Automatic detection of acute lymphoblasitc leukemia using image processing

Acute lymphoblastic leukemia is a form of blood cancer caused due to the abnormal increase in the production of immature white blood cells in the bone marrow, mostly affecting children below 5 years and adults above 50 years of age. The ailment has to be detected and treated at an early stage for recovery. Early signs of the disease in children include fever and bruising which can go unnoticed during the critical early stage. We propose and implement a fully automated algorithm by use of image processing to aid in the detection of acute lymphoblastic leukemia by identifying and counting the infected white blood cells present in the human blood sample. The method provides high speed, accuracy and scope for early detection of the disease. The algorithm is implemented in MATLAB and an average accuracy greater than 90% is achieved.