An Automatic HEp-2 Specimen Analysis System Based on an Active Contours Model and an SVM Classification
The antinuclear antibody (ANA) test is widely used for screening, diagnosing, and monitoring of autoimmune diseases. The most common methods to determine ANA are indirect immunofluorescence (IIF), performed by human epithelial type 2 (HEp-2) cells, as substrate antigen. The evaluation of ANA consist...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | http://www.mdpi.com/2076-3417/9/2/307 |
_version_ | 1811219426874228736 |
---|---|
author | Donato Cascio Vincenzo Taormina Giuseppe Raso |
author_facet | Donato Cascio Vincenzo Taormina Giuseppe Raso |
author_sort | Donato Cascio |
collection | DOAJ |
description | The antinuclear antibody (ANA) test is widely used for screening, diagnosing, and monitoring of autoimmune diseases. The most common methods to determine ANA are indirect immunofluorescence (IIF), performed by human epithelial type 2 (HEp-2) cells, as substrate antigen. The evaluation of ANA consist an analysis of fluorescence intensity and staining patterns. This paper presents a complete and fully automatic system able to characterize IIF images. The fluorescence intensity classification was obtained by performing an image preprocessing phase and implementing a Support Vector Machines (SVM) classifier. The cells identification problem has been addressed by developing a flexible segmentation methods, based on the Hough transform for ellipses, and on an active contours model. In order to classify the HEp-2 cells, six SVM and one k-nearest neighbors (KNN)classifiers were developed. The system was tested on a public database consisting of 2080 IIF images. Unlike almost all work presented on this topic, the proposed system automatically addresses all phases of the HEp-2 image analysis process. All results have been evaluated by comparing them with some of the most representative state-of-the-art work, demonstrating the goodness of the system in the characterization of HEp-2 images. |
first_indexed | 2024-04-12T07:26:42Z |
format | Article |
id | doaj.art-145fd4a8c8c24201aaa58a06822fb36f |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-04-12T07:26:42Z |
publishDate | 2019-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-145fd4a8c8c24201aaa58a06822fb36f2022-12-22T03:42:11ZengMDPI AGApplied Sciences2076-34172019-01-019230710.3390/app9020307app9020307An Automatic HEp-2 Specimen Analysis System Based on an Active Contours Model and an SVM ClassificationDonato Cascio0Vincenzo Taormina1Giuseppe Raso2Department of Physics and Chemistry, University of Palermo, 90128 Palermo, ItalyDepartment of Physics and Chemistry, University of Palermo, 90128 Palermo, ItalyDepartment of Physics and Chemistry, University of Palermo, 90128 Palermo, ItalyThe antinuclear antibody (ANA) test is widely used for screening, diagnosing, and monitoring of autoimmune diseases. The most common methods to determine ANA are indirect immunofluorescence (IIF), performed by human epithelial type 2 (HEp-2) cells, as substrate antigen. The evaluation of ANA consist an analysis of fluorescence intensity and staining patterns. This paper presents a complete and fully automatic system able to characterize IIF images. The fluorescence intensity classification was obtained by performing an image preprocessing phase and implementing a Support Vector Machines (SVM) classifier. The cells identification problem has been addressed by developing a flexible segmentation methods, based on the Hough transform for ellipses, and on an active contours model. In order to classify the HEp-2 cells, six SVM and one k-nearest neighbors (KNN)classifiers were developed. The system was tested on a public database consisting of 2080 IIF images. Unlike almost all work presented on this topic, the proposed system automatically addresses all phases of the HEp-2 image analysis process. All results have been evaluated by comparing them with some of the most representative state-of-the-art work, demonstrating the goodness of the system in the characterization of HEp-2 images.http://www.mdpi.com/2076-3417/9/2/307IIF imagesHough transformactive contours modelcell segmentationSVMKNNROC curve |
spellingShingle | Donato Cascio Vincenzo Taormina Giuseppe Raso An Automatic HEp-2 Specimen Analysis System Based on an Active Contours Model and an SVM Classification Applied Sciences IIF images Hough transform active contours model cell segmentation SVM KNN ROC curve |
title | An Automatic HEp-2 Specimen Analysis System Based on an Active Contours Model and an SVM Classification |
title_full | An Automatic HEp-2 Specimen Analysis System Based on an Active Contours Model and an SVM Classification |
title_fullStr | An Automatic HEp-2 Specimen Analysis System Based on an Active Contours Model and an SVM Classification |
title_full_unstemmed | An Automatic HEp-2 Specimen Analysis System Based on an Active Contours Model and an SVM Classification |
title_short | An Automatic HEp-2 Specimen Analysis System Based on an Active Contours Model and an SVM Classification |
title_sort | automatic hep 2 specimen analysis system based on an active contours model and an svm classification |
topic | IIF images Hough transform active contours model cell segmentation SVM KNN ROC curve |
url | http://www.mdpi.com/2076-3417/9/2/307 |
work_keys_str_mv | AT donatocascio anautomatichep2specimenanalysissystembasedonanactivecontoursmodelandansvmclassification AT vincenzotaormina anautomatichep2specimenanalysissystembasedonanactivecontoursmodelandansvmclassification AT giusepperaso anautomatichep2specimenanalysissystembasedonanactivecontoursmodelandansvmclassification AT donatocascio automatichep2specimenanalysissystembasedonanactivecontoursmodelandansvmclassification AT vincenzotaormina automatichep2specimenanalysissystembasedonanactivecontoursmodelandansvmclassification AT giusepperaso automatichep2specimenanalysissystembasedonanactivecontoursmodelandansvmclassification |