Predicting Autism from Resting-State fMRI Data

This study obtained fMRI data from a publicly available Autism Brain Imaging Data Exchange (ABIDE) database (Di Martino et al., 2014 (link)). For the following analysis and prediction, we used 75 ASD patients and 102 healthy controls with ages ranging from 6.5 to 39.1 years old, scanned at New York University Langone Medical Center. ASD subjects were included based on the autism criteria in Diagnostic and Statistical Manual of Mental Disorders, 4th Edition, Text Revision (DSM-IV-TR) (American Psychiatric Association, 2000 ). Additionally, these subjects were acquired with a 3-T Siemens Allegra scanner. The main parameters of functional images for the resting-state are as follows: repetition time (TR)/Echo time (TE) = 2000/15 ms, flip angle = 90°, number of slices = 33, slice thickness = 4 mm, and voxel size = 3.0 × 3.0 × 4.0 mm³. T1-weighted images were acquired with the following parameters: TR/TE = 2530/3.25 ms, flip angle = 7°, slice thickness = 1.33 mm, and voxel size = 1.3 × 1.0 × 1.3 mm³. More details on the subject collection, exclusion criteria, and data parameters can be obtained from the website.¹