Mohamed Abdel-Nasser

Analysis of tissue abnormality and breast density in mammographic images using a uniform local directional pattern

We propose a simple and robust local descriptor of breast tissues in mammograms called ULDP.ULDP is evaluated in the task of mass/normal breast tissue classification.ULDP is evaluated in the task of breast tissue density classification.The results are comparable to the state-of-the-art methods on two databases. This paper proposes a computer-aided diagnosis system to analyze breast tissues in mammograms, which performs two main tasks: breast tissue classification within a region of interest (ROI; mass or normal) and breast density classification. The proposed system consists of three steps: segmentation of the ROI, feature extraction and classification. Although many feature extraction methods have been used to characterize breast tissues, the literature shows no consensus on the optimal feature set for breast tissue characterization. Specifically, mass detection on dense breast tissues is still a challenge. In the feature extraction step, we propose a simple and robust local descriptor for breast tissues in mammograms, called uniform local directional pattern (ULDP). This descriptor can discriminate between different tissues in mammograms, yielding a significant improvement in the analysis of breast cancer. Classifiers based on support vector machines show a performance comparable to the state-of-the-art methods.

Breast tumor classification in ultrasound images using texture analysis and super-resolution methods

Ultrasound images can be used to detect tumors that do not appear in the mammograms of dense breasts. Several computer-aided diagnosis (CAD) systems based on this type of images have been proposed to detect tumors and discriminate between benign and malignant ones. To characterize those lesions, many of the aforementioned systems rely on texture analysis methods. However, speckle noise and artifacts that appear in ultrasound images may degrade their performance. To tackle this problem, and contrary to the state-of-the-art methods that utilize a single image of the breast, this paper proposes the use of a super-resolution approach that exploits the complementary information provided by multiple images of the same target. The proposed CAD system consists of four stages: super-resolution computation, extraction of the region of interest, feature extraction and classification. We have evaluated the performance of five texture methods with the proposed CAD system: gray level co-occurrence matrix features, local binary patterns, phase congruency-based local binary pattern, histogram of oriented gradients and pattern lacunarity spectrum. We show that our super-resolution-based approach improves the performance of the evaluated texture methods and thus outperforms the state of the art in benign/malignant tumor classification. Graphical abstractDisplay Omitted HighlightsWe propose a new breast tumor classification approach in ultrasound images.We propose the use of a super-resolution approach to improve texture methods.Several texture methods have been evaluated in this paper.

Temporal mammogram image registration using optimized curvilinear coordinates

Registration of mammograms plays an important role in breast cancer computer-aided diagnosis systems. Radiologists usually compare mammogram images in order to detect abnormalities. The comparison of mammograms requires a registration between them. A temporal mammogram registration method is proposed in this paper. It is based on the curvilinear coordinates, which are utilized to cope both with global and local deformations in the breast area. Temporal mammogram pairs are used to validate the proposed method. After registration, the similarity between the mammograms is maximized, and the distance between manually defined landmarks is decreased. In addition, a thorough comparison with the state-of-the-art mammogram registration methods is performed to show its effectiveness.

Impacts of GERD on the Accumulated Sediment in Lake Nubia Using Machine Learning and GIS Techniques

This chapter aims to study and discuss the effect (hypothesis) of constructing the GERD on the deposited sediment amount in the AHDL. To achieve the objective of this chapter; a machine learning approach represented in a regression tree (RTs) model was used and calibrated to simulate the changes in bed levels and water velocities in the study area within AHDL by using the field measured data and GIS analysis for the year 2008 (reference case). Furthermore, a model verification process has been done to ensure the applicability of the applied model using the available field data in the year 2012. The results of the bed levels and velocities during calibration and verification of the model show low values of RMSE % (for calibration 2.90 and 2.57 for bed levels and velocities, respectively, and for calibration 4.66 and 4.98% for bed levels and velocities, respectively) and high R2 (for calibration 0.9975 and 0.9978 for bed levels and velocities, respectively, and for verification 0.9921 and 0.9959 for bed levels and velocities, respectively), indicating that the model was efficiently calibrated and verified. It shows good agreement between the simulated and measured data (by comparisons of simulated longitudinal and cross sections with the measured ones). Thus, this model is considered trustful and reliable to the prediction of sediment and erosion (bed changes) in the study area within AHDL after GERD construction. Accordingly, four of the possible scenarios are performed through the well-calibrated and verified model by reducing the flow quantity and its associated annual sediment rate by 5–10 and 60–65%, respectively. These scenarios are considered as prediction cases after GERD construction. The impact of GERD construction is then studied by comparing some sections along and across the studied lake portion before and after GERD construction (applied scenarios). This impact appeared clearly as a reduction in the amount of the accumulated sediment (decrease in bed levels) accompanied by an increase in erosion amount. Based on the applied scenarios, results showed that the amount of sediment was reduced by 25–27%, 52–55%, 76–81%, and 90–97% in the year 2030, 2040, 2050, and 2060, respectively, compared to the predicted amount of sediment in the year 2020 without GERD operation/construction. As a positive impact of the GERD construction, the lifetime of the upstream AHD reservoir will be prolonged due to the decrease in the amount of the accumulated sediment. This study provides decision-makers with a preliminary knowledge about the impact of GERD operation/construction on AHDL sediment pattern and consequently on Egypt and Sudan. Moreover, the current study opens new windows for future research to investigate the impacts of the different aspects of GERD of AHDL.

