1 3
Med Biol Eng Comput
DOI 10.1007/s11517-015-1267-x
ORIGINAL ARTICLE
Erythrocyte shape classification using integral-geometry-based
methods
X. Gual-Arnau
1
· S. Herold-García
2
· A. Simó
3
Received: 2 May 2013 / Accepted: 2 March 2015
© International Federation for Medical and Biological Engineering 2015
with other deformations present in the images. A process of
automatic classification, with cross-validation of errors with
the proposed descriptors and with other two functions used
in previous studies, was realized.
Keywords Contour functions · Erythrocytes ·
Shape classification · Integral geometry
1 Introduction
Sickle cell disease (SCD) is one of the most common
genetic diseases and has been recognized as a major public
health problem by international agencies, such as the World
Health Organization (WHO) and the United Nations Edu-
cational, Scientific and Cultural Organization (UNESCO).
SCD causes the hardening or polymerization of the hemo-
globin that contains the erythrocytes, leading to sickle-
shaped red blood cells. Sickle-shaped means that the eryth-
rocytes are shaped like a crescent. Sickle cells tend to block
blood flow in the blood vessels and result in a risk of vari-
ous complications, for example the risk of vaso-occlusive
crisis. The patients that have this disease are classified into
three types: those with a benignant form, who do not have
pain crisis, those with a moderate form, who only have one
crisis a year, and the seriously ill that have two or more cri-
ses per year. They all have deformed cells in their blood, in
lesser or greater quantity according to their condition. The
treatment depends on this condition, and in general, it is a
moisturizing treatment that does not cause collateral prob-
lems. If the patient is seriously ill, the quantity of elongated
cells is very high and he should receive anti-deforming
treatments, applied periodically.
Quantitative analysis of digital images has been applied
previously to the study and classification of erythrocytes,
Abstract Erythrocyte shape deformations are related to
different important illnesses. In this paper, we focus on one
of the most important: the Sickle cell disease. This disease
causes the hardening or polymerization of the hemoglobin
that contains the erythrocytes. The study of this process
using digital images of peripheral blood smears can offer
useful results in the clinical diagnosis of these illnesses.
In particular, it would be very valuable to find a rapid and
reproducible automatic classification method to quantify the
number of deformed cells and so gauge the severity of the
illness. In this paper, we show the good results obtained in
the automatic classification of erythrocytes in normal cells,
sickle cells, and cells with other deformations, when we use
a set of functions based on integral-geometry methods, an
active contour-based segmentation method, and a k-NN clas-
sification algorithm. Blood specimens were obtained from
patients with Sickle cell disease. Seventeen peripheral blood
smears were obtained for the study, and 45 images of differ-
ent fields were obtained. A specialist selected the cells to use,
determining those cells which were normal, elongated, and
* A. Simó
simo@uji.es
X. Gual-Arnau
gual@uji.es
S. Herold-García
silena@csd.uo.edu.cu
1
Institute of New Imaging Technologies, Universitat Jaume I,
12071 Castelló, Spain
2
Departamento de Computación, Universidad de Oriente,
Santiago de Cuba, Cuba
3
Institut Universitari de Matemàtiques i Aplicacions de
Castelló, Universitat Jaume I, Avda. del Riu Sec s/n,
12071 Castellón, Spain