Comparison of distances for supervised segmentation of white matter tractography

Abstract

Abstract-Tractograms are mathematical representations of the main paths of axons within the white matter of the brain, from diffusion MRI data. Such representations are in the form of polylines, called streamlines, and one streamline approximates the common path of tens of thousands of axons. The analysis of tractograms is a task of interest in multiple fields, like neurosurgery and neurology. A basic building block of many pipelines of analysis is the definition of a distance function between streamlines. Multiple distance functions have been proposed in the literature, and different authors use different distances, usually without a specific reason other than invoking the "common practice". To this end, in this work we want to test such common practices, in order to obtain factual reasons for choosing one distance over another. For these reason, in this work we compare many streamline distance functions available in the literature. We focus on the common task of automatic bundle segmentation and we adopt the recent approach of supervised segmentation from expert-based examples. Using the HCP dataset, we compare several distances obtaining guidelines on the choice of which distance function one should use for supervised bundle segmentation.

Mapping population-based structural connectomes

“…At the population level, to quantify variations in the diffusion connectomes and local WM changes of healthy and diseased brains, there are roughly three broad analytical methods, including (i) standard region-based analysis (Lee et al, 2009; Alexander et al, 2007), (ii) voxel-based analysis (Smith et al, 2006; Schwarz et al, 2014; Snook et al, 2007), and (iii) tract-specific analysis (Fornito et al, 2013; Zhu et al, 2011; Yeatman et al, 2012; Cousineau et al, 2017; Jin et al, 2014; Heiervang et al, 2006; Ciccarelli et al, 2003; Wang et al, 2016a; Wassermann et al, 2010; Garyfallidis et al, 2017; Olivetti et al, 2017; Sharmin et al, 2016). The region-based method often parcellates the brain into regions of interest (ROIs) that have anatomical meaning and studies the statistical properties of each region (Lee et al, 2009; Alexander et al, 2007).…”

Classifyber, a robust streamline-based linear classifier for white matter bundle segmentation

“…The global landmarks are 100 streamlines evenly spread over a whole tractogram. The minimum average direct flip distance (d MDF ) is one of the most commonly adopted distance function between streamlines, see Garyfallidis et al (2012) and Olivetti et al (2017). (ii) Set 2: streamline distances from 100 local landmarks.…”

“…Streamline-based segmentation methods group together streamlines according to some similarity measures, or distances. Typical distances between two streamlines are the minimum average direct flip (d MDF ) distance or the minimum average mean (d MAM ) distance, which account for the respective positions and shapes of the two streamlines, see Garyfallidis et al (2015); Olivetti et al (2017). Based on such concepts, an accurate and easy way to compute a vectorial representation of streamlines has been proposed in Olivetti et al (2012) and since been used for multiple applications, like clustering, interactive segmentation and fast nearest-neighbor queries, see Olivetti et al (2013);Porro-Muñoz et al (2015); Sharmin et al (2016).…”

White matter fiber analysis using kernel dictionary learning and sparsity priors

“…Several studies have also focused on incorporating anatomical features into the clustering [6,13], or on clustering large multi-subject datasets [4]. A detailed description and comparison of several distances and clustering approaches can be found in [17,21,22].…”