Automated Discrimination of Brain Pathological State Attending to Complex Structural Brain Network Properties: The Shiverer Mutant Mouse Case

Abstract

Neuroimaging classification procedures between normal and pathological subjects are sparse and highly dependent of an expert's clinical criterion. Here, we aimed to investigate whether possible brain structural network differences in the shiverer mouse mutant, a relevant animal model of myelin related diseases, can reflect intrinsic individual brain properties that allow the automatic discrimination between the shiverer and normal subjects. Common structural networks properties between shiverer (C3Fe.SWV Mbpshi/Mbpshi, n = 6) and background control (C3HeB.FeJ, n = 6) mice are estimated and compared by means of three diffusion weighted MRI (DW-MRI) fiber tractography algorithms and a graph framework. Firstly, we found that brain networks of control group are significantly more clustered, modularized, efficient and optimized than those of the shiverer group, which presented significantly increased characteristic path length. These results are in line with previous structural/functional complex brain networks analysis that have revealed topologic differences and brain network randomization associated to specific states of human brain pathology. In addition, by means of network measures spatial representations and discrimination analysis, we show that it is possible to classify with high accuracy to which group each subject belongs, providing also a probability value of being a normal or shiverer subject as an individual anatomical classifier. The obtained correct predictions (e.g., around 91.6–100%) and clear spatial subdivisions between control and shiverer mice, suggest that there might exist specific network subspaces corresponding to specific brain disorders, supporting also the point of view that complex brain network analyses constitutes promising tools in the future creation of interpretable imaging biomarkers.

Studying the topological organization of the cerebral blood flow fluctuations in resting state

“…On the other hand the paralimbic regions with right asymmetric topology play a critical role in channeling emotion and motivation to behaviorally relevant motor acts, mental content and extrapersonal events (Mesulam, 2000). In line with previous findings in Iturria-Medina et al (2011a, 2011b we suppose that hub regional asymmetries indicate that left hemisphere presents more central or indispensable regions for the whole-brain structural network than the right one. Since the connectivity of a given region is related to its cellular characteristics such as cell packing density, cell size, and number of cortical neurons (Costa and Sporns, 2005;Lerch et al, 2006), blood flow asymmetries of the cortex might be related to hemisphere specific functional specializations and metabolic demand, which is based on the high correspondence between our results and well-known structural and functional regional asymmetries seems to support the fact that the left hemisphere is 'regionally' more specialized than the right one.…”

“…among cerebral regions revealing specific features of the brain networks architecture. In addition, its capabilities to differentiate normal from aberrant behaviors of human cerebral networks have been evidenced (Bassett et al, 2008;He et al, 2008He et al, , 2009aHe et al, , 2009bIturria-Medina et al, 2011b).…”

Long-term reorganization of structural brain networks in a rabbit model of intrauterine growth restriction

“…Although the study of brain networks in animal models has been seminal to the field (Sporns et al, 2005), brain networks obtained from diffusion MRI in small animals are scarce. To the best of our knowledge, this is the second study of this kind in small mammals (Iturria-Medina et al, 2011), and the first showing brain networks in rabbits. This animal model has some specific methodological difficulties that had to be overcome.…”

Combining Classification with fMRI-Derived Complex Network Measures for Potential Neurodiagnostics

“…A classifier combined with feature selection was applied optimizing for connection fraction threshold. Another study [48] applied linear discriminant analysis to global CNA measures, derived from anatomical connectivity graphs originating from a mouse model for neurological disease and control mice. This resulted in an 18 dimensional space, clearly a different scenario from the one we describe.…”