fMRI Feature Extraction Model for ADHD Classification Using Convolutional Neural Network

This study addresses ADHD identification using functional magnetic resonance imaging (fMRI) data for the resting state brain by evaluating multiple feature extraction methods. The features of seed-based correlation (SBC), fractional amplitude of low-frequency fluctuation (fALFF), and regional homogeneity (ReHo) are comparatively applied to obtain the specificity and sensitivity. This helps to determine the best features for ADHD classification using convolutional neural networks (CNN). The methodology using fALFF and ReHo resulted in an accuracy of 67%, while SBC gained an accuracy between 84% and 86% and sensitivity between 65% and 75%.

Source: International Journal of E-Health and Medical Communications - November 4, 2020 Category: Information Technology Authors: De Silva, Senuri Dayarathna, Sanuwani Udara Ariyarathne, Gangani Meedeniya, Dulani Jayarathna, Sampath Tags: Health Information Systems Medicine & Healthcare Source Type: research