Texture Features for the Detection of Acute Lymphoblastic Leukemia
Acute Lymphoblastic Leukemia (ALL) is a cancer of the blood or bone marrow. Detection of ALL is usually done by skilled pathologists, automatic detection of leukemia will reduce the diagnosis time and will also be independent of the skills of the patholog
- PDF / 207,476 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 94 Downloads / 209 Views
Abstract Acute Lymphoblastic Leukemia (ALL) is a cancer of the blood or bone marrow. Detection of ALL is usually done by skilled pathologists, automatic detection of leukemia will reduce the diagnosis time and will also be independent of the skills of the pathologist. In this paper, we propose using texture descriptors extracted from the nucleus image for detection of ALL. The disease causes change in the chromatin distribution of the nucleus, which can be observed in the form of texture. We have used two texture features, namely Local Binary pattern and Gray Level Co-occurrence Matrix for automatic detection of ALL. A comparative analysis of both the features is presented. It is seen that LBP features perform better than GLCM features. Keywords Blast
Texture Leukemia
1 Introduction Leukemia is a cancer of blood or bone marrow which is caused due to increase in number of immature white blood cells (WBC). WBC form the immune system of the human body and disturbance in the population of these cells causes many health problems [1]. Leukemia can be classified into four categories: Acute lymphoblastic Leukemia (ALL), Chronic Lymphoblastic Leukemia (CLL), Acute Myelogenous Leukemia (AML) and Chronic Myelogenous Leukemia (CML). The classification (acute or chronic) is based on the time span in which the disease progresses and the type of WBC affected by the disease (lymphocyte or myeloid) [2]. V. Singhal (&) Manipal University, Jaipur, India e-mail: [email protected] P. Singh The LNM Institute of Information Technology, Jaipur, India e-mail: [email protected] © Springer Science+Business Media Singapore 2016 S.C. Satapathy et al. (eds.), Proceedings of International Conference on ICT for Sustainable Development, Advances in Intelligent Systems and Computing 409, DOI 10.1007/978-981-10-0135-2_52
535
536
V. Singhal and P. Singh
ALL is caused due to rapid increase in the number of immature lymphocytes called blasts. ALL accounts for 80 % of childhood leukemia and is mostly found in the age group of 2–5 years [3]. The diagnosis of the disease is difficult as the symptoms of ALL are common to other health disorders like fever, anemia, weakness, joint pain, etc. The manual method for detection of ALL includes the inspection of the blood or bone marrow sample under a microscope by a skilled pathologist [1]. This method of diagnosis is time-consuming and subjective as it depends on the skills of the pathologist. Automation of this process can help in reducing the detection time and also be beneficial for remote diagnosis. The basic difference between normal and blast cells is based on the changes in shape, size and changes in the chromatin pattern in the nucleus [4]. The normal lymphocytes are regular in shape and smaller in size as compared to blast cells. Changes in chromatin distribution can be visualized as texture of nucleus. Thus, texture of nucleus can be used for discrimination between normal and blast cells. Many methods have been proposed in literature for automatic detection of ALL. Asadi et al. [2] use zerni
Data Loading...
