A new FISH Signals Fusion Detection approach for diagnosing Chronic Myeloid Leukemia

Abstract

Cancer is consider one of the worst disease in the modern era which cause a huge number of deaths each year world wide. It is generated due to the abnormal growth of attacking enormous number of cells to the human body cells that white blood cells can't defend for the human body. Regionally, the number of death as a consequence of the cancer is increasing and affect the growing economies badly. Medical imaging is a technique that visualize the inside of the human body using computerized device. Usually, manipulating the problems of medical imaging using image processing techniques. Leukemia is cancer of the body's blood-forming tissues, including the bone marrow and the lymphatic system. Chronic Myeloid Leukemia (CML) is a type of blood cancer that causes the body to produce a large number of white blood cells. In this research, FISH (Florescent In Situ Hybridization) images is the key factor of detecting abnormalities in genes. FISH usually used for detecting abnormality in chromosomes and DNA features. CML also can be detected using FISH. CML diagnosis depends on the detection of fused Red and Green signals. Our approach first detects FISH signals, their colors, and then fusion between these colors. Moreover, number of fusions need to be counted in order to specify the proper treatment as the number of fusion is important in defining the severity of the case. We prepared our dataset for our own experiment and publish it online for research usage. Our approach experimental accuracy achieved 98% which prove the efficiency of the approach when compared to similar research.