HEp-2 cell classification in IIF images using Shareboost

I. Ersoy, F. Bunyak, Jing Peng, K. Palaniappan

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

35 Citations (Scopus)

Abstract

Indirect immunofluorescence (IIF) imaging is a method used for detection of antinuclear auto-antibodies (ANA) for the diagnosis of autoimmune diseases. We present a feature extraction and classification scheme to classify the fluorescence staining patterns of HEp-2 cells in IIF images. We propose a set of complementary features that are sensitive to staining pattern variations among classes. Our feature set utilizes local shape measures via Hessian matrix, gradient features using our adaptive robust structure tensors and texture features. We apply our multi-view ShareBoost algorithm to this set using each feature descriptor as a separate view. ShareBoost utilizes a single re-sampling distribution for all views that helps the classifier to exploit the interplay between subspaces and is robust to noisy labels. Our experimental results show an average of over 90 percent accuracy in classification of six HEp-2 cell types.

Original languageEnglish
Title of host publicationICPR 2012 - 21st International Conference on Pattern Recognition
Pages3362-3365
Number of pages4
StatePublished - 1 Dec 2012
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: 11 Nov 201215 Nov 2012

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Other

Other21st International Conference on Pattern Recognition, ICPR 2012
CountryJapan
CityTsukuba
Period11/11/1215/11/12

Fingerprint

Antibodies
Tensors
Feature extraction
Labels
Classifiers
Textures
Fluorescence
Sampling
Imaging techniques

Cite this

Ersoy, I., Bunyak, F., Peng, J., & Palaniappan, K. (2012). HEp-2 cell classification in IIF images using Shareboost. In ICPR 2012 - 21st International Conference on Pattern Recognition (pp. 3362-3365). [6460885] (Proceedings - International Conference on Pattern Recognition).
Ersoy, I. ; Bunyak, F. ; Peng, Jing ; Palaniappan, K. / HEp-2 cell classification in IIF images using Shareboost. ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. pp. 3362-3365 (Proceedings - International Conference on Pattern Recognition).
@inproceedings{32b4629b16794f62b48b55ca93a61c47,
title = "HEp-2 cell classification in IIF images using Shareboost",
abstract = "Indirect immunofluorescence (IIF) imaging is a method used for detection of antinuclear auto-antibodies (ANA) for the diagnosis of autoimmune diseases. We present a feature extraction and classification scheme to classify the fluorescence staining patterns of HEp-2 cells in IIF images. We propose a set of complementary features that are sensitive to staining pattern variations among classes. Our feature set utilizes local shape measures via Hessian matrix, gradient features using our adaptive robust structure tensors and texture features. We apply our multi-view ShareBoost algorithm to this set using each feature descriptor as a separate view. ShareBoost utilizes a single re-sampling distribution for all views that helps the classifier to exploit the interplay between subspaces and is robust to noisy labels. Our experimental results show an average of over 90 percent accuracy in classification of six HEp-2 cell types.",
author = "I. Ersoy and F. Bunyak and Jing Peng and K. Palaniappan",
year = "2012",
month = "12",
day = "1",
language = "English",
isbn = "9784990644109",
series = "Proceedings - International Conference on Pattern Recognition",
pages = "3362--3365",
booktitle = "ICPR 2012 - 21st International Conference on Pattern Recognition",

}

Ersoy, I, Bunyak, F, Peng, J & Palaniappan, K 2012, HEp-2 cell classification in IIF images using Shareboost. in ICPR 2012 - 21st International Conference on Pattern Recognition., 6460885, Proceedings - International Conference on Pattern Recognition, pp. 3362-3365, 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, 11/11/12.

HEp-2 cell classification in IIF images using Shareboost. / Ersoy, I.; Bunyak, F.; Peng, Jing; Palaniappan, K.

ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. p. 3362-3365 6460885 (Proceedings - International Conference on Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

TY - GEN

T1 - HEp-2 cell classification in IIF images using Shareboost

AU - Ersoy, I.

AU - Bunyak, F.

AU - Peng, Jing

AU - Palaniappan, K.

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Indirect immunofluorescence (IIF) imaging is a method used for detection of antinuclear auto-antibodies (ANA) for the diagnosis of autoimmune diseases. We present a feature extraction and classification scheme to classify the fluorescence staining patterns of HEp-2 cells in IIF images. We propose a set of complementary features that are sensitive to staining pattern variations among classes. Our feature set utilizes local shape measures via Hessian matrix, gradient features using our adaptive robust structure tensors and texture features. We apply our multi-view ShareBoost algorithm to this set using each feature descriptor as a separate view. ShareBoost utilizes a single re-sampling distribution for all views that helps the classifier to exploit the interplay between subspaces and is robust to noisy labels. Our experimental results show an average of over 90 percent accuracy in classification of six HEp-2 cell types.

AB - Indirect immunofluorescence (IIF) imaging is a method used for detection of antinuclear auto-antibodies (ANA) for the diagnosis of autoimmune diseases. We present a feature extraction and classification scheme to classify the fluorescence staining patterns of HEp-2 cells in IIF images. We propose a set of complementary features that are sensitive to staining pattern variations among classes. Our feature set utilizes local shape measures via Hessian matrix, gradient features using our adaptive robust structure tensors and texture features. We apply our multi-view ShareBoost algorithm to this set using each feature descriptor as a separate view. ShareBoost utilizes a single re-sampling distribution for all views that helps the classifier to exploit the interplay between subspaces and is robust to noisy labels. Our experimental results show an average of over 90 percent accuracy in classification of six HEp-2 cell types.

UR - http://www.scopus.com/inward/record.url?scp=84874572947&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9784990644109

T3 - Proceedings - International Conference on Pattern Recognition

SP - 3362

EP - 3365

BT - ICPR 2012 - 21st International Conference on Pattern Recognition

ER -

Ersoy I, Bunyak F, Peng J, Palaniappan K. HEp-2 cell classification in IIF images using Shareboost. In ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. p. 3362-3365. 6460885. (Proceedings - International Conference on Pattern Recognition).