Automatic recognition of five types of white blood cells in peripheral blood

Seyed Hamid Rezatofighi; Kosar Khaksari; Hamid Soltanian-Zadeh

doi:10.1007/978-3-642-13775-4_17

Automatic recognition of five types of white blood cells in peripheral blood

Seyed Hamid Rezatofighi, Kosar Khaksari, Hamid Soltanian-Zadeh

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

35 Citations (Scopus)

Abstract

An automatic system which is capable of recognizing white blood cells can assist hematologists in the diagnosis of many diseases. In this paper, we propose a new system based on image processing techniques in order to recognize five types of white blood cells in the peripheral blood. To segment nucleus and cytoplasm, a Gram-Schmidt orthogonalization method and a snake algorithm are applied, respectively. Moreover, three kinds of features are extracted from the segmented areas and two groups of textural features extracted by Local Binary Pattern (LBP) and co-occurrence matrix are evaluated. Best features are selected using a Sequential Forward Selection (SFS) algorithm and performances of two classifiers, ANN and SVM, are compared. In this application, the best result is obtained using LBP as the textural feature and SVM as the classifier. In sum, the results demonstrate that the methods are accurate and fast enough to execute in hematological laboratories.

Original language	English
Title of host publication	Image Analysis and Recognition - 7th International Conference, ICIAR 2010, Proceedings
Publisher	Springer
Pages	161-172
Number of pages	12
Edition	PART 2
ISBN (Print)	3642137741, 9783642137747
DOIs	https://doi.org/10.1007/978-3-642-13775-4_17
Publication status	Published - 2010
Externally published	Yes
Event	International Conference on Image Analysis and Recognition 2010 - Povoa de Varzim, Portugal Duration: 21 Jun 2010 → 23 Jun 2010 Conference number: 7th

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Number	PART 2
Volume	6112
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	International Conference on Image Analysis and Recognition 2010
Abbreviated title	ICIAR 2010
Country/Territory	Portugal
City	Povoa de Varzim
Period	21/06/10 → 23/06/10

Keywords

classification
feature selection
peripheral blood
segmentation
textural feature
White blood cell

Access to Document

10.1007/978-3-642-13775-4_17

Cite this

Rezatofighi, S. H., Khaksari, K., & Soltanian-Zadeh, H. (2010). Automatic recognition of five types of white blood cells in peripheral blood. In Image Analysis and Recognition - 7th International Conference, ICIAR 2010, Proceedings (PART 2 ed., pp. 161-172). (Lecture Notes in Computer Science ; Vol. 6112, No. PART 2). Springer. https://doi.org/10.1007/978-3-642-13775-4_17

@inproceedings{4b30881fb0a34812ae66904619937141,

title = "Automatic recognition of five types of white blood cells in peripheral blood",

abstract = "An automatic system which is capable of recognizing white blood cells can assist hematologists in the diagnosis of many diseases. In this paper, we propose a new system based on image processing techniques in order to recognize five types of white blood cells in the peripheral blood. To segment nucleus and cytoplasm, a Gram-Schmidt orthogonalization method and a snake algorithm are applied, respectively. Moreover, three kinds of features are extracted from the segmented areas and two groups of textural features extracted by Local Binary Pattern (LBP) and co-occurrence matrix are evaluated. Best features are selected using a Sequential Forward Selection (SFS) algorithm and performances of two classifiers, ANN and SVM, are compared. In this application, the best result is obtained using LBP as the textural feature and SVM as the classifier. In sum, the results demonstrate that the methods are accurate and fast enough to execute in hematological laboratories.",

keywords = "classification, feature selection, peripheral blood, segmentation, textural feature, White blood cell",

author = "Rezatofighi, {Seyed Hamid} and Kosar Khaksari and Hamid Soltanian-Zadeh",

year = "2010",

doi = "10.1007/978-3-642-13775-4_17",

language = "English",

isbn = "3642137741",

series = "Lecture Notes in Computer Science ",

publisher = "Springer",

number = "PART 2",

pages = "161--172",

booktitle = "Image Analysis and Recognition - 7th International Conference, ICIAR 2010, Proceedings",

edition = "PART 2",

note = "International Conference on Image Analysis and Recognition 2010, ICIAR 2010 ; Conference date: 21-06-2010 Through 23-06-2010",

