Applying convolutional neural networks for pre-detection of alzheimer's disease from structural MRI data

Gunawardena, K. A. N. N. P; Rajapakse, Roshan N.; Kodikara, Nihal

doi:10.1109/m2vip.2017.8211486

Cited by 72 publications

(51 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The network utilizes an MRI scan as input and removes layer intelligence element representation from the first to the final exit layer. [3] This study consists of two main tests. They therefore validated an existing and highly effective method of acquiring Support Vector Machine (SVMs) as an initial trial.…”

Section: Background Study and Related Workmentioning

confidence: 99%

Deep Learning techniques for effective diagnosis of Alzheimer's disease using MRI images

et al. 2021

View full text Add to dashboard Cite

The determination of Alzheimer’s disease (AD) from neuroimaging data such as MRI has been immensely researched over the last few years. Recent advances in deep learning from a computer perspective have advanced in that research. However, the general limitations of such algorithms depend on the large number of training images, as well as the need to carefully perform the construction of deep networks. In past few days deep learning strategies have found great achievement in the analysis of medical imaging. But very little has been done in the use of deep learning strategies to turn up and differentiate Alzheimer’s disease. We are building a deep convolutional network and demonstrating performance on the ADNI-Alzheimer’s Disease Neuroimaging Initiative Dataset. We present a deep convolutional neural network to recognize Alzheimer and differentiate according the current phase of the disease.

show abstract

Section: Background Study and Related Workmentioning

confidence: 99%

Deep Learning techniques for effective diagnosis of Alzheimer's disease using MRI images

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The dataset is taken from the Kaggle website. The data set, consisting of 6400 brain tomography scans, consists of normal people, people with moderate Alzheimer's disease, and people with severe Alzheimer's disease (12). In this study, we divided the brain tomography of a person into four classes as i) normal tomography (have no Alzheimer's disease), ii) mild disease, iii) moderate disease, iv) high-grade disease.…”

Section: Datasetmentioning

confidence: 99%

Automated Detection of Alzheimer's Disease Using Wavelet Transform with Convolutional Neural Networks

OLABI¹,

Yilmaz²,

Aslan³

2020

EJOH

View full text Add to dashboard Cite

Objective: Alzheimer's disease (AD) is a chronic disease that causes the death of nerve cells and tissue loss in the brain. It usually starts slowly and worsens over time. Individual computer aided systems are needed for early and accurate diagnosis of Alzheimer's. Magnetic resonance imaging (MRI) offers the opportunity to examine the pathological brain changes associated with AD. In recent years, neuroimaging data has been increasingly used to characterize AD with machine learning methods, offering promising tools for personalized diagnosis. Very recently, a number of studies have proposed to aid the diagnosis of AD through convolutional neural networks (CNNs).Methods: CNN is machine learning algorithm which is used in a variety of fields, including image and pattern recognition, speech recognition, natural language processing, and video analysis. In this study Discrete wavelet transform (DWT) was used for feature extraction. DWT has attractive properties and has better image representation than other transforms like Fourier. Medical images are vulnerable to noise, they are preprocessed to remove unwanted data and improve quality. Feature extraction and classification are two essential components for the recognition system that have a significant impact on the efficiency of the system. DWT is an implementation of wavelet transform that uses a separate set of wavelet scales and translations that follow some defined rules. The aim of this study is to detect Alzheimer's disease by using convolutional neural networks and to reduce noise by preprocessing by applying DWT on the entered images.Results: With combining DWT feature extraction and CNN algorithm for detecting Alzheimer's disease, the performance and learning rate are significantly decreased. The accuracy of the model results based on pure CNN with machine learning algorithm is higher than with than the accuracy in CNN learning without DWT future extraction. Accuracy values are 75% and 69 % successively. Conclusion:Ultimately, this study revealed that the combination of MET-PLGA NPs with current cancer therapies holds promise for the potential of breast cancer treatment.

show abstract

“…For example various uses of CNNs for Magnetic Resonance Imaging (MRI) segmentation are presented in (9). CNNs are used for several applications Different groups have tried utilizing CNNs (10,11) to analyze and separate AD from healthy or no condition (NC), patients using MRI scans as an input, while others have utilized a special type of MRI scan technique-the functional magnetic resonance imaging (fMRI) time-series information (12,13). An investigation was performed by Thompson et al (14) in this regard in a paper titled, "Applying Convolutional Neural Networks for pre-detection of AD from structural MRI data."…”

Section: Introductionmentioning

confidence: 99%

A Predictive and Preventive Model for Onset of Alzheimer's Disease

Singhania

Tripathy

Hasan

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

Alzheimer's Disease (AD) is a neurodegenerative irreversible brain disorder that gradually wipes out the memory, thinking skills and eventually the ability to carry out day-to-day tasks. The amount of AD patients is rapidly increasing due to several lifestyle changes that affect biological functions. Detection of AD at its early stages helps in the treatment of patients. In this paper, a predictive and preventive model that uses biomarkers such as the amyloid-beta protein is proposed to detect, predict, and prevent AD onset. A Convolution Neural Network (CNN) based model is developed to predict AD at its early stages. The results obtained proved that the proposed model outperforms the traditional Machine Learning (ML) algorithms such as Logistic Regression, Support Vector Machine, Decision Tree Classifier, and K Nearest Neighbor algorithms.

show abstract

Applying convolutional neural networks for pre-detection of alzheimer's disease from structural MRI data

Cited by 72 publications

References 12 publications

Deep Learning techniques for effective diagnosis of Alzheimer's disease using MRI images

Deep Learning techniques for effective diagnosis of Alzheimer's disease using MRI images

Automated Detection of Alzheimer's Disease Using Wavelet Transform with Convolutional Neural Networks

A Predictive and Preventive Model for Onset of Alzheimer's Disease

Contact Info

Product

Resources

About