Predicting Alzheimer's disease by classifying 3D-Brain MRI images using SVM and other well-defined classifiers

Matoug, Sofia; Abdel-Dayem, Amr R.; Passi, Kalpdrum; Gross, Wolfgang L.; Alqarni, Mohammed

doi:10.1088/1742-6596/341/1/012019

Cited by 7 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This algorithm is structured on the theory of statistical learning, which helps in improving the general aptitude of machines to learn unseen data [ 26 ]. Recently, SVMs are widely used in many real-life applications, such as object detection [ 27 ], face identification in images [ 28 ], hand written alphabets recognition [ 29 ], and brain images abnormalities classification [ 15 , 16 , 30 ]. SVM classification is highly accurate and having elegant mathematical tractability than other classification techniques, like artificial neural networks, Bayesian networks, and decision tree.…”

Section: Methodsmentioning

confidence: 99%

An Automated and Intelligent Medical Decision Support System for Brain MRI Scans Classification

2015

View full text Add to dashboard Cite

A wide interest has been observed in the medical health care applications that interpret neuroimaging scans by machine learning systems. This research proposes an intelligent, automatic, accurate, and robust classification technique to classify the human brain magnetic resonance image (MRI) as normal or abnormal, to cater down the human error during identifying the diseases in brain MRIs. In this study, fast discrete wavelet transform (DWT), principal component analysis (PCA), and least squares support vector machine (LS-SVM) are used as basic components. Firstly, fast DWT is employed to extract the salient features of brain MRI, followed by PCA, which reduces the dimensions of the features. These reduced feature vectors also shrink the memory storage consumption by 99.5%. At last, an advanced classification technique based on LS-SVM is applied to brain MR image classification using reduced features. For improving the efficiency, LS-SVM is used with non-linear radial basis function (RBF) kernel. The proposed algorithm intelligently determines the optimized values of the hyper-parameters of the RBF kernel and also applied k-fold stratified cross validation to enhance the generalization of the system. The method was tested by 340 patients’ benchmark datasets of T1-weighted and T2-weighted scans. From the analysis of experimental results and performance comparisons, it is observed that the proposed medical decision support system outperformed all other modern classifiers and achieves 100% accuracy rate (specificity/sensitivity 100%/100%). Furthermore, in terms of computation time, the proposed technique is significantly faster than the recent well-known methods, and it improves the efficiency by 71%, 3%, and 4% on feature extraction stage, feature reduction stage, and classification stage, respectively. These results indicate that the proposed well-trained machine learning system has the potential to make accurate predictions about brain abnormalities from the individual subjects, therefore, it can be used as a significant tool in clinical practice.

show abstract

Section: Methodsmentioning

confidence: 99%

An Automated and Intelligent Medical Decision Support System for Brain MRI Scans Classification

2015

View full text Add to dashboard Cite

show abstract

“…It classifies with an accuracy of 90.3% with all the attributes. The result of DNN shows that the better performance compare to SVM as reported on [7] and the accuracy of DNN and backpropagation algorithm report in [14] [15] are comparable but the error rate is reduced in case of DNN. Therefore, it can be assumed that deep learning algorithms are more beneficial when dealing with learning from large amounts of unsupervised data.…”

Section: Resultsmentioning

confidence: 77%

“…The resulting attributes are respectively the surface area of the extracted region, the perimeter, Mean, Standard deviation, 28 horizontal distances (D1, D2, …, D28), the Height and the coordinates of the centre of gravity of the region (Gx, Gy). The attributes are normalized into the range (0, 1) [7].…”

Section: B Attribute Selectionmentioning

confidence: 99%

“…[6] [7]. Medical image processing and machine learning tools can help neurologists in assessing whether a subject is developing the Alzheimer disease.…”

Section: Introductionmentioning

confidence: 99%

“…Neuroimaging, such as magnetic resonance imaging (MRI) or computed tomography (CT) and with single photon emission computed tomography (SPECT) or positron emission tomography (PET) can be used to help exclude other cerebral pathology or subtypes of dementia. It may predict conversion from prodromal to Alzheimer"s disease.[6] [7]. Medical image processing and machine learning tools can help neurologists in assessing whether a subject is developing the Alzheimer disease.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Deep Neural Network Classification method to Alzheimer?s Disease Detection

