scholarly journals VBM-Based Alzheimer’s Disease Detection from the Region of Interest of T1 MRI with Supportive Gaussian Smoothing and a Bayesian Regularized Neural Network

2021 ◽  
Vol 11 (13) ◽  
pp. 6175
Author(s):  
Bijen Khagi ◽  
Kun Ho Lee ◽  
Kyu Yeong Choi ◽  
Jang Jae Lee ◽  
Goo-Rak Kwon ◽  
...  
Keyword(s):  
Neural Network ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Statistical Parametric Mapping ◽  
Region Of Interest ◽  
Extraction Process ◽  
Dementia Patients ◽  
Mri Features ◽  
Mri Scans ◽  
The Brain

This paper presents an efficient computer-aided diagnosis (CAD) approach for the automatic detection of Alzheimer’s disease in patients’ T1 MRI scans using the voxel-based morphometry (VBM) analysis of the region of interest (ROI) in the brain. The idea is to generate a normal distribution of feature vectors from ROIs then later use for classification via Bayesian regularized neural network (BR-NN). The first dataset consists of the magnetic resonance imaging (MRI) of 74 Alzheimer’s disease (AD), 42 mild cognitive impairment (MCI), and 74 control normal (CN) from the ADNI1 dataset. The other dataset consists of the MRI of 42 Alzheimer’s disease dementia (ADD), 42 normal controls (NCs), and 39 MCI due to AD (mAD) from our GARD2 database. We aim to create a generalized network to distinguish normal individuals (CN/NC) from dementia patients AD/ADD and MCI/mAD. Our performance relies on our feature extraction process and data smoothing process. Here the key process is to generate a Statistical Parametric Mapping (SPM) t-map image from VBM analysis and obtain the region of interest (ROI) that shows the optimistic result after two-sample t-tests for a smaller value of p < 0.001(AD vs. CN). The result was overwhelming for the distinction between AD/ADD and CN/NC, thus validating our idea for discriminative MRI features. Further, we compared our performance with other recent state-of-the-art methods, and it is comparatively better in many cases. We have experimented with two datasets to validate the process. To validate the network generalization, BR-NN is trained from 70% of the ADNI dataset and tested on 30% of the ADNI, 100% of the GARD dataset, and vice versa. Additionally, we identified the brain anatomical ROIs that may be relatively responsible for brain atrophy during the AD diagnosis.

Neuroimaging in Alzheimer’s Disease

2013 ◽  
pp. 427-431 ◽  
Author(s):  
Hidenao Fukuyama
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Posterior Part ◽  
Lewy Body Disease ◽  
New Drugs ◽  
Amyloid Protein ◽  
Dementia Patients ◽  
Positron Emission ◽  
Occipital Lobes ◽  
The Brain

The diagnosis of Alzheimer’s disease (AD) is often based on clinical and pathological data. Positron emission tomography (PET) using the tracer 18F-FDG revealed findings specific to AD-mainly the posterior part of the brain and the association cortices of the parietal and occipital lobes were affected by a reduction in glucose metabolism. Recent advances in the development of tracers for amyloid protein, which is the key protein in the pathogenesis of AD, enables the pattern of deposition of amyloid protein in the brain to be visualized. Various tracers have been introduced to visualize other aspects of AD pathology. Recent clinical interests on dementia have focused on the early detection of AD and variation of Parkinson’s disease, namely dementia with Lewy body disease (DLB), because the earlier the diagnosis, the better the prognosis. The differential diagnosis of mild AD or mild cognitive impairment (MCI) as well as DLB has been studied using PET and MRI as part of the NIH’s Alzheimer disease Neuroimaging initiative (ADNI). At present, many countries are participating in the ADNI, which is yielding promising results. This chapter’s study will improve the development of new drugs for the treatment of dementia patients by enabling the evaluation of the effect and efficacy of those drugs.

