Abstract—Leukemia is a highly fatal hematologic cancer which starts in blood-forming tissue, such as bone marrow and triggers high production of immature and abnormal shaped blood cells. Skilled medical officers are required to diagnose leukemia from blood smears. This poses a problem in remote areas and rural areas where there is a shortage of qualified medical personnel. This paper proposes a computer-aided diagnosis system that can detect and classify leukemia from blood microscopic images. Satisfactory preliminary experimental results demonstrate the efficacy of our system.

Index Terms—leukemia detection, classification, scale-invariant feature transform, pattern recognition.

Cite: Lokman Faivdullah, Farid Azahar, Zaw Zaw Htike, and Wei Yan Nyein Naing, "Leukemia Detection from Blood Smears," Journal of Medical and Bioengineering, Vol. 4, No. 6, pp. 488-491, December 2015. Doi: 10.12720/jomb.4.6.488-491