Alzheimer is a memory depletion disease, which is widely recognized as dementia. The research on early detection of dementia has received huge interest among the researchers to help in reducing mortality rates of Alzheimer's patients. In recent years in the medical field, the deep learning techniques play an important role in computer aided diagnosis. In this research, the automatic recognition of Alzheimer Disease (AD) based on the Magnetic Resonance Imaging (MRI) is accomplished by implementing an unsupervised classification technique named Deep Neural Network (DNN) with the rectified Adam optimizer. At first, Histogram of Oriented Gradients (HOG) is utilized to extract the feature values from the brain images, which were acquired from National Institute of Mental Health and Neurosciences (NIMHANS) and Alzheimer disease Neuroimaging Initiative (ADNI) datasets. Next, the extracted features were given as the input to DNN with the rectified Adam optimizer to distinguish the healthy, AD and Mild Cognitive Impairment (MCI) patients. The experimental results have revealed that the HOG-DNN with the rectified Adam optimizer has achieved better performance in AD recognition and showed 16% enhancement in classification accuracy compared to other existing work; Landmark based features with support vector machine classifier.

Detection of Alzheimer disease using Magnetic Resonance Imaging (MRI) is the most challenging aspect in the field of medical image processing and analysis. In this paper, the proposed methodology has three major steps: image acquisition, image pre-processing and segmentation. Initially, the brain images were acquired from the dataset: Open Access Series of Imaging Studies (OASIS). After image acquisition, image pre-processing was carried out using median filter, it utilized for cutting down the noise and to improve the quality of acquired brain images. Then, segmentation was carried-out using Fast-Independent Component Analysis (Fast-ICA) along with Otsu multilevel thresholding. It was a flexible high level machine learning technique to localize the object in complex template. In experimental analysis, the proposed approach distinguishes the brain MRI tissues: White Matter (WM), Cerebro-Spinal Fluid (CSF), and Grey Matter (GM) by means of Tanimoto index, similarity index, precision, and recall. The proposed methodology improved the Alzheimer tissue detection up to 15-30% compared to the existing methods: Band Expansion Process (BEP), ICA and BEP-ICA in terms of precision and recall.

No abstract

No abstract

The automatic recognition and classification of Alzheimer disease utilizing magnetic resonance imaging is a hard task, due to the complexity and variability of the size, location, texture and shape of the lesions. The objective of this study is to propose a proper feature dimensional reduction and classification approach to improve the performance of Alzheimer disease recognition and classification. At first, the input brain images were acquired from Open Access Series of Imaging Studies (OASIS) and National Institute of Mental Health and Neuro Sciences (NIMHANS) databases. Then, the image pre-processing and feature extraction were attained by applying Contrast Limited Adaptive Histogram Equalization (CLAHE) and Discrete Wavelet Transform (DWT) approach to denoise and extract the feature vectors from the images. In addition, Probabilistic Principal Component Analysis (PPCA) was used to diminish the extracted features dimension that effectively lessen the “curse of dimensionality” concern. At last, Long Short-Term Memory (LSTM) classifier was employed to classify the brain images as Alzheimer disease, normal, and Mild Cognitive Impairment (MCI). From the simulation outcome, the proposed system attained better performance compared to the existing systems and showed 3–11% improvement in recognition accuracy.