Our Group organises 3000+ Global Events every year across USA, Europe & Asia with support from 1000 more scientific Societies and Publishes 700+ 51黑料吃瓜网 Journals which contains over 50000 eminent personalities, reputed scientists as editorial board members.
Alzheimer's disease is the most common type of dementia which it has no cure nor imaging test for it. Diagnosis of the
Alzheimer芒�?�?s disease (AD) still a challenge and difficult. An early diagnosis for Alzheimer芒�?�?s disease is very important to
delay the progression of it. This paper extract and analyze various important features of 3D-MRI brain medical images to
provide better analysis and diagnosis of AD. These extracted features had been used for detection of the abnormalities among
different demented and non-demented MRI AD images. This paper deals with the statistical analysis to discriminate among
the different types of tissue. Also, it investigates and building up an efficient Computer Aided Diagnosis (CAD) system for
AD to assist the medical doctors to easily diagnose the disease. Statistical, structural, and textural features had been extracted
for different images. These extracted features had been used as an input to the SVM classifier. In addition, all these features
had been applied to the proposed algorithm and then had been classified using SVM classifier. The performance of the CAD
system based on statistical analysis and the proposed algorithm had been measured using different metric parameters. Also,
the proposed algorithm had been applied to the images with intensity level. The obtained results indicate that the metric
parameters increase from 60% without using the proposed algorithm to 100% using the proposed algorithm.
Alzheimer芒�?�?s disease is a degenerative brain disease and the most common cause of dementia. The most common initial
symptom is a gradually worsening ability to remember new information, planning or solving problems, completing familiar
tasks at home or work, Confusion with time or place, and problems with words in speaking or writing. Alzheimer芒�?�?s disease is
a progressive disease, which means that it gets worse over time. There is no cure, specific blood or imaging test for Alzheimer's
disease. However, some drugs are available which may help slow the progression of Alzheimer's symptoms for a limited time.
Diagnosis of the Alzheimer芒�?�?s disease (AD) still a challenge and difficult, especially in the early stages. The early detection
will be key to prevent, slow and stop Alzheimer芒�?�?s disease. The last 10 years have seen a tremendous growth in research on
early detection. Statistical analysis method is one of the important methods for feature extraction in digital images. There are
different previous approaches that depends on extracting statistical, textural, and structural features from digital images in
different application.
The statistical analysis of 3D and 2D images of AD had been presented in this paper. Different important statistical,
structural and textural features that had been extracted from different AD MRI images (normal, very mild AD and mild AD).
The 3D images had been analyzed in three plans and the features had been extracted from each plane. Studying and analyzing
these extracted features may help the medical doctors to diagnose the Alzheimer芒�?�?s disease.
This paper presents the proposed algorithm which consists of six stages. These stages are:
1. Preprocessing and Normalization for the input images.
2. 3D or 2D image to 1D signal conversion.
3. Proposed feature selection method.
4. Proposed feature extraction method.
5. Cross-validation
6. Feature matching or Classification process using SVM.
The obtained results represent different extracted features from normal, very mild and mild 3D MRI images. The features
had been extracted from the images planes (X-Y, X-Z, and Y-Z). The number of pixels used for calculation was very large
this leads to high values for each feature. By studying the three difference types of extracted statistical, structural and textural
features it is noted that, the values of these different extracted features for normal, very mild and mild stages may help the
medical doctors to diagnose the Alzheimer芒�?�?s disease. The results concluded as follows:
1. The SVM classifier had been used to classify the statistical features of the images into two classes (normal and patient). The
obtained values of the metric parameters were about 60%.
2. The proposed algorithm had been applied to the extracted statistical features before performing the classification step
using the SVM. The obtained results of the metric parameters values improved to 70%.
3. The proposed algorithm had been applied to the 2D images with only intensity level of the images. The obtained results of
the values of the metric parameters improved to 100% using number of extracted features equal to 500 features.
Finally, the trends of this paper for the Alzheimer芒�?�?s disease is to build up a CAD system used to assist the medical doctors
to easly diagnosis it without the need to ask about the symptoms, do physical examinations, check neurological functions, or
ask about blood tests and urine samples.
