Open AccessAlzheimer Disease Diagnosis from fMRI Images Based on Latent Low Rank Features and Support Vector Machine (SVM)
Author(s) -
Nastaran Shahparian,
Mehran Yazdi,
Mohammad R. Khosravi
Publication year - 2021
Publication title -
current signal transduction therapy
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.128
H-Index - 17
eISSN - 2212-389X
pISSN - 1574-3624
DOI - 10.2174/1574362414666191202144116
Subject(s) - support vector machine , artificial intelligence , pattern recognition (psychology) , computer science , functional magnetic resonance imaging , classifier (uml) , cognitive impairment , kernel (algebra) , disease , machine learning , medicine , psychology , neuroscience , mathematics , pathology , combinatorics
In recent years, resting-state functional magnetic resonance imaging (rsfMRI)has been increasingly used as a noninvasive and practical method in different areas of neuroscienceand psychology for recognizing brain’s mechanism as well as diagnosing neurologicaldiseases. In this work, we use rs-fMRI data for diagnosing Alzheimer's disease. Materials and Methods: To do that, by using the rs-fMRI of a patient, we computed the time seriesof some anatomical regions and then applied the Latent Low Rank Representation method toextract suitable features. Next, based on the extracted features, we apply a Support Vector Machine(SVM) classifier to determine whether the patient belongs to a healthy category, mild stageof the disease or Alzheimer's stage. Results: The obtained classification accuracy for the proposed method is more than 97.5%. Conclusion: We performed different experiments on a database of rs-fMRI data containing theimages of 43 healthy subjects, 36 mild cognitive impairment patients and 32 Alzheimer’s patientsand the obtained results demonstrated that the best performance is achieved when the SVM withGaussian kernel and the features of only 7 regions were used.