PERHITUNGAN DAN PEMISAHAN SEL DARAH PUTIH BERDASARKAN CENTROID DENGAN MENGGUNAKAN METODE MULTI PASS VOTING DAN K-MEANS PADA CITRA SEL ACUTE LEUKEMIA

• Main Authors: Nursanti Novi Arisa, Chastine Fatichah
• Format: Article
• Language: English
• Published: Institut Teknologi Sepuluh Nopember 2018-10-01
• Series: JUTI: Jurnal Ilmiah Teknologi Informasi
• Online Access: http://juti.if.its.ac.id/index.php/juti/article/view/661
• ISSN: 1412-6389; 2406-8535

<p><em>Leukemia is one of the dangerous diseases that can cause death. One of the types of leukemia is acute leukemia that includes ALL (</em><em>A</em><em>cute </em><em>L</em><em>ymphoblastic </em><em>L</em><em>eukemia) and AML (Acute Myeloid Leukemia). The fastest identification against this disease can be done by computing and analysing white blood cell types. However, the manual c</em><em>ounting</em><em> and identification of the white blood cell types are still limited by time. Therefore, automatic counting process is necessary to be conducted in order to get the results more quickly and accurately. Previous studies showed that automatic counting process in the image of Acute Leukemia cells faced some obstacles, the existence of touching cell and the implementation of  geometry feature that cannot produce an accurate counting. It is because the shapes of the cell are various. This study proposed a method for the counting of white blood cells and the separation of touching cells on Acute Leukemia cells image by using Multi Pass Voting method (MPV) based on seed detection (centroid) and K-Means method. Initial segmentation used for separating foreground and background area is canny edge detection. The next stage is seed detection (centroid) using Multi Pass Voting method. The co</em><em>unting</em><em> of white blood cells is based on the results of the centroid produced. The existence of the touching cells are  separated using K-Means method, the determination of the initial centroid  is based on the results of the Multi Pass Voting method. Based on the evaluation results of 40 images of Acute Leukemia dataset, the proposed method is capable to properly compute based on the centroid. It is also able to separate the touching cell into a single cell. The accuracy of the white blood cell counting </em><em>result</em><em> is about 98,6%.</em><em></em></p>