Gender identification based on human brain structural MRI with a multi‐layer 3D convolution extreme learning machine. Issue 4 (4th December 2019)

• Record Type: Journal Article
• Authors: Hu, Dewen; Luo, Zhiguo; Zhao, Longfei
• Is Part Of: Cognitive computation and systems. Volume 1:Issue 4(2019)
• Page Start: 91
• Page End: 96
• Publication Date: 2019-12-04
• Subjects: biomedical MRI -- neurophysiology -- feature extraction -- image classification -- diseases -- medical image processing -- brain -- convolutional neural nets -- gender issues -- medical disorders -- psychology; male brains -- female brains -- brain diseases -- multilayer 3D convolution extreme learning machine -- sex‐specific brain differences -- structural MRI grey matter -- human connectome projects -- MCN‐ELM algorithm -- human brain -- neuroimaging studies -- gender differences -- psychiatric disorders -- sMRI -- HCP -- multilayer 3D convolution neural networks; Cognitive science -- Periodicals; Artificial intelligence -- Periodicals; Neurosciences -- Periodicals; Computer science -- Periodicals; Neurosciences; Computer science; Cognitive science; Artificial intelligence; Periodicals; Electronic journals; 006.3
• DOI: 10.1049/ccs.2018.0018
• Languages: English
• ISSNs: 2517-7567

Abstract

Abstract : Previous group‐level neuroimaging studies have shown significant gender differences in the human brain. Research on sex‐specific brain differences in healthy individuals is an important base for understanding sex‐specific expression in psychiatric disorders. This study proposes a multi‐layer 3D convolution extreme learning machine (MCN‐ELM) to classify male and female brains based on structural MRI (sMRI) grey matter (GM) data scans from human connectome projects (HCP) of 876 healthy adults (491 females). First, the authors extracted multi‐scale features by three‐scale multi‐layer 3D convolution neural networks (CNNs) without fine‐tuning the parameters of convolution kernels. Then, they pulled the network output feature maps into a vector as separate ELMs. By voting on the three‐scale networks, the MCN‐ELM algorithm classifies male and female brains with an accuracy of 98.06% through a 10‐fold cross‐validation strategy, outperforming other state‐of‐the‐art algorithms. The proposed method may be used to understand other brain diseases. Additionally, the results show that the human brain can be categorised into two distinct classes, male and female brains, suggesting it is better to treat men and women separately when researching psychiatric disorders.