Thesis (Ph.D.) - Cairo University - Faculty of Engineering - Department of Systems and Biomedical Engineering

Leukaemia is a malignant disease characterized by the uncontrolled accumulation of abnormal white blood cells. Blood smear microscopic images are investigated by haematologist to diagnose most blood disease. Manual methods are a tiresome, time-consuming and susceptible to error procedure due to the tedious nature of this process. The total dataset consisted of 739 images represent three types of leukaemia cells: Blast, myelocyte and segmented cells. The algorithm results demonstrated an overall accuracy of 99.517%, sensitivity of 99.348%, and specificity of 99.529%. Therefore, this algorithm yielded promising results and warrants further research. Classifying step of the cells according to its morphological extracted features was presented. Classifiers as decision tree, neural network, fuzzy logic and support vector machine were implemented and compared. It was concluded that it might be possible to build an automated support system based on the combined Image processing and analysis features extracted from a digital microscopic images, motivate to expand to observe all acute myeloid leukemia cell types

Issued also as CD