scholarly journals Image processing for early detection of Alzheimer’s disease using Iridology

2020 ◽  
Vol 11 (4) ◽  
pp. 5555-5559
Author(s):  
Asuntha A ◽  
Sai Kalyan Reddy R ◽  
Vamshikrishna K ◽  
Premsagar N
Keyword(s):  
Alzheimer’S Disease ◽  
Image Processing ◽  
Alzheimer's Disease ◽  
Memory Loss ◽  
Region Of Interest ◽  
Colour Pattern ◽  
Training Methods ◽  
Iris Image ◽  
Alternative Research ◽  
The Brain

Alzheimer's disease is caused by genetics, personal lifestyle and other environmental factors. It is an irreversible disease that slowly destroys the brain memory cells. There are no specific methods for the detection of Alzheimer's disease. The primary symptoms of Alzheimer's disease are memory loss, difficulty in thinking, a problem in writing and speaking and others. Iridology is alternative research that has gained more popularity in recent years, which studies the alterations of the iris in correspondence with the organs of the human body. The combination of digital image processing with Iridology gives an excellent opportunity to explore and learn about different neuronal diseases, specifically Alzheimer's disease. In this work, MATLAB software is applied to determine the colour, pattern and other factors that show the existence of Alzheimer's disease. The noise in the iris image is removed by the Gaussian filter, followed by histogram analyses and cropping. The Hough circle transform is used to identify the region of interest and to convert the circular iris image into rectangle form. In the training methods, the SVM and CNN classifiers are used to classify whether the person has Alzheimer's disease. Finally, the results are compared with the real-time images.

scholarly journals Early Detection of Alzheimer’s Disease using Convolutional Neural Network Architecture

2021 ◽  
Vol 8 (2) ◽  
pp. 48-57
Author(s):  
Deepthi Kamath ◽  
Misba Firdose Fathima ◽  
Monica K. P ◽  
Kusuma Mohanchandra
Keyword(s):  
Neural Network ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Brain Mri ◽  
Memory Loss ◽  
Neural Network Approach ◽  
The Neural Network ◽  
Mri Scans

Alzheimer's disease is an extremely popular cause of dementia which leads to memory loss, problem-solving and other thinking abilities that are severe enough to interfere with daily life. Detection of Alzheimer’s at a prior stage is crucial as it can prevent significant damage to the patient’s brain. In this paper, a method to detect Alzheimer’s  Disease from Brain MRI images is proposed. The proposed approach extracts shape features and texture of the Hippocampus region from the MRI scans and a Neural Network is used as a Multi-Class Classifier for detection of AD. The proposed approach is implemented and it gives better accuracy as compared to conventional approaches. In this paper, Convolutional Neural Network is the Neural Network approach used for the detection of AD at a prodromal stage.

scholarly journals Multimodal Prediction of Alzheimer's Disease Severity Level Based on Resting-State EEG and Structural MRI

2021 ◽  
Vol 15 ◽  
Author(s):  
Belmir Jesus ◽  
Raymundo Cassani ◽  
William J. McGeown ◽  
Marco Cecchi ◽  
K. C. Fadem ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Disease Severity ◽  
Resting State ◽  
Structural Mri ◽  
Rate Of Change ◽  
Machine Learning Algorithms ◽  
Mri Features ◽  
Mri Scans ◽  
Eeg Features

While several biomarkers have been developed for the detection of Alzheimer's disease (AD), not many are available for the prediction of disease severity, particularly for patients in the mild stages of AD. In this paper, we explore the multimodal prediction of Mini-Mental State Examination (MMSE) scores using resting-state electroencephalography (EEG) and structural magnetic resonance imaging (MRI) scans. Analyses were carried out on a dataset comprised of EEG and MRI data collected from 89 patients diagnosed with minimal-mild AD. Three feature selection algorithms were assessed alongside four machine learning algorithms. Results showed that while MRI features alone outperformed EEG features, when both modalities were combined, improved results were achieved. The top-selected EEG features conveyed information about amplitude modulation rate-of-change, whereas top-MRI features comprised information about cortical area and white matter volume. Overall, a root mean square error between predicted MMSE values and true MMSE scores of 1.682 was achieved with a multimodal system and a random forest regression model.

