Thesis (M.Sc.) - Cairo University - Faculty of Computers and Information - Department of Information Technology

Primary malignant liver tumours, cause 1.25 millions death per year worldwide. HCC is prevalent in Asia and Africa because of the presence of a large sub clinical population with hepatitis C virus infection. Early detection and accurate staging of liver cancer is an important issue in practical radiology. Although Multi Detector-row Computed Tomography ( MDCT ) or MRI is widely used for the diagnosis of liver tumours, the amount of information obtained from MDCT/MRI is very large, and its currently dif- {uFB01}cult for inexperienced radiologists or physicians to interpret all the images within a short time span. In this research, we considered the problem of developing an intelligent automated sys- tem for detecting the presence of tumour nodules in the liver CT images, that can be considered as a second reader to the radiologists. At that time and still now, it is well known that the visual detection of liver tumour nodules is a di{uFB03}cult task for radiologists, who may miss some of the nodules. Radiologists have missed these lesions due to the overlap of normal anatomic structures with nodules.

Issued also as CD