Papers by Mohammed Elmogy
2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)
In this paper, a computer-aided diagnosis (CAD) system for early diagnosis of prostate cancer fro... more In this paper, a computer-aided diagnosis (CAD) system for early diagnosis of prostate cancer from diffusion-weighted magnetic resonance imaging (DWI) is proposed. The proposed system begins with defining a region of interest that contains the prostate across the various slices of the input volume. Then, the apparent diffusion coefficient (ADC) of the defined region is calculated, normalized and refined. Finally, the classification of prostate into either benign or malignant is performed through two stages. In the first stage, seven convolutional neural networks (CNNs) are utilized to get initial probabilities for each case. Then, a random forest (RF) classifier uses these probabilities a s input to decide the final diagnosis. The proposed system is a novel system in the sense that it has the ability to detect prostate cancer without any prior processing (e.g., the segmentation of the prostate region). Evaluation of the developed system is done using DWI datasets collected at seven different b-values from 32 patients (16 benign and 16 malignant). The acquisition of these DWI datasets is performed using two different scanners with different magnetic field strengths (1.5 Tesla and 3 Tesla). The resulting accuracy of the proposed system after the second stage of classification shows a good performance close to the performance of up-to-date systems.
Cryptography is about constructing protocols by which different security means are being added to... more Cryptography is about constructing protocols by which different security means are being added to our precious information to block adversaries. Properties of DNA are appointed for different sciences and cryptographic purposes. Biological complexity and computing difficulties provide twofold security safeguards and make it difficult to penetrate. Thus, a development in cryptography is needed not to negate the tradition but to make it applicable to new technologies. In this paper, we review the most significant research, which is achieved in the DNA cryptography area. We analysed and discussed its achievements, limitations, and suggestions. In addition, some suggested modifications can be made to bypass some detected inadequacies of these mechanisms to increase their robustness. Biological characteristics and current cryptography mechanisms limitations were discussed as motivations for heading DNA-based cryptography direction.
2018 24th International Conference on Pattern Recognition (ICPR), 2018
This paper introduces a diagnosis system for detecting early signs of diabetic retinopathy (DR) u... more This paper introduces a diagnosis system for detecting early signs of diabetic retinopathy (DR) using optical coherence tomography angiography (OCTA) images. We developed a segmentation technique that was able to extract blood vessels from both retinal superficial and deep maps. It is based on a higher order joint Markov-Gibbs random field (MGRF) model, which combines both current and spatial appearance information of retinal blood vessels. To be able to train/test a support vector machine (SVM) classifier, three local features were extracted from the segmented images. These extracted features are the density and appearance of the retinal blood vessels in addition to the distance map of the foveal avascular zone (FAZ). Then, we used SVM with linear kernel to distinguish sub-clinical DR patients from normal cases. By using 105 subjects, the presented computer-aided diagnosis (CAD) system demonstrated an overall accuracy (ACC) of 97.3 % and a Dice similarity coefficient (DSC) of 97.9%.
Identifying genes related to Parkinson's disease (PD) is an active and effective research top... more Identifying genes related to Parkinson's disease (PD) is an active and effective research topic in biomedical analysis, which plays a critical role in diagnosis and treatment. In recent years, many studies have proposed different techniques for predicting disease-related genes. However, a few of these techniques are designed or developed for PD gene prediction. Most of these PD techniques are developed to identify only protein genes and discard long non-coding (lncRNA) genes, which play an essential role in biological processes and the Transformation and development of diseases. This paper proposes a novel prediction system to identify protein and lncRNA genes related to PD that can aid in an early diagnosis. First, we preprocessed the genes into DNA FASTA sequences from the UCSC genome browser and removed the redundancies. Second, we extracted some significant features of DNA FASTA sequences using five numerical mapping techniques with Fourier transform and PyFeat method with A...
