Machine learning in fMRI classification
Statistical analysis method is utilitarian in neuroimaging. For instance, SPM12, FSL and BrainVoyager are widely used for testing the hypotheses about functional magnetic resonance imaging (fMRI). However, that testing and studying of brain images mostly consist of experts work. It is not fully auto...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
International Neuroinformatics Coordinating Facilities (INCF)
2016
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/61306/6/61306-Machine%20learning.pdf http://irep.iium.edu.my/61306/ https://www.frontiersin.org/books/Neuroinformatics_2016/976 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Islam Antarabangsa Malaysia |
| Language: | English |
| Summary: | Statistical analysis method is utilitarian in neuroimaging. For instance, SPM12, FSL and BrainVoyager are widely used for testing the hypotheses about functional magnetic resonance imaging (fMRI). However, that testing and studying of brain images mostly consist of experts work. It is not fully automatic and time-consuming. There are fractions of decision making processes by the experts that require extensive knowledge and sets of rule of thumb. Systematically, machine learning is expected to automate the process while running the embedded sets of rule of thumb during the process. In addition, pattern recognition is one of the method in machine learning that differ to working principle of SPM12 and its counterpart. The recognizing of patterns in brain images is expected to pragmatically tackle the work of testing the fMRI hypotheses. Thus, the aim of this paper is to prove the need of machine learning in fMRI classification. |
|---|