T.E. Taha

Automated detection of diabetic retinopathy in blurred digital fundus images

Diabetic retinopathy (DR) is a condition where the retina is damaged due to fluid leaking from the blood vessels into the retina. In extreme cases, the patient will become blind. Therefore, early detection of diabetic retinopathy is crucial to prevent blindness. The main stages of diabetic retinopathy are non-proliferate diabetes retinopathy (NPDR) and proliferate diabetes retinopathy (PDR). In this study, we propose a system for automated classification of normal, and abnormal retinal images by automatically detecting the blood vessels, hard exudates microaneurysms, entropy and homogeneity. The objective measurements such as blood vessels area, exudates area, microaneurysms area, entropy and homogeneity are computed from the processed retinal images. These objective measurements are finally fed to the artificial neural network (ANN) classifier for the automatic classification. Different approaches for image restoration are tested and compared on Fundus images. The effect of restoration on the automatic detection process is investigated in this paper.

K2. Automatic pectoral muscle boundary detection in mammograms using eigenvectors segmentation

Mammograms are X-ray images, which are used in breast cancer detection. Automatic pectoral muscle removal on Medio-Lateral Oblique-view (MLO) of mammograms is an essential step for many mammography processing algorithms. Presence of pectoral muscle gives false positive results in automated breast cancer detection. The sizes, the shapes and the intensity contrasts of pectoral muscles change greatly from one MLO view to another. So, the suppression or exclusion of the pectoral muscle from the mammograms is demanded for computer-aided analysis, and this task requires the identification of the pectoral muscle. The main objective of this study is to propose an automated method to efficiently identify the pectoral muscle in MLO mammograms. This work uses a normalized graph cuts segmentation technique for identifying the pectoral muscle edge.

Characterization of the surface impedance of a superconducting thin film with application to propagation characteristics of surface acoustic waves

In this paper, an algorithm suitable for the computer aided design (CAD) has been developed to estimate and model the main characteristic parameters of superconducting thin films. The detailed parameters of the superconducting thin film such as the surface impedance are described with the aid of the two-fluid model. An impedance function that varies with the temperature and frequency has been obtained. The attenuation constant has been also computed and presented. The obtained results show that, within a certain range of temperature, the surface impedance exhibits a negative real part. This negative resistance phenomenon is indicative of amplification which may occur if the superconducting thin film is embedded in a proper microwave circuit. It can be seen that, the attenuation strongly depends on the frequency and the dispersion-less behavior of the superconducting thin film can be observed. As an application, the obtained surface impedance of a high Tc superconducting thin film can be used to study the propagation characteristics of a surface acoustic wave (SAW). As a result of low loss and hence negative part, the implementation of high gain surface acoustic wave amplifier becomes possible. The computer simulation results are verified by comparison with results using the surface impedance formula of Mattis-Bardeen theory and show a good agreement.

Comparative study between different denoising filters for speckle noise reduction in ultrasonic b-mode images

Image denoising involves processing of the image data to produce a visually high quality image. The denoising algorithms may be classified into two categories, spatial filtering algorithms and transform domain algorithms. In this paper a comparative study between different denoising filters for speckle noise reduction in ultrasonic b-mode images based on calculating the Peak Signal to Noise Ratio (PSNR) value as a metric is presented.

Computer-Aided Diagnosis System for Alzheimer’s Disease Using Different Discrete Transform Techniques

The different discrete transform techniques such as discrete cosine transform (DCT), discrete sine transform (DST), discrete wavelet transform (DWT), and mel-scale frequency cepstral coefficients (MFCCs) are powerful feature extraction techniques. This article presents a proposed computer-aided diagnosis (CAD) system for extracting the most effective and significant features of Alzheimer’s disease (AD) using these different discrete transform techniques and MFCC techniques. Linear support vector machine has been used as a classifier in this article. Experimental results conclude that the proposed CAD system using MFCC technique for AD recognition has a great improvement for the system performance with small number of significant extracted features, as compared with the CAD system based on DCT, DST, DWT, and the hybrid combination methods of the different transform techniques.

