An autism spectrum disorder adaptive identification based on the Elimination of brain connections: a proof of long-range underconnectivity

Autism spectrum disorder (ASD) is theoretically characterized by alterations in functional connectivity between brain regions. Many works presented approaches to determine informative patterns that help predict autism from typical development. However, most of the proposed pipelines are not specifically designed for problem, i.e. they do corroborate with theories about connectivity. In this paper, we propose a framework takes into account properties local and long range under-connectivity autistic brain. The originality approach adopt elimination as technique order well emerge alterations, show how contribute differentiate ASD controls. Experimental results conducted on large multi-site Brain Imaging Data Exchange (ABIDE) our provides accurate prediction up 70% succeeds prove existence deficits long-range subjects brains.