Efficient k-NN based HEp-2 cells classifier

J 2014

Efficient k-NN based HEp-2 cells classifier

STOKLASA, Roman, Tomáš MAJTNER and David SVOBODA

Basic information

Original name

Efficient k-NN based HEp-2 cells classifier

Authors

STOKLASA, Roman (703 Slovakia, guarantor, belonging to the institution), Tomáš MAJTNER (703 Slovakia, belonging to the institution) and David SVOBODA (203 Czech Republic, belonging to the institution)

Edition

PATTERN RECOGNITION, OXFORD, PERGAMON-ELSEVIER SCIENCE LTD, 2014, 0031-3203

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United Kingdom of Great Britain and Northern Ireland

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 3.096

RIV identification code

RIV/00216224:14330/14:00073423

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1016/j.patcog.2013.09.021

UT WoS

000334978100012

Keywords in English

HEp-2 cells; Classifier; Image descriptor; Classification; Nearest neighbours; IIF; Indirect Immunofluorescence

Abstract

V originále

Human Epithelial (HEp-2) cells are commonly used in the Indirect Immunofluorescence (IIF) tests to detect autoimmune diseases. The diagnosis consists of searching and classification to specific patterns created by Anti-Nuclear Antibodies (ANAs) in the patient serum. Evaluation of the IIF test is mostly done by humans, which means that it is highly dependent on the experience and expertise of the physician. Therefore, a significant amount of research has been focused on the development of computer aided diagnostic systems which could help with the analysis of images from microscopes. This work deals with the design and development of HEp-2 cells classifier. The classifier is able to categorize pre-segmented images of HEp-2 cells into 6 classes. The core of this engine consists of the following image descriptors: Haralick features, Local Binary Patterns, SIFT, surface description and a granulometry-based descriptor. These descriptors produce vectors that form metric spaces. k-NN classification is based on aggregated distance function which combines several features together. An extensive set of evaluations was performed on the publicly available MIVIA HEp-2 images dataset which allows a direct comparison of our approach with other solutions. The results show that our approach is one of the leading classifiers when comparing with other participants in the HEp-2 Cells Classification Contest.

Links

GBP302/12/G157, research and development project

Name: Dynamika a organizace chromosomů během buněčného cyklu a při diferenciaci v normě a patologii

Investor: Czech Science Foundation

MUNI/A/0855/2013, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace III. (Acronym: FI MAV III.)

Investor: Masaryk University, Category A

Files attached

Efficient_k-NN_basedHEp-2cellsclassifier.pdf

Request the author's version of the file

Citovat

STOKLASA, Roman, Tomáš MAJTNER and David SVOBODA. Efficient k-NN based HEp-2 cells classifier. PATTERN RECOGNITION. OXFORD: PERGAMON-ELSEVIER SCIENCE LTD, 2014, vol. 47, No 7, p. 2409-2418. ISSN 0031-3203. Available from: https://dx.doi.org/10.1016/j.patcog.2013.09.021.

@article{1129437,
   author = {Stoklasa, Roman and Majtner, Tomáš and Svoboda, David},
   article_location = {OXFORD},
   article_number = {7},
   doi = {http://dx.doi.org/10.1016/j.patcog.2013.09.021},
   keywords = {HEp-2 cells; Classifier; Image descriptor; Classification; Nearest neighbours; IIF; Indirect Immunofluorescence},
   language = {eng},
   issn = {0031-3203},
   journal = {PATTERN RECOGNITION},
   title = {Efficient k-NN based HEp-2 cells classifier},
   url = {http://www.sciencedirect.com/science/article/pii/S0031320313003932},
   volume = {47},
   year = {2014}
}

TY  - JOUR
ID  - 1129437
AU  - Stoklasa, Roman - Majtner, Tomáš - Svoboda, David
PY  - 2014
TI  - Efficient k-NN based HEp-2 cells classifier
JF  - PATTERN RECOGNITION
VL  - 47
IS  - 7
SP  - 2409-2418
EP  - 2409-2418
PB  - PERGAMON-ELSEVIER SCIENCE LTD
SN  - 00313203
KW  - HEp-2 cells
KW  - Classifier
KW  - Image descriptor
KW  - Classification
KW  - Nearest neighbours
KW  - IIF
KW  - Indirect Immunofluorescence
UR  - http://www.sciencedirect.com/science/article/pii/S0031320313003932
N2  - Human Epithelial (HEp-2) cells are commonly used in the Indirect Immunofluorescence (IIF) tests to detect autoimmune diseases. The diagnosis consists of searching and classification to specific patterns created by Anti-Nuclear Antibodies (ANAs) in the patient serum. Evaluation of the IIF test is mostly done by humans, which means that it is highly dependent on the experience and expertise of the physician. Therefore, a significant amount of research has been focused on the development of computer aided diagnostic systems which could help with the analysis of images from microscopes. This work deals with the design and development of HEp-2 cells classifier. The classifier is able to categorize pre-segmented images of HEp-2 cells into 6 classes. The core of this engine consists of the following image descriptors: Haralick features, Local Binary Patterns, SIFT, surface description and a granulometry-based descriptor. These descriptors produce vectors that form metric spaces. k-NN classification is based on aggregated distance function which combines several features together. An extensive set of evaluations was performed on the publicly available MIVIA HEp-2 images dataset which allows a direct comparison of our approach with other solutions. The results show that our approach is one of the leading classifiers when comparing with other participants in the HEp-2 Cells Classification Contest.
ER  -

STOKLASA, Roman, Tomáš MAJTNER and David SVOBODA. Efficient k-NN based HEp-2 cells classifier. \textit{PATTERN RECOGNITION}. OXFORD: PERGAMON-ELSEVIER SCIENCE LTD, 2014, vol.~47, No~7, p.~2409-2418. ISSN~0031-3203. Available from: https://dx.doi.org/10.1016/j.patcog.2013.09.021.

Detailed Information on Publication Record