Assessment of Alzheimer's Disease through sMRI Phase Images

Classification of patients of different categories of Alzheimer's disease (AD) is a challenging task with subsequent applications in the diagnosis of AD. This task requires careful examination of results by a panel of experts which is usually cumbersome and hard to obtain and is intricate in conventional MRI images due to similar intensities of background pixels and surrounding brain structures. Manual interpretation of results is also difficult and time consuming. There is a need for an accurate and robust method for the classification of initial stages of AD that uses disease non-specific features and requires very little or no intervention of a medical domain expert. In this research, state of the art machine learning algorithms such as Independent Component Analysis, Neural Nets and Support Vector Machine have been used for the classification and assessment of sMRI phase images of initial categories of AD. Obtained results are quite satisfactory is terms of accuracy and robustness of classification of initial categories of AD as well as predicting the influence of different socioeconomic parameters on the rate of progression of AD in its early stages.

Autorentext

Ahsan Bin Tufail received the MS degree in electrical engineering from National University of Sciences and Technology, Islamabad, Pakistan, in 2013. Since then, he has been with Allied Bank Ltd, Lahore, Pakistan, where he is currently working as an Information Technology Officer at Information Technology Group.

Klappentext

Classification of patients of different categories of Alzheimer's disease (AD) is a challenging task with subsequent applications in the diagnosis of AD. This task requires careful examination of results by a panel of experts which is usually cumbersome and hard to obtain and is intricate in conventional MRI images due to similar intensities of background pixels and surrounding brain structures. Manual interpretation of results is also difficult and time consuming. There is a need for an accurate and robust method for the classification of initial stages of AD that uses disease non-specific features and requires very little or no intervention of a medical domain expert. In this research, state of the art machine learning algorithms such as Independent Component Analysis, Neural Nets and Support Vector Machine have been used for the classification and assessment of sMRI phase images of initial categories of AD. Obtained results are quite satisfactory is terms of accuracy and robustness of classification of initial categories of AD as well as predicting the influence of different socioeconomic parameters on the rate of progression of AD in its early stages.