Biology subjects

de Almeida Martins, J. P.

Publications and source records attributed to de Almeida Martins, J. P..

2 recordsLinked to original sources

bioRxiv2021

Neural Networks for parameter estimation in microstructural MRI: a study with a high-dimensional diffusion-relaxation model of white matter microstructure

Specific features of white-matter microstructure can be investigated by using biophysical models to interpret relaxation-diffusion MRI brain data. Although more intricate models have the potential to reveal more details of the tissue, they also incur time-consuming parameter estimation that may con-verge to inaccurate solutions due to a prevalence of local minima in a degenerate fitting landscape. Machine-learning fitting algorithms have been proposed to accelerate the parameter estimation and increase the robustness of the attained estimates. So far, learning-based fitting approaches have been restricted to lower-dimensional microstructural models where dense sets of training data are easy to generate. Moreover, the degree to which machine learning can alleviate the degeneracy problem is poorly understood. For conventional least-squares solvers, it has been shown that degeneracy can be avoided by acquisition with optimized relaxation-diffusion-correlation protocols that include tensor-valued diffusion encoding; whether machine-learning techniques can offset these acquisition require-ments remains to be tested. In this work, we employ deep neural networks to vastly accelerate the fitting of a recently introduced high-dimensional relaxation-diffusion model of tissue microstructure. We also develop strategies for assessing the accuracy and sensitivity of function fitting networks and use those strategies to explore the impact of acquisition protocol design on the performance of the network. The developed learning-based fitting pipelines were tested on relaxation-diffusion data acquired with optimized and sub-sampled acquisition protocols. We found no evidence that machine-learning algorithms can by themselves replace a careful design of the acquisition protocol or correct for a degenerate fitting landscape.

neuroscience↗

bioRxiv2020

Visualizing orientation-specific relaxation-diffusion features mapped onto orientation distribution functions estimated via nonparametric Monte Carlo MRI signal inversion

Diffusion MRI techniques are widely used to study in vivo changes in the human brain connectome. However, to resolve and characterise white matter fibres in heterogeneous diffusion MRI voxels remains a challenging problem typically approached with signal models that rely on prior information and restrictive constraints. We have recently introduced a 5D relaxation-diffusion correlation framework wherein multidimensional diffusion encoding strategies are used to acquire data at multiple echo-times in order to increase the amount of information encoded into the signal and ease the constraints needed for signal inversion. Nonparametric Monte Carlo inversion of the resulting datasets yields 5D relaxation-diffusion distributions where contributions from different sub-voxel tissue environments are separated with minimal assumptions on their microscopic properties. Here, we build on the 5D correlation approach to derive fibre-specific metrics that can be mapped throughout the imaged brain volume. Distribution components ascribed to fibrous tissues are resolved, and subsequently mapped to a dense mesh of overlapping orientation bins in order to define a smooth orientation distribution function (ODF). Moreover, relaxation and diffusion measures are correlated to each independent ODF coordinate, thereby allowing the estimation of orientation-specific relaxation rates and diffusivities. The proposed method is tested on a healthy volunteer, where the estimated ODFs were observed to capture major WM tracts, resolve fibre crossings, and, more importantly, inform on the relaxation and diffusion features along distinct fibre bundles. If combined with fibre-tracking algorithms, the methodology presented in this work may be useful for investigating the microstructural properties along individual white matter pathways.

neuroscience↗