A computer simulation of the switching effect in superconducting SAW delay lines

A novel concept for the interaction between a surface acoustic wave (SAW) and a superconducting thin film deposited on the surface of a piezoelectric substrate is presented. The thin film superconductor complex conductivity is described with the aid of the two-fluid model. The effects of the superconductor complex conductivity on the propagation characteristics of the SAW are given. The obtained results show that the attenuation of the SAW is proportional to the resistivity of the thin film even through the superconductor transitions. It is found that there is an abrupt jump in the SAW attenuation and velocity at the critical conductivity which can be used as an on/off switching mechanism in SAW delay lines. Our simulation results give good agreement with published experimental data. The SAW attenuation and velocity measurements can be used as a useful technique in superconductor characterization.

Computer Aided Diagnosis System Feature Extraction of Alzheimer Disease Using MFCC

Mel-Scale Frequency Cepstral Coefficients (MFCC) is very efficient technique for feature extraction. This paper proposes a Computer Aided Diagnosis (CAD) system for extracting the most effective and significant features of Alzheimer Disease (AD) using MFCC technique for the 3-D MRI images. Classification is performed using Linear Support Vector Machine (SVM). Experimental results represent that the proposed CAD system using MFCC for AD recognition give excellent accuracy with small number of significant extracted features which reduces the memory size and simplify the hardware implementation of the CAD system. The proposed approach have better performance and stability.

K9. Automatic Segmentation of Digital Mammograms to Detect Masses

Mammography is a well-known method for detection of breast tumors. Early detection and removal of the primary tumor is an essential and effective method to enhance survival rate and reduce mortality. Breast tumor segmentation is needed for monitoring and quantifying breast cancer. However, automated tumor segmentation in mammograms poses many challenges considering the characteristics of images. In this paper, we propose a fully automatic algorithm for segmentation of breast masses, using two types of image segmentation; normalized graph cuts to delineate pectoral muscle, and then optimal thresholding based on the two-dimensional entropy for mass detection.

Characterization of the surface impedance of a superconducting thin film

In this paper,an algorithm suitable for the computer aided design (CAD) has been developed to estimate and model the main characteristic parameters of superconducting thin films. The detailed parameters of the superconducting thin film such that the surface impedance is described with the aid of the two-fluid model. An impedance function that varies with the temperature and frequency has been obtained. The attenuation constant has been computed and presented. The obtained results show that, within a certain range of temperature, the surface impedance exhibits negative real part. This negative resistance phenomenon is indicative of amplification which may occur if the superconducting thin film is embedded in a proper microwave circuit. It can be seen that the attenuation strongly depends on the frequency. The computer simulation results are verified by comparison with results using surface impedance formula of Mattis-Bardeen theory and show good agreement.

Nuclear reactors safety core parameters prediction using Artificial Neural Networks

The present work investigates an appropriate algorithm based on Multilayer Perceptron Neural Network (MPNN), Apriori association rules and Particle Swarm Optimization (PSO) models for predicting two significant core safety parameters; the multiplication factor Keff and the power peaking factor Pmax of the benchmark 10 MW IAEA LEU research reactor. It provides a comprehensive analytic method for establishing an Artificial Neural Network (ANN) with self-organizing architecture by finding an optimal number of hidden layers and their neurons, a less number of effective features of data set and the most appropriate topology for internal connections. The performance of the proposed algorithm is evaluated using the 2-Dimensional neutronic diffusion code MUDICO-2D to obtain the data required for the training of the neural networks. Experimental results demonstrate the effectiveness and the notability of the proposed algorithm comparing with Trainlm-LM, quasi-Newton (Trainbfg-BFGS), and Resilient Propagation (trainrp-RPROP) algorithms.