Segmentation of Leukemia Cells Using Clustering: A Comparative Study

Segmentation of Leukemia Cells Using Clustering: A Comparative Study

Eman Mostafa (Shoubra University, Cairo, Egypt) and Heba A. Tag El-Dien (Shoubra University, Cairo, Egypt)
Copyright: © 2019 |Pages: 10
DOI: 10.4018/IJSE.2019070103
OnDemand PDF Download:
No Current Special Offers


Leukemia is a blood cancer which is defined as an irregular augment of undeveloped white blood cells called “blasts.” It develops in the bone marrow, which is responsible for blood cell generation including leukocytes and white blood cells. The early diagnosis of leukemia greatly helps in the treatment. Accordingly, researchers are interested in developing advanced and accurate automated techniques for localizing such abnormal blood cells. Subsequently, image segmentation becomes an important image processing stage for successful feature extraction and classification of leukemia in further stages. It aims to separate cancer cells by segmenting the microscopic image into background and cancer cells that are known as the region of interested (ROI). In this article, the cancer blood cells were segmented using two separated clustering techniques, namely the K-means and Fuzzy-c-means techniques. Then, the results of these techniques were compared to in terms of different segmentation metrics, such as the Dice, Jac, specificity, sensitivity, and accuracy. The results proved that the k-means provided better performance in leukemia blood cells segmentation as it achieved an accuracy of 99.8% compared to 99.6% with the fuzzy c-means.
Article Preview


Human blood is classified into white blood cells (WBCs), red blood cells (RBCs), and platelets (Liu et al., 2019). Leukemia is a wide category of cancers that influence white blood cells. Generally, white blood cells can be classified into five categories, namely neutrophils, eosinophils, basophils, lymphocytes, and monocyte. Leukemia can prevent white blood cells from battling diseases and causes them to duplicate wildly, which leads to critical health problems that threatens the patient's life (Chatap, & Shibu, 2014). It has two main categories, including acute leukemia and chronic leukemia. Acute leukemia is diagnosed when the larger part of the influenced white blood cells cannot work normally, causing fast degeneration, while chronic leukemia is diagnosed when a few of the influenced blood cells cannot work regularly, causing a slower degeneration. Furthermore, acute leukemia is sub-categorized into acute lymphocytic leukemia (ALL) and acute myeloid leukemia (AML), whereas chronic leukemia is sub-categorized into chronic lymphocytic leukemia (CLL) and chronic myeloid leukemia (CML).

Manual detection methods of leukemia depend on the physician experience and naked eye inspection which are inaccurate and time consuming. Thus, recently automated detection methods are used. The segmentation of cancer cell images has a direct effect on the classification process, which in turn helps in the process of diagnosis and treatment. Mainly, there are four basic processes for image in computer-aided diagnoses which are image acquisition, image preprocessing, and image segmentation in addition to image classification. Generally, image segmentation is a significant process in image processing, which divides the whole image into several regions for extracting the region of interest. In the microscopic blood samples, the blast cell is extracted for leukemia detection.

The blood cell segmentation is considered a challenging task due to the cells’ complex morphology, including shape, texture, color and size. In addition to the ambiguity, uncertainty, and inconsistencies in the captured microscopic images with varying illumination, as well as the existence of overlapping between the cells (Reyes et al., 2015). Thus, a highly efficient method is required for segmentation of leukemia blood cell. There are several types of image segmentation, such as watershed, edge-based, threshold, region-based, and clustering methods. The cluster method includes different methods for example K-means, fuzzy c-means (FCM), hierarchical clustering, and model-based clustering (Dhanachandra, & Chanu, 2017). In the present work, the performance of k-means and FCM clustering methods is investigated.

Complete Article List

Search this Journal:
Open Access Articles
Volume 13: 2 Issues (2022): Forthcoming, Available for Pre-Order
Volume 12: 2 Issues (2021): Forthcoming, Available for Pre-Order
Volume 11: 2 Issues (2020)
Volume 10: 2 Issues (2019)
Volume 9: 2 Issues (2018)
Volume 8: 2 Issues (2017)
Volume 7: 2 Issues (2016)
Volume 6: 2 Issues (2015)
Volume 5: 2 Issues (2014)
Volume 4: 2 Issues (2013)
Volume 3: 2 Issues (2012)
Volume 2: 2 Issues (2011)
Volume 1: 2 Issues (2010)
View Complete Journal Contents Listing