U-Healthcare Monitoring Systems, 2019
Abstract The growing significance of clinical decision support systems (CDSS) has become a positi... more Abstract The growing significance of clinical decision support systems (CDSS) has become a positive factor influential in pushing medical care toward success. It depends on using successful and effective reasoning methodologies. This survey aims to give a brief overview of the research directions that are practiced under the domain of reasoning methodologies used in CDSS implementation. It focuses on studying the roles of fuzzy ontology and fuzzy logic in the CDSS implementation given in the scientific literature. We are trying to identify new future trends in this domain. We adopt a search methodology involving the definition of research questions, the determination of selection criteria, and the description of the search strategy. The primary questions of this review are as follows: Which reasoning techniques have been used in CDSS? What is the accuracy of using different reasoning techniques in real applications? What are the limitations of existing reasoning techniques? How to enhance the reasoning process in DSS? The manuscript describes the current published literature in Science Direct, Springer Link, PubMed, and IEEE Xplore from 2009 through November 2017. The search strategy contains four processes: screening papers, selecting papers, extracting and analyzing concepts, and identifying future trends. Our search identified 1886 papers across different electronic databases. These papers are used as an initial database. After reviewing these articles, we selected 134 relevant articles that are more interesting and suitable for the goals of this paper. These relevant articles are included in our critical analysis to find the possible future trends. The literature review showed that case-based reasoning (CBR), Mamdani fuzzy inference, and ontology systems are the most-used reasoning techniques. However, the fuzzy inference failures, the unclear and not unified methods for the fuzzy ontology construction process and tools, the limitations of existing fuzzy description logic reasoners, and the manual case adaptation process in CBR are still the main problems and might not support the clinical practice effectively. Most of these models used ontology and fuzzy logic as two separate models, and no real overlap occurs. There are some serious points to be discussed to enhance the inference of the fuzzy component. Ontology can be used to enhance the capabilities of the fuzzy inference system. Our solution is the hybridization of regular and mature crisp ontology reasoning with regular and mature Mamdani fuzzy reasoning. We expect that will be the best choice to overcome the current limitations of crisp ontology and fuzzy reasoning. In this paper, the different reasoning methodologies applied to CDSS are analyzed. We are looking to combine ontology and Mamdani fuzzy inference in a hybrid CDSS system. The hybrid model is the most logical step to improve the fuzzy expert system by adding a semantic reasoning process to its capabilities. There are many reasons for this decision. First, the fuzzy expert systems are stable and mathematically proved, and there are many fuzzy reasoners such as Mamdani, etc. In addition, crisp ontology and its special case of (standard) medical ontologies have stable, crisp description logic such as SROIQ D , well-known languages such as OWL 2, and well-established reasoners.
Egypt has the highest prevalence of Hepatitis C virus (HCV) in the world. It is important to pres... more Egypt has the highest prevalence of Hepatitis C virus (HCV) in the world. It is important to present research in a liver domain based on a real dataset collected from different localities in Egypt and suffering from liver diseases. This paper presents two case studies to explore the most important factors for detecting the liver disease in Egypt. The first considers an HCV treatment. The second evaluates the drinking water pollution by iron on liver functions. We encountered many problems in these studies, such as how to deal with complex, inconsistent, and missing data. In addition, we studied the impact of missing treatment techniques on classification accuracy. Therefore, we propose an Interval-valued Fuzzy Rough with Support Vector Machine (SVM) classification model. In the preparation stage, we use Interval-valued Fuzzy Rough set theory for feature selection that can handle missing values efficiently and get a good reduction. After that, we do the imputation process, which is limited to relevant attributes. It can reap many benefits, such as raise efficiency and saving the time of dealing with missing values. In the classification stage, we use SVM, which is a powerful technique to get good classification performance. Finally, we compare the output results of the SVM with other classification techniques to guarantee the highest classification performance.
Machine Learning in Bio-Signal Analysis and Diagnostic Imaging, 2019
Abstract In the last years, a lot of literature has provided considerable support for multilabel ... more Abstract In the last years, a lot of literature has provided considerable support for multilabel classification in machine learning. It means that each sample or instance belongs to more than one class label simultaneously. Therefore, it represents complex objects that have multiple meanings. It helps in capturing more information by labeling some basic and hidden patterns. In this respect, multilabel classification is very useful in medical data analysis. It addresses the problem of diagnosis, surgery, anatomy, disease progress, analysis, and teaching purposes in medicine. There are many patients have many diseases at the same time, maybe in the same organ, such as ocular diseases. On the other side, the multilabel classification is a challenging issue by nature. This is due to high dimensionality, sparseness, and imbalance of available data. Some problems with labels are raised, such as label dependency, locality, interlabel diversity, and similarity. Therefore, our survey introduces significant topics of the multilabel classification in medical image analysis field. Notably, most of the literature did not show how multilabel classification affect the medical image analysis. In this chapter, we presented the different examples of medical image classification by the multilabel methods. We present the detailed analysis and discussions of the literature findings. The performance of the methods is compared on five publicly available data sets such as yeast, scene, genebase, corel5k and BibTex of multilabel classification using famous measures. Moreover, we intend to give the researcher a computer-aided CAD system framework for the existing multilabel classification research.
