An Optimization Approach Based on Collective Correlation Coefficient for Biomarker Extraction in the Classification of Alzheimer’s Disease
In this paper, based on Magnetic Resonance Imaging (MRI), the effective biomarkers were efficiently extracted for the classification of Alzheimer’s Disease (AD), mild cognitive impairment (MCI) and health control (HC) with the help of the improved Genetic Algorithm based on the Collective Correlation Coefficient (GA-CCC). Firstly, 544 related features from 68 regions of left and right brain hemispheres were extracted. Secondly, aiming at optimizing Gaussian Process Classifier (GPC) performance, the CCC was employed to help extract the biomarkers for the AD classification and to improve the optimization efficiency of the conventional GA. Finally, experiments showed that the proposed GA-CCC significantly improved the classifications of AD vs. MCI and MCI vs. HC in an efficient way. Plus, many acquired brain regions are known to be strongly involved in the pathophysiological mechanisms of AD.
KeywordsMagnetic Resonance Imaging Alzheimer’s Disease Collective Correlation Coefficient Biomarker
This study was supported by NSF of China (grant No. 61772143, 61300107 and 61672168), NSF of Guangdong (grant No. S2012010010212), NSF of Guangzhou (grant No. 201601010034 and 201804010278) and the Opening Project of Guangdong Key Laboratory of Big Data Analysis and Processing (grant No. 201801). Data collection and sharing for this project was funded by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer’s Association; Alzheimer’s Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer’s Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California.
- 1.Chen, B., Zhang, D.Q.: Predicting clinical variables in Alzheimer’s disease based on multimodal relevance vector regression. J. Nanjing Univ. (Nat. Sci.) 48(2), 140–146 (2012)Google Scholar
- 3.Young, J.M.: Probabilistic Prediction of Alzheimer’s Disease from Multimodal Image Data with Gaussian Processes. Doctoral dissertation, University of London (2015)Google Scholar
- 5.Zheng, L.P., Hao, Z.X.: A review on the theory for the genetic algorithm. Comput. Eng. Appl. 39(21), 50–53 (2003)Google Scholar
- 7.Lama, R.K., et al.: Diagnosis of Alzheimer’s disease based on structural MRI images using a regularized extreme learning machine and PCA features. J. Healthc. Eng. (2017)Google Scholar
- 8.Jongkreangkrai, C., Vichianin, Y., Tocharoenchai, C., Arimura, H.: Computer-aided classification of Alzheimer’s disease based on support vector machine with combination of cerebral image features in MRI. J. Phys. Conf. Ser. 694(1), 012036 (2016)Google Scholar