DESIGN OF A LEUKEMIA DETECTION SYSTEM USING DIGITAL BLOOD SMEAR IMAGES
No Thumbnail Available
Date
2023-06
Journal Title
Journal ISSN
Volume Title
Publisher
Faculty of Engineering and Technology, University of Ilorin
Abstract
Leukaemia is a fatal blood cancer that occurs due to the formation of abnormal and excessive increases in white
blood cells in the bone marrow or blood. The traditional approaches used to diagnose the disease involve the
manual analysis of blood sample images obtained from a microscope. This approach is tedious, slow, timeconsuming,
and prone to errors. Therefore, automatic detection of leukaemia based on the counting of the two
blood cells is paramount for diagnosis and increasing the patient’s survival rate. This paper presents a system that
can detect each of the two blood cells needed through image processing, segmentation, and classification. The
detection, classification, and counts are only limited to two of the cells present in the digital blood smear which
are the white blood cells (WBCs) and red blood cells (RBCs). The model was evaluated with a collection of
confirmed cases and normal cases to test its effectiveness in predicting the presence of Leukaemia by computing
the ratio of WBC to RBC. The suggested model exhibits good performance results and can be utilized to make a
reliable computer-aided diagnosis detection of leukaemia cancer.
Description
Keywords
Leukaemia, White Blood Cells (WBCs), Red Blood Cells (RBCs), Detection, Machine Learning, Blood Smear.