scholarly journals Differential Diagnosis of Alzheimer's Disease and Mild Cognitive Impairment Using the Structural and Diffusion MRI Features of the Brain

2021 ◽  
Author(s):  
Seyed Amir Zamanpour ◽  
Bahare Bigham ◽  
Mohamad-Hoseyn Sigari ◽  
Hoda Zare
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Diffusion Mri ◽  
Support Vector ◽  
Treatment And Prevention ◽  
Mri Features ◽  
The Brain ◽  
And Diffusion

Abstract Introduction: Accurate, fast, and reliable diagnosis of Alzheimer's Disease (AD) from Mild Cognitive Impairment (MCI) is crucial for prescribing proper treatment and prevention of disease progression. At first glance, structural and diffusion MRI images, are affected by neurodegenerative proceedings in AD and MCI. In this study, we are looking for the most effective features to detect and differentiate between healthy normal control (NC), AD, and MCI groups by non-invasive Magnetic Resonance Imaging (MRI) method and propose the automatic multi-class classification using the structural and diffusion MRI Features of the brain. Methods: The structural and diffusion MRI data were downloaded from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database on three groups including AD, MCI, and NC subjects. Four famous classification models of machine learning were used to discover the best classification as a diagnostic tool for separation of the NC, AD and MCI groups. Results: Taken together, our results from this study lead to classify three groups for differentiation between the NC group and patients with MCI and AD, with average accuracy factor 89.9% for Support Vector Machine (SVM) and 91.9% for Artificial Neural Network (ANN) using selected features. Conclusions: Top 9 regions repetitive of WM based on four types of features are the caudate nucleus, corpus callosum, hippocampus, para hippocampus, temporal gyrus, putamen nucleus, cingulate gyrus, the region of 36 and 3 Brodmann. Therefore, these regions could be considered for identifying, monitoring, and future drug trials that could target this brain region to AD and MCI Management.

scholarly journals Diagnosis of Alzheimer Disease Using 2D MRI Slices by Convolutional Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Fanar E. K. Al-Khuzaie ◽  
Oguz Bayat ◽  
Adil D. Duru
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Magnetic Resonance ◽  
Convolutional Neural Network ◽  
Dropout Rate ◽  
Resonance Imaging ◽  
Data Set ◽  
The Brain

There are many kinds of brain abnormalities that cause changes in different parts of the brain. Alzheimer’s disease is a chronic condition that degenerates the cells of the brain leading to memory asthenia. Cognitive mental troubles such as forgetfulness and confusion are one of the most important features of Alzheimer’s patients. In the literature, several image processing techniques, as well as machine learning strategies, were introduced for the diagnosis of the disease. This study is aimed at recognizing the presence of Alzheimer’s disease based on the magnetic resonance imaging of the brain. We adopted a deep learning methodology for the discrimination between Alzheimer’s patients and healthy patients from 2D anatomical slices collected using magnetic resonance imaging. Most of the previous researches were based on the implementation of a 3D convolutional neural network, whereas we incorporated the usage of 2D slices as input to the convolutional neural network. The data set of this research was obtained from the OASIS website. We trained the convolutional neural network structure using the 2D slices to exhibit the deep network weightings that we named as the Alzheimer Network (AlzNet). The accuracy of our enhanced network was 99.30%. This work investigated the effects of many parameters on AlzNet, such as the number of layers, number of filters, and dropout rate. The results were interesting after using many performance metrics for evaluating the proposed AlzNet.

scholarly journals Alzheimer’s Disease: Classification and Detection using MRI Dataset

