Joint-Connectivity-Based Sparse Canonical Correlation Analysis of Imaging Genetics for Detecting Biomarkers of Parkinson's Disease

• Published in: IEEE transactions on medical imaging Vol. 39; no. 1; pp. 23 - 34
• Main Authors: Kim, Mansu, Won, Ji Hye, Youn, Jinyoung, Park, Hyunjin
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Biomarkers; Brain; brain connectivity; Computer simulation; Connectivity; Correlation; Correlation analysis; Datasets; Diseases; Genetics; Imaging genetics; Magnetic resonance imaging; magnetic resonance imaging (MRI); Medical imaging; Movement disorders; Neural networks; Neurodegenerative diseases; Neuroimaging; Neurological diseases; Nucleotides; Parkinson's disease; Parkinson’s disease (PD); Performance evaluation; prior information; single nucleotide polymorphism (SNP); Single-nucleotide polymorphism; sparse canonical correlation analysis (SCCA); Sparse matrices
• ISSN: 0278-0062; 1558-254X; 1558-254X
• DOI: 10.1109/TMI.2019.2918839

Imaging genetics is a method used to detect associations between imaging and genetic variables. Some researchers have used sparse canonical correlation analysis (SCCA) for imaging genetics. This study was conducted to improve the efficiency and interpretability of SCCA. We propose a connectivity-based penalty for incorporating biological prior information. Our proposed approach, named joint connectivity-based SCCA (JCB-SCCA), includes the proposed penalty and can handle multi-modal neuroimaging datasets. Different neuroimaging techniques provide distinct information on the brain and have been used to investigate various neurological disorders, including Parkinson's disease (PD). We applied our algorithm to simulated and real imaging genetics datasets for performance evaluation. Our algorithm was able to select important features in a more robust manner compared with other multivariate methods. The algorithm revealed promising features of single-nucleotide polymorphisms and brain regions related to PD by using a real imaging genetic dataset. The proposed imaging genetics model can be used to improve clinical diagnosis in the form of novel potential biomarkers. We hope to apply our algorithm to cohorts such as Alzheimer's patients or healthy subjects to determine the generalizability of our algorithm.