کنفرانس مهندسی برق ایران

صفحه اصلی / سی و یکمین کنفرانس بین المللی مهندسی برق

Deep Convolutional Neural Network for ADHD Classification using resting-state fMRI

نویسندگان :

MohammadHadi Firouzi¹ Maliheh Ahmadi² Kamran Kazemi³ Mohammad Sadegh Helfroush⁴ Ardalan Aarabi⁵

1- دانشگاه صنعتی شیراز 2- دانشگاه صنعتی شیراز 3- دانشگاه صنعتی شیراز 4- دانشگاه صنعتی شیراز 5- دانشگاه پیکاردی ژول وررن فرانسه

کلمات کلیدی :

Attention deficit-hyperactivity disorder،Resting-state fMRI،Deep learning،Convolutional neural network

چکیده :

Attention Deﬁcit/Hyperactivity Disorder (ADHD) is the most common diagnosed mental disorder in childhood and may persist into adulthood. ADHD is characterized by symptoms of inattention, hyperactivity and impulsivity. ADHD is a neurodevelopmental disease and widely affects brain functions, thus investigating brain functional connectivity is more effective in the childhood. The exact mechanism of how ADHD affects brain neural connections is not discovered and discriminating children with ADHD from the control group is challenging issue. Deep learning methods demonstrated promising result for diagnosing diseases. Deep learning and neuroimaging tools such as functional resonance imaging (fMRI) was combined in order to differentiate among neural activities of ADHD and TDC patients. This study suggests a deep learning-based procedure that is used for classifying these TDC and ADHD groups. At the first step resting-state fMRI (rsfMRI) data of NYU imaging site from ADHD-200 global competition public dataset were preprocessed for in order to remove artifacts. Next, our algorithm uses functional parcellation for dividing brain regions into 412 parcels. Our algorithm extracts features and classifies ADHD and TDC patients at a same time while some other methods extract features and classify subjects with different algorithms. 5-fold cross-validation is applied to investigate classification results. Our results show that proposed procedure in this study outperforms other methods in state-of-the-art by accuracy of 76.088.