2021 ◽  
Vol 10 (5) ◽  
pp. 70-72
Author(s):  
V P Suhaira ◽  
Sita S ◽  
Joby George
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Heart Function ◽  
Brain Mri ◽  
Memory Loss ◽  
Disease Classification ◽  
Data Set ◽  
Mri Scans ◽  
Disease Experience ◽  
The Brain

Alzheimer's disease (AD) is a hereditary brain condition that is incurable and progresses over time. Patients with Alzheimer's disease experience memory loss, uncertainty, and difficulty speaking, reading, and writing as a result of this condition. Alzheimer's disease eventually affects the portion of the brain that controls breathing and heart function, leading to death. This framework proposes the OASIS (Open Access Series of Imaging Studies) dataset, which contains the existing MRI data set, which is comprised of a longitudinal sample of 150 subjects aged 60 to 96 who were all acquired on the same scanner using similar sequences. This paper uses a combination of brain MRI scans and psychological parameters to predict disease with high accuracy using various classifier algorithms, and the results can be compared to improve performance.

scholarly journals Identification of Alzheimer's disease using a convolutional neural network model based on T1-weighted magnetic resonance imaging

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Jong Bin Bae ◽  
Subin Lee ◽  
Wonmo Jung ◽  
Sejin Park ◽  
Weonjin Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Magnetic Resonance ◽  
Convolutional Neural Network ◽  
Medial Temporal Lobe ◽  
Processing Time ◽  
Resonance Imaging ◽  
Mri Scans

AbstractThe classification of Alzheimer’s disease (AD) using deep learning methods has shown promising results, but successful application in clinical settings requires a combination of high accuracy, short processing time, and generalizability to various populations. In this study, we developed a convolutional neural network (CNN)-based AD classification algorithm using magnetic resonance imaging (MRI) scans from AD patients and age/gender-matched cognitively normal controls from two populations that differ in ethnicity and education level. These populations come from the Seoul National University Bundang Hospital (SNUBH) and Alzheimer’s Disease Neuroimaging Initiative (ADNI). For each population, we trained CNNs on five subsets using coronal slices of T1-weighted images that cover the medial temporal lobe. We evaluated the models on validation subsets from both the same population (within-dataset validation) and other population (between-dataset validation). Our models achieved average areas under the curves of 0.91–0.94 for within-dataset validation and 0.88–0.89 for between-dataset validation. The mean processing time per person was 23–24 s. The within-dataset and between-dataset performances were comparable between the ADNI-derived and SNUBH-derived models. These results demonstrate the generalizability of our models to different patients with different ethnicities and education levels, as well as their potential for deployment as fast and accurate diagnostic support tools for AD.

Deep-Learning-Based Classification and Diagnosis of Alzheimer's Disease

2020 ◽  
pp. 1358-1382
Author(s):  
Rekh Ram Janghel
Keyword(s):  
Neural Network ◽  
Alzheimer’S Disease ◽  
Neural Networks ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Magnetic Resonance Image ◽  
Cross Validation ◽  
Convolution Neural Network ◽  
Learning Networks ◽  
Mri Scans

Alzheimer's is the most common form of dementia in India and it is one of the leading causes of death in the world. Currently it is diagnosed by calculating the MSME score and by manual study of MRI scan. In this chapter, the authors develop and compare different methods to diagnose and predict Alzheimer's disease by processing structural magnetic resonance image scans (MRI scans) with deep learning neural networks. The authors implement one model of deep-learning networks which are convolution neural network (CNN). They use four different architectures of CNN, namely Lenet-5, AlexNet, ZFNet, and R-CNN architecture. The best accuracies for 75-25 cross validation and 90-10 cross validation are 97.68% and 98.75%, respectively, and achieved by ZFNet architecture of convolution neural network. This research will help in further studies on improving the accuracy of Alzheimer's diagnosis and prediction using neural networks.

Sign in / Sign up

Export Citation Format

Share Document