Analyzing the evolution of breast tumors through flow fields and strain tensors

Abstract Breast cancer is one of the most perilous diseases that annually attack thousands of women. Physicians usually monitor the breast tumor changes during the course of a chemotherapy treatment. Computer programs may help physicians to predict the pathological response in order to adjust the medical treatment to produce the intended effects. This paper proposes a method for quantifying and visualizing the changes of breast tumors of cases undergoing medical treatment through strain tensors. The proposed method determines the displacement fields between each follow-up mammogram and its baseline. To compute the displacement fields, we evaluated the performance of eight robust and recent optical flow methods through landmark-based error and statistical analysis. Since, there is no ground truth to evaluate the optical flow methods when they are applied to mammograms, we propose to aggregate the best optical flow methods using ordered weighted averaging operators. The aggregated optical flow methods using the ‘as many as possible’ operator yields the smallest landmark-based error among three aggregation approaches analyzed with the proposed algorithm. The resulting optical flow is then used to estimate the strain tensors. The proposed method provides a good quantification and visualization for breast tumor changes and that helps physicians to plan treatment for their patients.

Accurate photovoltaic power forecasting models using deep LSTM-RNN

Photovoltaic (PV) is one of the most promising renewable energy sources. To ensure secure operation and economic integration of PV in smart grids, accurate forecasting of PV power is an important issue. In this paper, we propose the use of long short-term memory recurrent neural network (LSTM-RNN) to accurately forecast the output power of PV systems. The LSTM networks can model the temporal changes in PV output power because of their recurrent architecture and memory units. The proposed method is evaluated using hourly datasets of different sites for a year. We compare the proposed method with three PV forecasting methods. The use of LSTM offers a further reduction in the forecasting error compared with the other methods. The proposed forecasting method can be a helpful tool for planning and controlling smart grids.

Exploiting the Kinematic of the Trajectories of the Local Descriptors to Improve Human Action Recognition

This paper presents a video representation that exploits the properties of the trajectories of local descriptors in human action videos. We use spatial-temporal information, which is led by trajectories to extract kinematic properties: tangent vector, normal vector, bi-normal vector and curvature. The results show that the proposed method provides comparable results compared to the state-of-the-art methods. In turn, it outperforms compared methods in terms of time complexity.

Towards cost reduction of breast cancer diagnosis using mammography texture analysis

In this paper we analyse the performance of various texture analysis methods for the purpose of reducing the number of false positives in breast cancer detection; as a result, the cost of breast cancer diagnosis would be reduced. We consider well-known methods such as local binary patterns, histogram of oriented gradients, co-occurrence matrix features and Gabor filters. Moreover, we propose the use of local directional number patterns as a new feature extraction method for breast mass detection. For each method, different classifiers are trained on the extracted features to predict the class of unknown instances. In order to improve the mass detection capability of each individual method, we use feature combination techniques and classifier majority voting. Some experiments were performed on the images obtained from a public breast cancer database, achieving promising levels of sensitivity and specificity.

The Impact of Pixel Resolution, Integration Scale, Preprocessing, and Feature Normalization on Texture Analysis for Mass Classification in Mammograms

Texture analysis methods are widely used to characterize breast masses in mammograms. Texture gives information about the spatial arrangement of the intensities in the region of interest. This information has been used in mammogram analysis applications such as mass detection, mass classification, and breast density estimation. In this paper, we study the effect of factors such as pixel resolution, integration scale, preprocessing, and feature normalization on the performance of those texture methods for mass classification. The classification performance was assessed considering linear and nonlinear support vector machine classifiers. To find the best combination among the studied factors, we used three approaches: greedy, sequential forward selection (SFS), and exhaustive search. On the basis of our study, we conclude that the factors studied affect the performance of texture methods, so the best combination of these factors should be determined to achieve the best performance with each texture method. SFS can be an appropriate way to approach the factor combination problem because it is less computationally intensive than the other methods.

Compressive sensing MRI reconstruction using empirical wavelet transform and grey wolf optimizer

Magnetic resonance imaging (MRI) has exhibited an outstanding performance in the track of medical imaging compared to several imaging modalities, such as X-ray, positron emission tomography and computed tomography. MRI modality suffers from protracted scanning time, which affects the psychological status of patients. This scanning time also increases the blurring levels in MR image due to local motion actions, such as breathing as in the case of cardiac imaging. An acquisition technique called compressed sensing has contributed to solve the drawbacks of MRI and decreased the acquisition time by reducing the quantity of the measured data that is needed to reconstruct an image without significant degradation in image quality. All recent works have used different types of conventional wavelets for sparsifying the image, which employ constant filter banks that are independent of the characteristics of the input image. This paper proposes to use the empirical wavelet transform (EWT) which tunes its filter banks to the characteristics of the analyzed images. In other words, we use EWT to produce a sparse representation of the MRI images which yields a more accurate sparsification transform. In addition, the grey wolf optimizer is used to optimize the parameters of the proposed method. To validate the proposed method, we use three MRI datasets of different organs: brain, cardiac and shoulder. The experimental results show that the proposed method outperforms the state-of-the-art methods in terms of signal-to-noise ratio and structure similarity metrics.