International Journal of Advancements in Computing Technology, 2015
3D object recognition from point clouds is considered as a field of research that is growing fast... more 3D object recognition from point clouds is considered as a field of research that is growing fast. Based on the types of features used to represent an object, 3D object recognition approaches can be classified into two broad categories—local and global feature-based techniques. Local feature-based techniques are more robust to clutter and partial occlusions that are frequently present in a real-world scene. Whereas, global feature-based techniques are suitable for model retrieval and 3D shape classification especially with the weak geometric structure. Most systems for 3D object recognition use either local or global feature-based techniques. This is because of the difficulty of integrating a set of local features with a single global feature vector in an appropriate manner. In this paper, a 3D object recognition system based on local and global features of the objects using Point Cloud Library (PCL) is proposed. The proposed system uses a hybrid technique based on Viewpoint Feature...
2018 24th International Conference on Pattern Recognition (ICPR), 2018
This paper addresses the issue of early diagnosis of prostate cancer from diffusion-weighted magn... more This paper addresses the issue of early diagnosis of prostate cancer from diffusion-weighted magnetic resonance imaging (DWI) using a convolutional neural network (CNN) based computer-aided diagnosis (CAD) system. The proposed CNN-based CAD system first segments the prostate using a geometric deformable model. The evolution of this model is guided by a stochastic speed function that exploits first-and second-order appearance models besides shape prior. The fusion of these guiding criteria is accomplished using a nonnegative matrix factorization (NMF) model. Then, the apparent diffusion coefficients (ADCs) within the segmented prostate are calculated at each b-value. They are used as imaging markers for the blood diffusion of the scanned prostate. For the purpose of classification/diagnosis, a three dimensional CNN has been trained to extract the most discriminatory features of these ADC maps for distinguishing malignant from benign prostate tumors. The performance of the proposed CN...
2019 IEEE International Conference on Imaging Systems and Techniques (IST), 2019
Diabetic Retinopathy (DR) is considered one of the major reasons for vision loss in the working-a... more Diabetic Retinopathy (DR) is considered one of the major reasons for vision loss in the working-age population in most of the countries. DR is caused by high blood sugar levels (diabetes), which damages retinal blood vessels and leads to blindness. Both diagnosis and grading of DR require manual measurements and visual assessment of the changes that happen in the retina, which is a highly complex task. Thus, there is an unmet clinical need for a non-invasive and objective diagnostic system, which can improve the accuracy of both early signs and grading detection for DR. In this paper, we proposed a computer-aided diagnosis (CAD) system for detecting early signs as well as grading of DR. Four significant retinal vasculature features are extracted from optical coherence tomography angiography (OCTA) scans, which reflect the changes in the retinal blood vessels due to DR progress. The developed system fuses these four significant features with clinical and demographic biomarkers. The proposed system uses a 3D convolutional neural network (CNN) to segment blood vessels from both OCTA deep and superficial plexuses. Finally, these extracted features are classified by using the random forest (RF) technique to differentiate first between the DR from normal subjects. Then, grade the DR subjects into mild or moderate. Our preliminary results of grading DR in a cohort of patients (n == 100) demonstrated an average accuracy of 96.8%, sensitivity of 98.1%, and specificity of 88.8%. These results show the feasibility of the proposed approach in early detection as well as the grading of DR.
Sensors, 2021
Alzheimer’s disease (AD) is a neurodegenerative disorder that targets the central nervous system ... more Alzheimer’s disease (AD) is a neurodegenerative disorder that targets the central nervous system (CNS). Statistics show that more than five million people in America face this disease. Several factors hinder diagnosis at an early stage, in particular, the divergence of 10–15 years between the onset of the underlying neuropathological changes and patients becoming symptomatic. This study surveyed patients with mild cognitive impairment (MCI), who were at risk of conversion to AD, with a local/regional-based computer-aided diagnosis system. The described system allowed for visualization of the disorder’s effect on cerebral cortical regions individually. The CAD system consists of four steps: (1) preprocess the scans and extract the cortex, (2) reconstruct the cortex and extract shape-based features, (3) fuse the extracted features, and (4) perform two levels of diagnosis: cortical region-based followed by global. The experimental results showed an encouraging performance of the propos...
International Journal of Advanced Computer Research, 2021
Much effort is being made by the researchers in order to detect and diagnose diabetic retinopathy... more Much effort is being made by the researchers in order to detect and diagnose diabetic retinopathy (DR) automatically and accurately. The disease is very dangerous as it can cause blindness suddenly if it is not continuously screened. Therefore, many computers aided diagnosis (CAD) systems have been developed to diagnose the various DR grades. Recently, many CAD systems based on deep learning (DL) methods have been adopted to get deep learning merits in diagnosing the pathological abnormalities of DR disease. In this paper, we present a full based-DL CAD system, depending on multilabel classification. In the proposed DL CAD system, we present a customized EffecientNet model in order to diagnose the early and advanced grades of the DR disease based on transfer learning. Transfer learning is very useful in training small datasets. We utilized a multi-label Indian Diabetic Retinopathy Image Dataset (IDRiD) dataset. The experiments manifest that the proposed DL CAD system is robust, reliable, and deigns promising results in detecting and grading DR. The proposed system achieved accuracy (ACC) equals 86%, and the Dice similarity coefficient (DSC) equals 78.45%.
