trainednetwork to imaging data acquired in a clinical setting to generatemicrostructural parameter maps. Our network performed better than the sphericalmean technique and multi-layer perceptron, achieving higher prediction accuracythan the spherical mean technique with less rotational variance than themulti-layer perceptron. Although we focused on a constrained two-compartmentmodel of neuronal tissue, the network and training pipeline are generalizableand can be used to estimate the parameters of any Gaussian compartment model.To highlight this, we also trained the network to predict the parameters of athree-compartment model that enables the estimation of apparent neural somadensity using tensor-valued diffusion encoding.

Spherical convolutional neural networks can improve brain microstructure estimation from diffusion MRI data