Leukemia Diagnosis Using Microscopic Digital Images

No Thumbnail Available
Khader, Maha
Radi, Rawan
Journal Title
Journal ISSN
Volume Title
The microscopic images of the blood cells are observed to find out many diseases. Changes in the blood condition show the development of diseases in an individual, Leukemia can lead to death if it is left untreated. Based on some statistics it is found that the leukemia is the fifth cause of death in men and sixth cause of death in women. Leukemia originates in the bone marrow. Each bone contains a thin material inside it which is also known as a bone marrow. The components of blood are Red Blood Cells (erythrocytes), White Blood Cells (leucocytes), platelets and plasma. Leukemia is detected only by analyzing the white blood cells. So, our study is focused only on the white blood cells (WBCs). The cells in the bone marrow start changing and they get infected and become leukemia or infected cells. These leukemia cells are having strange properties than the normal cells. Their growth is abnormal and survival time is more than the normal cells. They interrupt normal cells to carry out their work. After a certain amount of time normal cells die while leukemia cells don’t. The old leukemia cells last for a long time and new leukemia cells produce in an abnormal way. The rate at which the leukemia cells progress is different according to the type of leukemia. In this work, automated approach of leukemia detection is proposed and determine the stage of cancer is done. In a manual method of Leukemia detection, experts check the microscopic images. This is lengthy and time taking process which depends on the person’s skill and not having a standard accuracy. The automated Leukemia detection system analyses the microscopic image and overcomes these drawbacks. It extracts the required parts of the images and applies some filtering techniques. K-mean clustering approach is used for white blood cells detection. The proposed system is successfully implemented in MATLAB.