}

Rezatofighi, SH, Khaksari, K & Soltanian-Zadeh, H 2010, Automatic recognition of five types of white blood cells in peripheral blood. in Image Analysis and Recognition - 7th International Conference, ICIAR 2010, Proceedings. PART 2 edn, Lecture Notes in Computer Science , no. PART 2, vol. 6112, Springer, pp. 161-172, International Conference on Image Analysis and Recognition 2010, Povoa de Varzim, Portugal, 21/06/10. https://doi.org/10.1007/978-3-642-13775-4_17

Automatic recognition of five types of white blood cells in peripheral blood. / Rezatofighi, Seyed Hamid; Khaksari, Kosar; Soltanian-Zadeh, Hamid.
Image Analysis and Recognition - 7th International Conference, ICIAR 2010, Proceedings. PART 2. ed. Springer, 2010. p. 161-172 (Lecture Notes in Computer Science ; Vol. 6112, No. PART 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Automatic recognition of five types of white blood cells in peripheral blood

AU - Rezatofighi, Seyed Hamid

AU - Khaksari, Kosar

AU - Soltanian-Zadeh, Hamid

N1 - Conference code: 7th

PY - 2010

Y1 - 2010

N2 - An automatic system which is capable of recognizing white blood cells can assist hematologists in the diagnosis of many diseases. In this paper, we propose a new system based on image processing techniques in order to recognize five types of white blood cells in the peripheral blood. To segment nucleus and cytoplasm, a Gram-Schmidt orthogonalization method and a snake algorithm are applied, respectively. Moreover, three kinds of features are extracted from the segmented areas and two groups of textural features extracted by Local Binary Pattern (LBP) and co-occurrence matrix are evaluated. Best features are selected using a Sequential Forward Selection (SFS) algorithm and performances of two classifiers, ANN and SVM, are compared. In this application, the best result is obtained using LBP as the textural feature and SVM as the classifier. In sum, the results demonstrate that the methods are accurate and fast enough to execute in hematological laboratories.

AB - An automatic system which is capable of recognizing white blood cells can assist hematologists in the diagnosis of many diseases. In this paper, we propose a new system based on image processing techniques in order to recognize five types of white blood cells in the peripheral blood. To segment nucleus and cytoplasm, a Gram-Schmidt orthogonalization method and a snake algorithm are applied, respectively. Moreover, three kinds of features are extracted from the segmented areas and two groups of textural features extracted by Local Binary Pattern (LBP) and co-occurrence matrix are evaluated. Best features are selected using a Sequential Forward Selection (SFS) algorithm and performances of two classifiers, ANN and SVM, are compared. In this application, the best result is obtained using LBP as the textural feature and SVM as the classifier. In sum, the results demonstrate that the methods are accurate and fast enough to execute in hematological laboratories.

KW - classification

KW - feature selection

KW - peripheral blood

KW - segmentation

KW - textural feature

KW - White blood cell

UR - http://www.scopus.com/inward/record.url?scp=77955411482&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-13775-4_17

DO - 10.1007/978-3-642-13775-4_17

M3 - Conference Paper

AN - SCOPUS:77955411482

SN - 3642137741

SN - 9783642137747

T3 - Lecture Notes in Computer Science

SP - 161

EP - 172

BT - Image Analysis and Recognition - 7th International Conference, ICIAR 2010, Proceedings

PB - Springer

T2 - International Conference on Image Analysis and Recognition 2010

Y2 - 21 June 2010 through 23 June 2010

ER -

Automatic recognition of five types of white blood cells in peripheral blood

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this