Open AccessSegmentation of White Blood Cells and Lymphoblast Cells Using Moving K-Means
Author(s) -
Ika Candradewi,
Reno Ghaffur Bagasjvara
Publication year - 2018
Publication title -
ijeis (indonesian journal of electronics and instrumentation system)/ijeis (indonesian journal of electronics and instrumentation systems)
Language(s) - English
Resource type - Journals
eISSN - 2460-7681
pISSN - 2088-3714
DOI - 10.22146/ijeis.39734
Subject(s) - segmentation , lymphoblastic leukemia , lymphoblast , white blood cell , artificial intelligence , image segmentation , process (computing) , computer science , image processing , medicine , computer vision , pattern recognition (psychology) , leukemia , image (mathematics) , immunology , biology , cell culture , genetics , operating system
One of the diagnosis procedures for acute lymphoblastic leukemia is screening for blood cells by expert operator using microscope. This process is relatively long and will slow healing process of this disease which need fast treatment. Another way to screen this disease is by using digital image processing technique in microscopic image of blood smears to detect lymphoblast cells and types of white blood cells. One of essential step in digital image processing is segmentation because this process influences the subsequent process of detecting and classifying Acute Lymphoblastic Leukemia disease. This research performed segmentation of white blood cells using moving k-means algorithm. Some process are done to remove noise such as red blood cells and reduce detection errors such as white blood cells and/or lymphoblastic cell that’s appear overlap. Postprocessing are performed to improve segmentation quality and to separate connected white blood cell. The dataset in this study has been validated with expert clinical pathologists from Sardjito Regional General Hospital, Yogyakarta, Indonesia. This research produces systems performance with results in sensitivity of 85.6%, precision 82.3%, Fscore of 83,9% and accuracy of 72.3%. Based on the results of the testing process with a much larger number of datasets on the side of the variations level of cell segmentation difficulties both in terms of illumination and overlapping cell, the method proposed in this study was able to detect or segment overlapping white blood cells better.