Automatic Alzheimer’s Disease Recognition from MRI Data Using Deep Learning Method

Abstract

Alzheimer's Disease (AD), the most common form of dementia, is an incurable neurological condition that results in a progressive mental deterioration. Although definitive diagnosis of AD is difficult, in practice, AD diagnosis is largely based on clinical history and neuropsychological data including magnetic resource imaging (MRI). Increasing research has been reported on applying machine learning to AD recognition in recent years. This paper presents our latest contribution to the advance. It describes an automatic AD recognition algorithm that is based on deep learning on 3D brain MRI. The algorithm uses a convolutional neural network (CNN) to fulfil AD recognition. It is unique in that the three dimensional topology of brain is considered as a whole in AD recognition, resulting in an accurate recognition. The CNN used in this study consists of three consecutive groups of processing layers, two fully connected layers and a classification layer. In the structure, every one of the three groups is made up of three layers, including a convolutional layer, a pooling layer and a normalization layer. The algorithm was trained and tested using the MRI data from Alzheimer's Disease Neuroimaging Initiative. The data used include the MRI scanning of about 47 AD patients and 34 normal controls. The experiment had shown that the proposed algorithm delivered a high AD recognition accuracy with a sensitivity of 1and a specificity of 0.93.

Application of deep learning in detecting neurological disorders from magnetic resonance images: a survey on the detection of Alzheimer’s disease, Parkinson’s disease and schizophrenia

“…In modern MRI scanners, these variations are tenuous enough that makes it difficult to detect. A solution to this approach comprises the usage of the convex accretion with an insistent method to enhance B1 uniformity in an anatomic region of interest (ROI) by differing the enormity and phase of every RF channel element separately [40][41][42]. A correction for nonlinearities in the gradients are applied by the scanner, called gradwarp.…”

“…A correction for nonlinearities in the gradients are applied by the scanner, called gradwarp. This correction tends to make the images spatially more accurate [41]. Large variance in the human brain's response to substantial field inhomogeneity results in image distortion.…”

“…Because the inhomogeneity field is slowly differing, it is a common practice to assume a smooth histogram. The N3 bias correction method is mostly used for that which is an iterative method that seeks the smooth multiplicative field maximizing the high-frequency content of the distribution of tissue intensity [41].…”

“…Luo et al provided an automatic AD detection algorithm using CNN on 3D brain MRI in which the 3D topology of the whole brain is considered [41]. The CNN architecture consists of three consecutive groups of processing layers, two fully connected layers, and a classification layer.…”

Analysis of Alzheimer’s Disease Based on the Random Neural Network Cluster in fMRI

“… Ortiz et al (2013) used Learning Vector Quantization (LVQ) algorithm to classify AD patients from HC, and the accuracy was close to 90%. Luo et al (2017) applied CNN to classify AD patients from HC, and the sensitivity and specificity of classification was 1 and 0.93 respectively. Suk et al (2014) used deep learning to classify AD patients from HC, and the accuracy was close to 93.35%.…”