SSRN Electronic Journal, 2008
1 Mobile robots and Humanoids need to use spatial information about their surrounding environment... more 1 Mobile robots and Humanoids need to use spatial information about their surrounding environment in order to effectively plan and execute navigation tasks. This spatial information can be presented in various ways to increase the interaction between the human and the robot. One of the more effective ways is by describing the route verbally which bridges the gap between the forms of spatial knowledge of such robots and the forms of language used by humans. In this paper, we build a topological map for robot route description. This map represents the route's motion actions and spatial relationships graphically to plan robot's navigation task. The map is generated by using Formal Route Instructions (FRIs) to simplify the route description process and also to avoid ambiguity. FRIs are designed to be simple, easy to use, and suitable for naïve users. 1 INTRODUCTION A robot is an intelligent, multipurpose machine, which can carry out a variety of online tasks. An essential aspect, which distinguishes robotics from other areas of AI, is the interaction of robots with humans and with their surrounding environment. In a robot system, various autonomous components such as sensing, recognition, planning, control, and their coordination must cooperate in recognizing the environment, solving problems, planning a behavior, and executing it. In order to make this interaction more intelligent, a robot needs functions such as: the ability to understand the environment by visual recognition, the ability to perform dexterous manipulation using force, tactile, and visual feedback, the ability to plan task procedures, the ability to communicate with humans, the ability to learn how to perform tasks, the ability to recover from errors, and so on [1]. All of these functions are required for robot intelligence to be realized adequately. Due of the potential for interaction with humans, research in humanoid robotics has made significant progress in recent years. The key reason for preferring humanoids is their shape, which seems to be optimal for being taught by humans and learning from humans. Humanoid robotics labs worldwide are working on creating robots that are similar to humans in shape and behavior. These similarities have been proven to facilitate the
SSRN Electronic Journal, 2008
Landmark recognition is identified as one important research area in robot navigation systems. It... more Landmark recognition is identified as one important research area in robot navigation systems. It is a key feature for building robots capable of navigating and performing tasks in human environments. However, current object recognition research largely ignores the problems that the mobile robot context introduces. We developed a landmark recognition system which is used by a humanoid robot to identify landmarks during its navigation. The humanoid landmark recognition system is based on a two-step classification stage which is robust and invariant towards scaling and translations. Also, it provides a good balance between fast processing time and high detection accuracy. An appearance-based classification method is initially used to provide the rough initial estimate of the landmark. It is followed by a refinement step using a modelbased method to estimate an accurate classification of the object. The goal of our work is to develop a rapid, robust object recognition system with a high detection rate that can actually be used by a humanoid robot to recognize landmarks during its navigation.
The 2010 International Conference on Computer Engineering & Systems, 2010
In mobile robot scenarios, it is expected that the robot autonomously navigates through home or o... more In mobile robot scenarios, it is expected that the robot autonomously navigates through home or office environments and processes objects/landmarks during navigation. Landmark manipulation is identified as one important research area in robot navigation systems. We have developed an online robot landmark processing system (RLPS) to detect, classify, and localize different types of landmarks during robot navigation. The RLPS is based on a two-step classification stage which is robust and invariant towards scaling and translations. It provides a good balance between fast processing time and high detection accuracy by combining the strengths of appearancebased and model-based object classification techniques. The experimental results showed that the RLPS is more powerful as it recognizes a wide range of landmarks and efficiently handles landmarks with occlusions, viewpoint variances, and illumination changes.
2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 2018
We propose a convolutional neural network (CNN) based computer-aided diagnosis (CAD) system for e... more We propose a convolutional neural network (CNN) based computer-aided diagnosis (CAD) system for early diagnosis of prostate cancer from diffusion-weighted magnetic resonance imaging (DWI). The proposed CNN-based CAD system begins by segmenting the prostate in a DWI dataset. Segmentation is achieved using our previously developed approach based on a geometric deformable model whose evolution is guided by first- and second-order appearance models. The spatial maps of apparent diffusion coefficients (ADCs) within the prostate, calculated for each 6-value, are used as image-based markers for the blood diffusion of the scanned prostate. For the purpose of classification/diagnosis, a three dimensional CNN has been trained to exact the most discriminatory features of these ADC maps for distinguishing malignant from benign prostate tumors. The proposed CNN-based CAD system is tested on DWI acquired from 23 patients using seven distinct 6-values. These experiments on in-vivo data confirm the high accuracy of the proposed CNN-based CAD system compared with our previously published results.
