Abstract
Difference exists widely in cognition, behavior and psychopathology between males and females, while the underlying neurobiology is still unclear. As brain structure is the fundament of its function, getting insight into structural brain may help us to better understand the functional mechanism of gender difference. Previous structural studies of gender difference in Magnetic Resonance Imaging (MRI) usually focused on gray matter (GM) concentration and structural connectivity (SC), leaving cortical morphology not characterized properly. In this study a large dataset is used to explore whether cortical three-dimensional (3-D) morphology can offer enough discriminative morphological features to effectively identify gender. Data of all available healthy controls (N = 1113) from the Human Connectome Project (HCP) were utilized. We suggested a multivariate pattern analysis method called Hierarchical Sparse Representation Classifier (HSRC) and got an accuracy of 96.77% for gender identification. Permutation tests were used to testify the reliability of gender discrimination (p < 0.001). Cortical 3-D morphological features within the frontal lobe were found the most important contributors to gender difference of human brain morphology. Moreover, we investigated gender discriminative ability of cortical 3-D morphology in predefined Anatomical Automatic Labeling (AAL) and Resting-State Networks (RSN) templates, and found the superior frontal gyrus the most discriminative in AAL and the default mode network the most discriminative in RSN. Gender difference of surface-based morphology was also discussed. The frontal lobe, as well as the default mode network, was widely reported of gender difference in previous structural and functional MRI studies, which suggested that morphology indeed affect human brain function. Our study indicates that gender can be identified on individual level by using cortical 3-D morphology and offers a new approach for structural MRI research, as well as highlights the importance of gender balance in brain imaging studies.
Highlights
CentOS 6.7, MATLAB R2015b, 1 fold Robust Feature Selection (RFS): 151.3 (0.7 mm) +158.8 (1.4 mm) +64.3 (2.8 mm) = 374.4 s for Hierarchical Sparse Representation Classifier (HSRC); 5682.6 s (0.7 mm) for direct sparsity) and storage demanded, but when direct sparsity is conducted in different resolution data, we do not see improvement of overall classification performance in higher resolution data, which proves that our HSRC algorithm plays a part
We investigated gender difference of cortical 3D morphology by proposing an HSRC approach, and got an accuracy of 96.77% in a 10-fold cross-validation
The robustness of classification was testified by permutation tests, and the frontal lobe was found the most discriminative region of gender difference in cortical 3-D morphology selected by HSRC
Summary
Gender difference has been widely reported in psychiatric and neurological diseases (Piccinelli and Wilkinson, 2000; Baron-Cohen et al, 2005; Shulman, 2007; Eranti et al, 2013; Lai et al, 2015), cognitive functions (Ren et al, 2009; Ohla and Lundstr, 2013; Yin et al, 2017; Chen et al, 2018) and behaviors (Christov-Moore et al, 2014), while its neurobiological mechanism is unclear yet Gender Identification of Cortical Morphology (Giudice, 2009). Previous reports tend to explain gender difference in the view of GM concentration, SC and Functional Connectivity (FC). Wang et al (2012) applied multivariate pattern analysis on GM concentration and resting state fMRI from healthy young adults and got an accuracy of 89%, and they found the occipital lobe and the cerebellum the most discriminative regions of gender difference; Yuan et al (2018a) proposed a three-dimensional weighted histogram of gradient orientation to describe the complex spatial structure of human brain image, and they got an over 90% accuracy of gender classification on 527 healthy adults from four research sites; Ruigrok et al (2014) reported gender difference in the amygdala, hippocampus, and insula after meta-analysis in human brain structure; Goldstein et al (2001) found females had higher percentage of GM than males, while Gur et al (1999) got a converse result in white matter; Feis et al (2013) used multimodal gender classification of T1-weighted, T2-weighted and fractional anisotropy images and indicated the frontal lobe the most discriminative lobe. Previous reports tend to explain gender difference in the view of GM concentration, SC and Functional Connectivity (FC). Wang et al (2012) applied multivariate pattern analysis on GM concentration and resting state fMRI from healthy young adults and got an accuracy of 89%, and they found the occipital lobe and the cerebellum the most discriminative regions of gender difference; Yuan et al (2018a) proposed a three-dimensional weighted histogram of gradient orientation to describe the complex spatial structure of human brain image, and they got an over 90% accuracy of gender classification on 527 healthy adults from four research sites; Ruigrok et al (2014) reported gender difference in the amygdala, hippocampus, and insula after meta-analysis in human brain structure; Goldstein et al (2001) found females had higher percentage of GM than males, while Gur et al (1999) got a converse result in white matter; Feis et al (2013) used multimodal gender classification of T1-weighted, T2-weighted and fractional anisotropy images and indicated the frontal lobe the most discriminative lobe. Gong et al (2009) found greater overall cortical connectivity and more efficient cortical network organizations in women; Ingalhalikar et al (2013) reported that males had stronger intra-hemispheric SC while females had stronger inter-hemispheric SC using diffusion tensor imaging. Zhang et al (2018) used 4 fMRI runs of 820 healthy controls from the HCP and got the accuracy of 87% using FC features for gender prediction, and they suggested that FC within the default, fronto-parietal and sensorimotor networks had the greatest gender prediction abilities while the right fusiform gyrus and the right ventromedial prefrontal cortex contributed the most in the default mode network
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
