Welcome to the InfoSci Platform
Reference Hub3
Comparison Analysis of GLCM and PCA on Parkinson's Disease Using Structural MRI

Comparison Analysis of GLCM and PCA on Parkinson's Disease Using Structural MRI

Sanjana Tomer, Ketna Khanna, Sapna Gambhir, Mohit Gambhir
Copyright: © 2022 |Volume: 12 |Issue: 1 |Pages: 15
ISSN: 2155-6377|EISSN: 2155-6385|EISBN13: 9781683182085|DOI: 10.4018/IJIRR.289577
Cite Article Cite Article

MLA

Tomer, Sanjana, et al. "Comparison Analysis of GLCM and PCA on Parkinson's Disease Using Structural MRI." IJIRR vol.12, no.1 2022: pp.1-15. http://doi.org/10.4018/IJIRR.289577

APA

Tomer, S., Khanna, K., Gambhir, S., & Gambhir, M. (2022). Comparison Analysis of GLCM and PCA on Parkinson's Disease Using Structural MRI. International Journal of Information Retrieval Research (IJIRR), 12(1), 1-15. http://doi.org/10.4018/IJIRR.289577

Chicago

Tomer, Sanjana, et al. "Comparison Analysis of GLCM and PCA on Parkinson's Disease Using Structural MRI," International Journal of Information Retrieval Research (IJIRR) 12, no.1: 1-15. http://doi.org/10.4018/IJIRR.289577

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Parkinson disease (PD) is a neurological disorder where the dopaminergic neurons experience deterioration. It is caused from the death of the dopamine neurons present in the substantia nigra i.e., the mid part of the brain. The symptoms of this disease emerge slowly, the onset of the earlier stages shows some non-motor symptoms and with time motor symptoms can also be gauged. Parkinson is incurable but can be treated to improve the condition of the sufferer. No definite method for diagnosing PD has been concluded yet. However, researchers have suggested their own framework out of which MRI gave better results and is also a non-invasive method. In this study, the MRI images are used for extracting the features. For performing the feature extraction techniques Gray Level Co-occurrence Matrix and Principal Component Analysis are performed and are analysed. Feature extraction reduces the dimensionality of data. It aims to reduce the feature of data by generating new features from the original one.