Gulhare

Shukla²,

Sharma

2017

IJARCSSE

View full text Add to dashboard Cite

Abstract-Early detection of Alzheimer disease (AD) is important for the management of disease. The human brainMagnetic resonance imaging (MRI) data have been used to detection of Alzheimer disease detection. The detection of AD is quite challenging and thus an automated tool to classify AD can be useful. Deep learning can make major advances in solving such problems. In this study, the longitudinal MRI data in non-demented and demented older adults data is utilized and the image processing technique was adopted for the data segmentation and attribute selection. Finally, deep neural network (DNN) classification is implemented for AD detection. The DNN 96.6% correctly identified AD and the minimum error rate obtained from a DNN. It shows the DNN will be useful for the development of improved computer aided diagnosis tool in MRI data.Keywords-Deep Neural Network, Alzheimer Disease, MRI Images, Classification I. INTRODUCTIONThe dementia is a global issue and that the effects of the future epidemic will be felt predominantly in low and middleincome countries. It was estimated that 46.8 million people worldwide were living with dementia in 2015 and this number will almost double every 20 years, to 87.88 million in 2035, 116.78 million in 2045 and 131.5 million in 2050. It has also a huge economic impact. The worldwide cost of dementia was estimated US$ 817.9 billion in the year of 2015 and it is projected the costs in 2030 will be around US$ 2 trillion [1]. Alzheimer"s disease (AD) is the most common cause of dementia associated with aging [2]; it accounts for 64 percent of all dementias [3]. AD is a growing public health problem among the elderly in developing countries, whose aging population is increasing rapidly [4]. AD is characterized by a progressive decline in cognitive function. AD is substantially increased among people aged 65 years or more, with a progressive decline in memory, thinking, language and learning capacity. AD should be differentiated from normal age-related decline in cognitive function, which is more gradual and associated with less disability. The disease often starts with mild symptoms and ends with severe brain damage. People with dementia lose their abilities at different rates [5]. The detection of AD in early and accurate is beneficial for the management of disease. Neuroimaging, such as magnetic resonance imaging (MRI) or computed tomography (CT) and with single photon emission computed tomography (SPECT) or positron emission tomography (PET) can be used to help exclude other cerebral pathology or subtypes of dementia. It may predict conversion from prodromal to Alzheimer"s disease.[6] [7]. Medical image processing and machine learning tools can help neurologists in assessing whether a subject is developing the Alzheimer disease. The image segmentation and classification is an important task in MRI data analysis for the AD detection. Image segmentation is intended to partition images into well-defined regions, where each region is a set of pixels that share the same range of intensitie...

show abstract

Visualizing Alzheimer's disease progression in low dimensional manifolds

Seo

Pan

Lee

et al. 2019

Heliyon

View full text Add to dashboard Cite

While tomographic neuroimaging data is information rich, objective, and with high sensitivity in the study of brain diseases such as Alzheimer's disease (AD), its direct use in clinical practice and in regulated clinical trial (CT) still has many challenges. Taking CT as an example, unless the relevant policy and the perception of the primary outcome measures change, the need to construct univariate indices (out of the 3-D imaging data) to serve as CT's primary outcome measures will remain the focus of active research. More relevant to this current study, an overall global index that summarizes multiple complicated features from neuroimages should be developed in order to provide high diagnostic accuracy and sensitivity in tracking AD progression over time in clinical setting. Such index should also be practically intuitive and logically explainable to patients and their families. In this research, we propose a new visualization tool, derived from the manifold-based nonlinear dimension reduction of brain MRI features, to track AD progression over time. In specific, we investigate the locally linear embedding (LLE) method using a dataset from Alzheimer's Disease Neuroimaging Initiative (ADNI), which includes the longitudinal MRIs from 562 subjects. About 20% of them progressed to the next stage of dementia. Using only the baseline data of cognitively unimpaired (CU) and AD subjects, LLE reduces the feature dimension to two and a subject's AD progression path can be plotted in this low dimensional LLE feature space. In addition, the likelihood of being categorized to AD is indicated by color. This LLE map is a new data visualization tool that can assist in tracking AD progression over time.

show abstract

Predicting Alzheimer's disease by classifying 3D-Brain MRI images using SVM and other well-defined classifiers

Cited by 7 publications

References 15 publications

An Automated and Intelligent Medical Decision Support System for Brain MRI Scans Classification

An Automated and Intelligent Medical Decision Support System for Brain MRI Scans Classification

Deep Neural Network Classification method to Alzheimer?s Disease Detection

Visualizing Alzheimer's disease progression in low dimensional manifolds

Contact Info

Product

Resources

About