HEBA MOHSEN MOHAMED MOSAAD HUSSIEN

Yasser M. Abd El-Latif

16/09/2022

https://link.springer.com/article/10.1007/s44196-022-00135-z

HEBA MOHSEN MOHAMED MOSAAD HUSSIEN

Sabah Sayed; Akram Salah

26/08/2022

https://ieeexplore.ieee.org/document/9868780?source=authoralert

HEBA MOHSEN MOHAMED MOSAAD HUSSIEN

nehal hamdy al-banhawy

01/12/2020

Handwritten signature identification and verification has become an active area of research in recent years. Handwritten signature identification systems are used for identifying the user among all users enrolled in the system while handwritten signature verification systems are used for authenticating a user by comparing a specific signature with his signature that is stored in the system. This paper presents a review for commonly used methods for pre-processing, feature extraction and classification techniques in signature identification and verification systems, in addition to a comparison between the systems implemented in the literature for identification techniques and verification techniques in online and offline systems with taking into consideration the datasets used and results for each system.

HEBA MOHSEN MOHAMED MOSAAD HUSSIEN

El-Sayed A. El-Dahshan, El-Sayed El-Horbaty, Abdel-Badeeh Salem

01/06/2018

Deep Learning is a new machine learning field that gained a lot of interest over the past few years. It was widely applied to several applications and proven to be a powerful machine learning tool for many of the complex problems. In this paper we used Deep Neural Network classifier which is one of the DL architectures for classifying a dataset of 66 brain MRIs into 4 classes e.g. normal, glioblastoma, sarcoma and metastatic bronchogenic carcinoma tumors. The classifier was combined with the discrete wavelet transform (DWT) the powerful feature extraction tool and principal components analysis (PCA) and the evaluation of the performance was quite good over all the performance measures.

HEBA MOHSEN MOHAMED MOSAAD HUSSIEN

El-Sayed A. El-Dahshan, El-Sayed El-Horbaty, Abdel-Badeeh Salem

01/09/2017

Alzheimer’s disease (AD) is known to be the most common cause of neurodegenerative dementia that affects people over 65 years. It’s an irreversible, progressive brain disorder that slowly destroys memory and thinking skills, and eventually the ability to carry out the simplest tasks and it has no treatment till now expect slowing down its symptoms if it was diagnosed in early stages. The diagnosis of AD includes mental status, physical exam and neurological exam, which is analyzing different imaging techniques such as magnetic resonance images (MRI). And accordingly, AD become a challenging wide area of research in the medical images application that aims to find a reliable methodology that can early detect and differential diagnosis of cognitive normal (CN), mild cognitive impairment (MCI) and AD by examining the brain MRIs. In this work, we proposed a methodology based on Discrete Wavelet Transform (DWT) feature extraction technique and Principal Component Analysis (PCA) for feature vector reduction then these features are entered to linear discriminant analysis (LDA) classifier. The performance of the proposed methodology was evaluated using two datasets obtained from Alzheimer's Disease Neuroimaging Initiative (ADNI) database and Harvard Medical School website. Our methodology achieved 94.59%average classification rate with AUC of ROC = 0.963over Harvard medical school dataset and 77.78% average classification rate with area under the ROC curve (AUC) = 0.809 over ADNI dataset using a 6-fold cross validation.

HEBA MOHSEN MOHAMED MOSAAD HUSSIEN

El-Sayed A. El-Dahshan, El-Sayed El-Horbaty, Abdel-Badeeh Salem

01/06/2017

The objective of this study is to present a computer-aided diagnosis (CAD) system for automatic detection of brain tumors in brain magnetic resonance (MR) images. The proposed system is based on sequential minimal optimization (SMO) algorithm for training Support Vector Machine (SVM) classifier using Weka open source software to classify three different types of malignant brain tumors (i.e., glioblastoma, sarcoma and metastatic bronchogenic carcinoma) on 66 brain MR images. The system composed of three main stages namely: image segmentation, feature extraction and selection and finally, the classification stage. We used the Fuzzy C-means (FCM) and K-means as two techniques for image segmentation and the Gray level co-occurrence matrix (GLCM) and Discrete Wavelet Transform (DWT) followed by Principal Component Analysis (PCA) as two techniques for feature extraction and selection. They form four different models of the CAD system. According to the evaluation of the proposed models of the CAD system, the performance of the FCM and DWT followed by PCA model was promising in terms of the classification rate. The average classification rate for all classes using 7-fold cross-validation was 93.94% with average area under the receiver operating characteristic (ROC) curve of 0.963 and the average classification rate on the training set and the 85% percentage spilt was 100% with average area under the ROC curve of 1.00.

