In this paper, we propose a novel framework for ASD diagnosis using structural magnetic resonance imaging (MRI). Our method deals explicitly with the distributional differences of gray matter (GM) and white matter (WM) features extracted from MR images. We project linearly the GM and WM features onto a canonical space where their correlations are mutually maximized. In this canonical space, features that are highly correlated with the class labels are selected for ASD diagnosis. In addition, graph matching is employed to preserve the geometrical relationships between samples when projected onto the canonical space. Our evaluations based on a public ASD dataset show that the proposed method outperforms all competing methods on all clinically important measures in differentiating ASD patients from healthy individuals.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4714957 | PMC |
| http://dx.doi.org/10.1007/s11682-015-9360-1 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Molecular Insights into the Control Mechanism of the Solid-Liquid Interface Interaction on Shale Oil Occurrence: Grand Canonical Monte Carlo and Molecular Dynamics Simulations Investigation.
Langmuir
January 2025
Hubei Key Laboratory of Oil and Gas Exploration and Development Theory and Technology (China University of Geosciences), Wuhan 430074, China.
The strong solid-liquid interaction leads to the complicated occurrence characteristics of shale oil. However, the solid-liquid interface interaction and its controls of the occurrence state of shale oil are poorly understood on the molecular scale. In this work, the adsorption behavior and occurrence state of shale oil in pores of organic/inorganic matter under reservoir conditions were investigated by using grand canonical Monte Carlo (GCMC) and molecular dynamics (MD) simulations.
View Article and Find Full Text PDFMSAB limits osteoarthritis development and progression through inhibition of β-catenin-DDR2 signaling.
Bioact Mater
April 2025
Research Center for Computer-aided Drug Discovery, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China.
The aberrant activation of the canonical Wnt/β-catenin signaling has been identified as a significant contributor to the pathogenesis of osteoarthritis (OA), exacerbating OA symptoms and driving OA progression. Despite its potential as a therapeutic target, clinical translation is impeded by the lack of a targeting delivery system and effective drug candidate that can modulate steady-state protein levels of β-catenin at post-translational level. Our study addresses these challenges by offering a new approach for OA treatment.
View Article and Find Full Text PDFTowards Rational Design of Confined Catalysis in Carbon Nanotube by Machine Learning and Grand Canonical Monte Carlo Simulations.
Angew Chem Int Ed Engl
December 2024
State Key Laboratory of Catalysis, Dalian National Laboratory for Clean Energy, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian, 116023, P. R. China.
The microenvironment is recognized to be as crucial as active sites in heterogeneous catalysis. It was found that the catalytic activity of a set of chemical reactions can be significantly influenced by the confined space of carbon nanotubes (CNTs), with some reactions showing superior activity, while others experience a negative impact. The rational design of confined catalysis must rely on the accurate insights of confined microenvironment.
View Article and Find Full Text PDFFragPT2: Multifragment Wave Function Embedding with Perturbative Interactions.
J Chem Theory Comput
January 2025
Instituut-Lorentz, Universiteit Leiden, Leiden 2300RA, The Netherlands.
Embedding techniques allow the efficient description of correlations within localized fragments of large molecular systems while accounting for their environment at a lower level of theory. We introduce FragPT2: a novel embedding framework that addresses multiple interacting active fragments. Fragments are assigned separate active spaces, constructed by localizing canonical molecular orbitals.
View Article and Find Full Text PDFIdentification of Protein Networks and Biological Pathways Driving the Progression of Atherosclerosis in Human Carotid Arteries Through Mass Spectrometry-Based Proteomics.
Int J Mol Sci
December 2024
Proteomics Core Facility, Department of Biochemistry and Molecular Biology, Faculty of Medicine, University of Debrecen, 4032 Debrecen, Hungary.
Vulnerable atherosclerotic plaques, especially hemorrhaged lesions, are the major cause of mortalities related to vascular pathologies. The early identification of vulnerable plaques helps to stratify patients at risk of developing acute vascular events. In this study, proteomics analyses of human carotid artery samples collected from patients with atheromatous plaques and complicated lesions, respectively, as well as from healthy controls were performed.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!