IEEE Access, 2021
The World Health Organization (WHO) indicates that the proportion of the elderly will soon includ... more The World Health Organization (WHO) indicates that the proportion of the elderly will soon include nearly a quarter of the world population. Ensuring that health systems are prepared to deal with this phenomenal rate of aging and associated diseases generates many challenges. Among these challenges is facing Alzheimer’s Disease (AD) that may occur at some point in the elderly life and may harm societies. AD is considered a neurological, psychological, mental, and health setback. The Clinical Decision Support System (CDSS) can improve patient care and support many medical functions, such as diagnosing diseases that can reduce preventable harm. This research’s main objective is to design, implement, and evaluate the Alzheimer’s Disease Diagnosis Ontology (ADDO). It is a comprehensive semantic knowledge base toward the development of fuzzy ontology-based CDSS for AD diagnosis. ADDO can serve as a core component of CDSS, which provides representation, annotation, and access to aspects r...
2016 IEEE International Conference on Image Processing (ICIP), 2016
In this paper, we propose a novel non-invasive framework for the early diagnosis of prostate canc... more In this paper, we propose a novel non-invasive framework for the early diagnosis of prostate cancer from diffusion-weighted magnetic resonance imaging (DW-MRI). The proposed approach consists of three main steps. In the first step, the prostate is localized and segmented based on a new level-set model. In the second step, the apparent diffusion coefficient (ADC) of the segmented prostate volume is mathematically calculated for different b-values. To preserve continuity, the calculated ADC values are normalized and refined using a Generalized Gauss-Markov Random Field (GGMRF) image model. The cumulative distribution function (CDF) of refined ADC for the prostate tissues at different b-values are then constructed. These CDFs are considered as global features describing water diffusion which can be used to distinguish between benign and malignant tumors. Finally, a deep learning auto-encoder network, trained by a stacked non-negativity constraint algorithm (SNCAE), is used to classify the prostate tumor as benign or malignant based on the CDFs extracted from the previous step. Preliminary experiments on 53 clinical DW-MRI data sets resulted in 100% correct classification, indicating the high accuracy of the proposed framework and holding promise of the proposed CAD system as a reliable non-invasive diagnostic tool.
2019 IEEE International Conference on Image Processing (ICIP)
The purpose of this work is to develop a computer-aided diagnosis (CAD) system for detecting and ... more The purpose of this work is to develop a computer-aided diagnosis (CAD) system for detecting and localizing prostate cancer from diffusion-weighted magnetic resonance imaging (DWI) acquired at five distinct b-values. The first step in the proposed system depends on nonnegative matrix factorization (NMF) to fuse intensity features of prostate voxels, spatial features of neighboring voxels, and shape prior features to guide the evolution of a level set function for accurate prostate segmentation. The second step in the proposed system involves calculating the apparent diffusion coefficient (ADC) maps of the segmented prostate regions as a discriminating feature between malignant and healthy cases. These ADC maps are used in the last step of the CAD system to train a convolutional neural network (CNN)-based model to identify the ADC maps with malignant tumors. To evaluate the accuracy of the system, 50% of the ADC maps are randomly chosen to train the CNN-model while the second 50% of the ADC maps are used to evaluate the accuracy of the trained model. The proposed CAD system resulted in an average area under the receiver operating characteristic curve (AUC) of 0.93 at the five b-values.
Electronics
Semantic interoperability of distributed electronic health record (EHR) systems is a crucial prob... more Semantic interoperability of distributed electronic health record (EHR) systems is a crucial problem for querying EHR and machine learning projects. The main contribution of this paper is to propose and implement a fuzzy ontology-based semantic interoperability framework for distributed EHR systems. First, a separate standard ontology is created for each input source. Second, a unified ontology is created that merges the previously created ontologies. However, this crisp ontology is not able to answer vague or uncertain queries. We thirdly extend the integrated crisp ontology into a fuzzy ontology by using a standard methodology and fuzzy logic to handle this limitation. The used dataset includes identified data of 100 patients. The resulting fuzzy ontology includes 27 class, 58 properties, 43 fuzzy data types, 451 instances, 8376 axioms, 5232 logical axioms, 1216 declarative axioms, 113 annotation axioms, and 3204 data property assertions. The resulting ontology is tested using rea...
Uploads
Papers by Mohammed Elmogy