A Fast Segmentation Scheme for Acute Lymphoblastic Leukemia Detection
In medical diagnosis systems, the classification of blood cells is essential for the evaluation and diagnosis of many diseases. Acute Lymphoblastic Leukemia (ALL) is the childhood blood cancer mostly found in children below 7-8 years. It can be fatal if left untreated. ALL cells are abnormal lymphocytes and have a condensed appearance to their chromatin. Through the analysis of white blood cells (WBCs) also called as leukocytes, the ALL can be detected. Presently the morphological analysis of blood cells is performed manually by skilled operators. This involves numerous drawbacks, such as slow analysis and a non-standard accuracy. It all depends on the skills of the operator. In the literature there are many examples of automated systems in order to analyze and classify the blood cells, most of which are only partial. This paper presents complete and fully automatic method for WBCs identification and classification of blasts cells from microscopic images. The proposed method is to segment normal and ALL lymphocytes from other blood cell components and to find out nuclei of blasts cells. The technique for segmentation used is Otsu’s thresholding algorithm. The whole work has been developed using MATLAB environment.
Mrs. Trupti A. Kulkarni-Joshi, Prof. Dilip S. Bhosale