Subcortical Features based Alzheimer’s disease diagnosis using Support vector machine
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Effective and accurate diagnosis of Alzheimer’s disease is currently of significant interest. Alzheimer’s disease (AD) is a highly progressive, neurodegenerative brain disorderliness that mainly attacks neurotransmitters, brain cells and brain nerves, affecting the working functions of brain such as its memory and actions or behaviours, finally causing dementia on ageing people. It is a severe neurological brain disorder, which is not curable, but earlier detection of Alzheimer’s disease can be helpful for proper treatment and prevent brain tissue damage. Detection and classification of Alzheimer’s disease are challenging. In this paper, a new Alzheimer’s disease detection and classification model using brain MRI data analysis are presented. High-resolution three-dimensional sMRI images were acquired from 100 AD subjects and 316 Healthy controls (HC). To segment the sub-cortical brain, a fully automated Freesurfer software package is calculated. Finally, 66 sub-cortical brain segmentation features are automatically extracted. After that, Principal component analysis (PCA) is used for dimensionality reduction purpose and a classification process is performed by applying Support vector machine (SVM) and Feed Forward neural network (FNN). Experimental results on the OASIS dataset show that SVM with feature selection approach could significantly improve classification accuracy of AD and HC subjects.
Abstract
Effective and accurate diagnosis of Alzheimer’s disease is currently of significant interest. Alzheimer’s disease (AD) is a highly progressive, neurodegenerative brain disorderliness that mainly attacks neurotransmitters, brain cells and brain nerves, affecting the working functions of brain such as its memory and actions or behaviours, finally causing dementia on ageing people. It is a severe neurological brain disorder, which is not curable, but earlier detection of Alzheimer’s disease can be helpful for proper treatment and prevent brain tissue damage. Detection and classification of Alzheimer’s disease are challenging. In this paper, a new Alzheimer’s disease detection and classification model using brain MRI data analysis are presented. High-resolution three-dimensional sMRI images were acquired from 100 AD subjects and 316 Healthy controls (HC). To segment the sub-cortical brain, a fully automated Freesurfer software package is calculated. Finally, 66 sub-cortical brain segmentation features are automatically extracted. After that, Principal component analysis (PCA) is used for dimensionality reduction purpose and a classification process is performed by applying Support vector machine (SVM) and Feed Forward neural network (FNN). Experimental results on the OASIS dataset show that SVM with feature selection approach could significantly improve classification accuracy of AD and HC subjects.
참고문헌 (15)
- Muller, H., "A review of contentbased image retrieval systems in medical applications---Clinical benefits and future directions", Int. J. Medical Inf, 73(1), pp.1~23 (2004)
- Müller H, "Biomedical image processing—methods and applications", pp.471~494 (2011), Springer
- Ferri, C. P., "Global prevalence of dementia: A Delphi consensus study", Lancet, 366, pp.2112~2117 (2005)
- Cummings JL, "Treatment of Alzheimer's disease:Current and future therapeutic approaches", Rev Neurol Dis, 1, pp.60~69 (2004)
- Franko E, "Alzheimer's disease Neuroimaging Initiative (2013): Evaluating Alzheimer's disease progression using rate of regional hippocampal atrophy", PLoS One, 8, pp.e71354~ (2013)
- Price JL, "Tangles and plaques in nondemented aging and “preclinical” Alzheimer's disease", Ann Neurol, 45, pp.358~368 (1999)
- Ramesh Kumar Lama, "Diagnosis of Alzheimer’s Disease Based on Structural MRI Images Using a Regularized Extreme Learning Machine and PCA Features", Journal of Healthcare Engineering, 2017, pp.11~ (2017)
- F. Liu, "Multiple Kernel Learning in the Primal for Multimodal Alzheimer’s Disease Classification", IEEE Journal of Biomedical and Health Informatics, 18(3), pp.984~990 (2014)
- Barnes J, "A meta-analysis of hippocampal atrophy rates in Alzheimer's disease", Neurobiol Aging (2008)
- S. Liu, "Multimodal Neuroimaging Feature Learning for Multiclass Diagnosis of Alzheimer's Disease", IEEE Transactions on Biomedical Engineering, 62(4), pp.1132~1140 (2015)
- Zhang D, "Multimodal classification of Alzheimer’s disease and mild cognitive impairment", NeuroImage, 55(3), pp.856~867 (2011)
- F. Li, "A Robust Deep Model for Improved Classification of AD", MCI Patients, 2015, pp.19(5), 1610~1616
- Fischl, B., "Whole brain segmentation : automated labeling of neuroanatomical structures in the human brain", Neuron, 33, pp.341~355 (2002)
- Debesh Jha, "Diagnosis of Alzheimer’s Disease Using Dual-Tree Complex Wavelet Transform, PCA, and Feed-Forward Neural Network", Journal of Healthcare Engineering, 2017, pp.13~ (2017)
- Cortes, Corinna, "Supportvector networks", Machine Learning, 20(3), pp.273~297 (1995)