Assessing the Feasibility of Estimating Axon Diameter using Diffusion Models and Machine Learning

Rutger H.J. Fick (1) , Neda Sepasian (2) , Marco Pizzolato (1) , Andrada Ianus (3, 4) , Rachid Deriche (1)

1 ATHENA - Computational Imaging of the Central Nervous System
2 TU/e - Eindhoven University of Technology [Eindhoven]
3 Champalimaud Centre for the Unknown [Lisbon]
4 UCL-CS - Department of Computer science [University College of London]

Axon diameter estimation has been a focus of the diffusion MRI community for the past decade. The main argument has been that while diffusion models always overestimate the true axon diameter, their estimation still correlates with changes in true value. Until now, this remains more as a discussion point. The aim of this paper is to clarify this hypothesis using a recently acquired cat spinal cord data set, where the diffusion MRI signal of both a multi-shell and Ax-Caliber acquisition have been registered with the underlying histology values. We find that the axon diameter as estimated by signal models and AxCaliber does not correlate with their true sizes for axon diameters smaller than 3 µm. On the other hand, we also train a random forest machine learning algorithm to map signal-based features to histology values of axon diameter and volume fraction. The results show that, in this dataset, this approach leads to a more reliable estimation of physically relevant axon diameters than using sophisticated diffusion models.

Mots clés: Random Forest; Index Terms— Diffusion MRI; Axon Diameter; Validation; Histology; MAP-MRI; 1D-SHORE; AxCaliber; Machine Learning

Domaines: Traitement du signal et de l'image [eess.SP]

Rutger H.J. Fick, Neda Sepasian, Marco Pizzolato, Andrada Ianus, Rachid Deriche. Assessing the Feasibility of Estimating Axon Diameter using Diffusion Models and Machine Learning. IEEE International Symposium on Biomedical Imaging (ISBI), Apr 2017, Melbourne, Australia. ⟨hal-01451664⟩