The Approximation of the Dissimilarity Projection

TL;DR

This paper explores how to effectively embed brain tractography data into a vector space using dissimilarity measures, enabling better machine learning analysis of complex neural pathways.

Contribution

It introduces a dissimilarity-based embedding method for tractography data and evaluates approximation quality with various prototype selection strategies.

Findings

Dissimilarity projection can approximate tractography data effectively.

Prototype selection impacts the accuracy and scalability of the embedding.

A scalable approximation method offers fast and accurate embeddings.

Abstract

Diffusion magnetic resonance imaging (dMRI) data allow to reconstruct the 3D pathways of axons within the white matter of the brain as a tractography. The analysis of tractographies has drawn attention from the machine learning and pattern recognition communities providing novel challenges such as finding an appropriate representation space for the data. Many of the current learning algorithms require the input to be from a vectorial space. This requirement contrasts with the intrinsic nature of the tractography because its basic elements, called streamlines or tracks, have different lengths and different number of points and for this reason they cannot be directly represented in a common vectorial space. In this work we propose the adoption of the dissimilarity representation which is an Euclidean embedding technique defined by selecting a set of streamlines called prototypes and then mapping any new streamline to the vector of distances from prototypes. We investigate the degree of approximation of this projection under different prototype selection policies and prototype set sizes in order to characterise its use on tractography data. Additionally we propose the use of a scalable approximation of the most effective prototype selection policy that provides fast and accurate dissimilarity approximations of complete tractographies.