HEBA MOHSEN MOHAMED MOSAAD HUSSIEN

El-Sayed A. El-Dahshan, El-Sayed El-Horbaty, Abdel-Badeeh Salem

01/01/2017

Recently, a lot of researches have been made in the area of automatic detection and diagnosing the brain tumor type based on different medical imaging techniques. This paper presents a new intelligent methodology applying k-means segmentation technique and a hybrid support vector machine (SVM) classifier based on Linear-SVM and Multi-SVM using two feature extraction techniques, namely : Gray level co-occurrence matrix (GLCM) and discrete wavelet transform (DWT) followed by Principle component analysis (PCA) to detect brain tumors in brain magnetic resonance images (MRIs) and differentiate between three types of malignant brain tumors: glioblastoma, sarcoma and metastatic bronchogenic carcinoma. The results of the two feature extraction techniques were compared according to their accuracy, sensitivity and specificity showing good results and high robustness.

HEBA MOHSEN MOHAMED MOSAAD HUSSIEN

El-Sayed A. El-Dahshan, El-Sayed El-Horbaty, Abdel-Badeeh Salem

01/05/2016

Segmentation is a core process for automatic detection and identification of brain tumors as it plays a vital role in extracting the information of the image as measuring and visualizing the brain's anatomical structures and analyzing the brain changes. From this point the need for accurate and automatic segmentation techniques has risen as manual segmentation is not a realistic solution and yet time consuming. This paper examines the various automated segmentation techniques used by researchers on brain magnetic resonance images (MRI), giving the most important features for the most common techniques used in the area of brain tumors. Moreover, a comparative study to address the differences, limitations, advantages and challenges of each technique mentioned when being used on brain MRI to find out their efficiency in this area and to put guidelines that should be considered when using these techniques.

HEBA MOHSEN MOHAMED MOSAAD HUSSIEN

El-Sayed A. El-Dahshan, Kenneth Revett, Abdel-Badeeh Salem

01/09/2014

Computer-aided detection/diagnosis (CAD) systems can enhance the diagnostic capabilities of physicians and reduce the time required for accurate diagnosis. The objective of this paper is to review the recent published segmentation and classification techniques and their state-of-the-art for the human brain magnetic resonance images (MRI). The review reveals the CAD systems of human brain MRI images are still an open problem. In the light of this review we proposed a hybrid intelligent machine learning technique for computer-aided detection system for automatic detection of brain tumor through magnetic resonance images. The proposed technique is based on the following computational methods; the feedback pulse-coupled neural network for image segmentation, the discrete wavelet transform for features extraction, the principal component analysis for reducing the dimensionality of the wavelet coefficients, and the feed forward back-propagation neural network to classify inputs into normal or abnormal. The experiments were carried out on 101 images consisting of 14 normal and 87 abnormal (malignant and benign tumors) from a real human brain MRI dataset. The classification accuracy on both training and test images is 99% which was significantly good. Moreover, the proposed technique demonstrates its effectiveness compared with the other machine learning recently published techniques. The results revealed that the proposed hybrid approach is accurate and fast and robust. Finally, possible future directions are suggested.

HEBA MOHSEN MOHAMED MOSAAD HUSSIEN

El-Sayed A. El-Dahshan, Abdel-Badeeh Salem

01/05/2012

This study presents a proposed hybrid intelligent machine learning technique for Computer-Aided detection system for automatic detection of brain tumor through magnetic resonance images. The technique is based on the following computational methods; the feedback pulse-coupled neural network for image segmentation, the discrete wavelet transform for features extraction, the principal component analysis for reducing the dimensionality of the wavelet coefficients, and the feed forward backpropagation neural network to classify inputs into normal or abnormal. The experiments were carried out on 101 images consisting of 14 normal and 87 abnormal (malignant and benign tumors) from a real human brain MRI dataset. The classification accuracy on both training and test images is 99 % which was significantly good. Moreover, The proposed technique demonstrates its effectiveness compared with the other machine learning recently published techniques.

HEBA MOHSEN MOHAMED MOSAAD HUSSIEN

El-Sayed A. El-Dahshan, Abdel-Badeeh Salem,El-Sayed M. El-Horbarty

01/11/2011

Brain tissue classification from Magnetic Resonance Imaging (MRI) is of great importance for research and clinical studies of the normal and diseased human brain. All MRI classification methods are sensitive to overlap in the tissue intensity distributions. Such overlaps are caused by inherent limitations of the image acquisition process, such as noise, intensity non-uniformity, and partial volume effect. Several approaches have been proposed to address this limitation of intensity-based classification. The objective of this paper is to make a comparative study on the recent published classification techniques for the brain magnetic resonance images (MRI). The contribution of this study is to determine the advantages and disadvantages of each technique and develop robust classification technique capable to perform an efficient and automated MRI normal/abnormal brain images classification.