Automatic Detection of Acute Lymphoblastic Leukemia Using Machine Learning
Authors
Ms. Lamis Bany Issa, Jordan University of Science and Technology, Irbid, Jordan Dr. Areen Al-Bashir, Jordan University of Science and Technology, Irbid, Jordan
Abstract
The identification of acute leukaemia blast cells in coloured microscopic images is a challenging task. Usually it is performed by visual assessment for microscopic images of blood samples. However, considering the quick advances in utilizing different image processing techniques; rapid and more accurate assessment can be achieved. Therefore, this paper proposed an enhanced automatic method to detect Acute Lymphoblastic Leukemia (ALL) utilizing microscopic blood sample images.
Our proposed methodology includes; Colour-based segmentation using K-Means clustering technique together with morphological operations and feature extraction algorithms and finally cell classification. The proposed method was tested on blood microscopic images from ALL-IDB1 database, University of Milano, Italy. ALL_IDB1 comprises of 108 blood cells images (healthy and leukaemia) in which the lymphocytes are lapelled by expert oncologists. The accuracy achieved was 96.3%. this relatively high accuracy suggests that the Colour-based method for segmentation was more efficient and acceptable compared to the traditional thresholding methods and the methods that not considered the overlapped cells.
1st International Conference on Electrical Engineering and Technologies (ElectriTek 2020)
Congress
International Congress on Engineering Technologies (EngiTek 2020), 16-18 June 2020, Irbid, Jordan
Pages
--1
Topics
Biomedical Signal Processing Biomedical Imaging Systems
ISSN
2227-331X
DOI
BibTeX
@inproceedings{1130EngiTek2020,
title={Automatic Detection of Acute Lymphoblastic Leukemia Using Machine Learning},
author={Lamis Bany Issa, and Areen Al-Bashir},
booktitle={International Congress on Engineering Technologies (EngiTek 2020)},
year={2020},
pages={--1},
doi={}},
organization={Mosharaka for Research and Studies}
}