Classification of chronic myeloid leukemia cell subtypes based on microscopic image analysis
Loading...
Date
2019-06-14
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This paper presents a simple and efficient computer-aided diagnosis method to classify Chronic Myeloid Leukemia
(CML) cells based on microscopic image processing. In the proposed method, a novel combination of both typical
and new features is introduced for cl
assification of CML cells. Next, an eff
ective decision tree classifier is pro-
posed to classify CML cells into eight groups. The proposed method was evaluated on 1730 CML cell images
containing 714 cells of non-cancerous bone marrow aspiration and 1016 cells of cancerous peripheral blood
smears. The performance of
the proposed classification method was compared to manual labels made by two
experts. The average values of accuracy
, specificity and sensitivity
were 99.0 %, 99.4 % and 98.3 %, respectively
for all groups of CML. In addition, Cohen's kappa coefficient demonstrated high conformity, 0.99, between joint
diagnostic results of two experts and the obtained results of the proposed approach. According to the obtained
results, the suggested method has a high capability to cla
ssify effective cells of CM
L and can be applied as a
simple, affordable and reliable computer-aided diagnosis tool to help pathologists to diagnose CML.
Description
Table of contents
Keywords
Chronic Myeloid Leukemia (CML), Blood cancer, Microscopic image processing, Classification, Decision tree classifier