Projects

Intelligent Diagnosis System for Liver Fibrosis in Chronic Hepatitis C (CHC).Collaboration Program between  Ministry of Higher Education and Scientific Research in Egypt and Tunisia.  Coordinators Egypt: Professor Aboul ella Hassanien, Tunisia: Professor Adel M. Alimi. National School of Engineers, University of Sfax, Tunisia.

 Project Budget:  50 000 L.E. for the Egyptian side

 Period: May 2012- May 2014

Project Objective

The aim of this study is to develop computerized image analysis system to assist radiologists in mammography interpretation of liver fibrosis images by using the bio-inspired computing. The suggested system is based on an empirical analysis of the image and it is split in several steps using local image properties. The suggested system steps are:  

(1)   Pre-processing,

(2)   Segmentation of potentially abnormal regions,

(3)   Feature extraction  and selection

(4)   Classification of these candidate regions based on the selected features

(5)   Evaluation

Pre-processing stage involves capturing the CT liver images, enhancing the captured liver CT images before a reasonable segmentation can be achieved as well as suppression noise in the segmented region of interest.  Segmentation stage involves grouping adjacent pixels with similar properties together to form connected regions. In the segmentation stage, features extracted from the image regions are used to assign them to one of the live fibrosis classes, this we called a classification process. Finally, prediction model is expected to extract knowledge in the form of rules which would guide the radiologists in his/her decision. Some quantitative measurement will used to evaluate the performance of the predicted model and a comparison with related published work will be considered.

=================================================

Graduated Student Projects

Group Funded Projects

================

Graduated Student Projects (2010-2011)  Funded by ITIDA- InformationTechnology Industry Development Agency 

·     Intelligent Water Quality Monitoring System: Abstract: The wireless sensor network (WSN) consists of spatially distributed autonomous sensors to cooperatively monitor physical or environmental conditions, such as temperature, sound, vibration, pressure, motion or pollutants. The development of wireless sensor networks are now used in many industrial and civilian application areas, including industrial process monitoring and control, machine health monitoring, home automation, and traffic control.  The project objective is to connect the whole room with specific sensors to ease the usage of the room contents of devices such as air conditioners, coffee machines....etc, to be controlled through computer system.

·    Heart Sound Identification and analysis System: Abstract: In this project we are supposed to introduce a different biometric technology for human identification unlike others that use fingerprints, iris, voice, vein or face to identify a person, which can be copied and regenerated easily, but in our case by using heart sound which has many properties that convinced us to choose it for human identification and most important one that is based on intrinsic human biometric dynamic signals acquired from the body which prevent it from being copied and will be used also in the medical field like diagnosing patient’s complaining.

·      An intelligent system for hepatitis C Virus (HCV) predictors: Abstract: We tried to identify the most significant predictors for HCV treatment response based on historical data to provide a support that helps doctors to examine patients in a right way and helps in the enhancements of their health. Our problem closely related to ICT field as we will use data mining techniques and computational intelligence paradigms. That is will be done by mining extracted patients medical, examination, inspection and historical data from different data sources into a data warehouse. The main objective of this project is   identifying the most important factors that affect the HCV treatment predictors.      

·   Intelligent Diagnosis System for Liver Fibrosis in Chronic Hepatitis. Abstract: Fibrosis liver disease is a deadly disease that adversely affects the lives of many people, which is the final result of injury to the liver. Accurate assessment of the degree of fibrosis is important clinically, especially when treatments aimed at reversing fibrosis are being evolved. Liver biopsy has been considered to be the gold standard to assess fibrosis. However, liver biopsy being invasive and is not favored by patients or physicians, alternative approaches to assess liver fibrosis have assumed great importance. The main objective of this project is Developing an   Intelligent Diagnosis System for Liver Fibrosis in Chronic Hepatitis C.

·   Automated Identification of Diabetic Retinopathy Stages Using Digital Fundus Images. Abstract: Diabetic retinopathy (DR) is caused by damage to the small blood vessels of the retina in the posterior part of the eye of the diabetic patient. The main stages of diabetic retinopathy are non-proliferate diabetes retinopathy (NPDR) and proliferate diabetes retinopathy (PDR). The retinal fundus photographs are widely used in the diagnosis and treatment of various eye diseases in clinics. It is also one of the main resources for mass screening of diabetic retinopathy. The aim of this project is to develop an intelligent computer aided system    for the detection of diabetic retinopathy stage using fundus images. 

·    An Automatic E-Contract Document Signing System  in a Secure Environment. Abstract: E-Contract system must have the characteristic of anti-deniability, integrity, security, and identity-authentication., so the main objective of the suggested project is to develop and implement the Al-Gamal or RAS digital signature algorithm on e-contract   in a secure environment. Using RSA and El-Gamal algorithm to generate a digital signature  for e-contract.

·      Multi-modal Biometric System.  Abstract: The uni-modal biometric systems making use of a single biometric modality have a limited performance that restricts their applicability in real life scenarios. The multimodal biometric systems make use of two or more modalities that together achieve much higher performances. Biometrics is a science that deals with human identification on the basis of our biological features. Therefore, Biometrics belongs to Pattern Recognition and is part of it. Biometric examples are all features we are born with like facial image, finger-prints, iris of the eye,  or the features we learn in our life like the way we write (signature), the way we walk (gait) or any of the behavioral characteristics. The objective is to develop an efficiency hybrid human print identification system.

 

Graduated Student Projects (2011-2012)