Activation data; Computer algorithms; Computer-assisted instrumentation; Diffusion imaging; Functional magnetic resonance imaging, fMRI; Functional neural systems; Image interpretation; Large data sets; Magnetic resonance imaging, MRI; Multiple database analyses; Neuroimaging; Pattern classification; Pattern recognition; Quantitative measurement; Support vector machine, SVM
Machine learning is the process of using computer algorithms to develop models by iteratively learning from data independent of human intervention. The advantage is that the learning algorithms make use of all available data, with the models adapting or “learning” as new data are introduced. Common examples include popular social networking and online shopping sites that employ machine learning to identify preferences and provide recommendations to its users. Regarding neuroimaging, machine learning is being utilized to understand underlying dimensions of important functional neural systems...
References and Readings
- Abdulkadir, A., Mortamet, B., Vemuri, P., Jack Jr., C. R., Krueger, G., & Kloppel, S. (2011). Effects of hardware heterogeneity on the performance of SVM Alzheimer’s disease classifier. NeuroImage, 58(3), 785–792. https://doi.org/10.1016/j.neuroimage.2011.06.029.CrossRefPubMedPubMedCentralGoogle Scholar
- Koutsouleris, N., Gaser, C., Bottlender, R., Davatzikos, C., Decker, P., Jager, M., …, & Meisenzahl, E. M. (2010). Use of neuroanatomical pattern regression to predict the structural brain dynamics of vulnerability and transition to psychosis. Schizophrenia Research, 123(2–3), 175–187. https://doi.org/10.1016/j.schres.2010.08.032.CrossRefGoogle Scholar
- Wang, L., Alpert, K. I., Calhoun, V. D., Cobia, D. J., Keator, D. B., King, M. D., …, & Ambite, J. L. (2016). SchizConnect: Mediating neuroimaging databases on schizophrenia and related disorders for large-scale integration. NeuroImage, 124(Pt B), 1155–1167. https://doi.org/10.1016/j.neuroimage.2015.06.065.CrossRefGoogle Scholar