An intelligent Alzheimer’s disease diagnosis method using unsupervised feature learning

Abstract

In computer systems, especially with the advancement of the Internet and databases, big data is increasingly expanding and is advancing exponentially [1-4]. This is mostly true in medical big data and images. Therefore, the issue of exploding data shows the concept and power of the big data. In the field of medicine, especially magnetic resonance imaging (MRI) images, the issue of big data with high data dimensions is investigated [5]. As people grow older in the community, an untreated disease would be common, which is called Alzheimer's, and it has been proven that it has no treatment, but it can be prevented from development with timely diagnosis. Alzheimer is known as the most common disease among the various causes of dementia and with each passing decade, the number of people infected with the disease is almost doubled. For this reason, timely

[Retracted] An Exploration: Alzheimer’s Disease Classification Based on Convolutional Neural Network

“…As compared to the normal control, an increased GM atrophy rate of about 2 percent/year was seen in AD subjects [ 73 ]. It may improve the precision of the diagnosis and thus act as an early diagnostic biomarker, especially for AD [ 74 ]. Image registration technique is used by [ 72 ], which means to align two or more images with the other image designated as fixed or reference image using the Montreal Neurological Institute standard space (MNI152).…”

“…The classification process includes multiple steps including feature extraction, selection, and reducing the number of features (i.e., dimensionality reduction), and finally, based on the reduced selected features, classification is performed. With the advent of neural networks, primarily CNN, it has become possible to integrate all these steps into a single system and be able to automatically and adaptively learn the hierarchy of features from low to complex levels by back propagation [ 74 ]. Still, for the active researcher, it is the biggest challenge to manage the whole neuroimaging modality.…”

“…Another widely used preprocessing technique is the motion correction utilized in [72] to suppress the motion artifacts. With the advent of neural networks, primarily CNN, it has become possible to integrate all these steps into a single system and be able to automatically and adaptively learn the hierarchy of features from low to complex levels by back propagation [74]. Still, for the active researcher, it is the biggest challenge to manage the whole neuroimaging modality.…”

Diagnosis of Alzheimer’s Disease by Time-Dependent Power Spectrum Descriptors and Convolutional Neural Network Using EEG Signal

“…The purpose of unsupervised feature learning is to define AD using the principle of unsupervised feature learning. An approach used sparse filtering to learn the expressive characteristics of brain images [ 78 ]. The SoftMax regression is trained to classify the circumstances.…”

Diagnosis of Alzheimer's Disease by Three-Dimensional Convolutional Neural Network Using Unsupervised Feature Learning Method

“…The authors of ref [20] recommended two methods: first, learn the features that characterize Alzheimer's illness using sparse filtering learning. For automatic classification, a second SoftMax regression technique was trained.…”