Classification of White Blood Cell Abnormalities for Early Detection of Myeloproliferative Neoplasms Syndrome Based on K-Nearest Neighborr

Scientific Journal of Informatics

Zilvanhisna Emka Fitri¹  Lindri Nalentine Yolanda Syahputri¹  Arizal Mujibtamala Nanda Imron² 

[1] Politeknik Negeri Jember;Universitas Jember;

关键词: mpns;    wbc abnormalities;    cielab;    thresholding;    knn;   

DOI  :  10.15294/sji.v7i1.24372

来源: DOAJ

【 摘 要 】

The myeloproliferative neoplasms (MPNs) are clonal hematopoietic stem cell disorders characterized by dysregulated proliferation and expansion of one or more of the myeloid lineages. The initial symptoms of MPN is a bone marrow abnormalities when producing red blood cells, white blood cells and platelets in large numbers and uncontrolled. An automatic and accurate white blood cell abnormality classification system is needed. This research uses digital image processing techniques such as conversion to the modified CIELab color space, segmentation techniques based on threshold values and feature extraction processes that produce four morphological features consisting of area, perimeter, metric and compactness. then the four features become input to the K-Nearest Neighborr (KNN) method. The testing process is based on variations in the value of K to get the best accuracy percentage of 94.3% tested on 159 test data.

【 授权许可】

Unknown