DocumentCode :
1759072
Title :
High-Order Statistics of Microtexton for HEp-2 Staining Pattern Classification
Author :
Xian-Hua Han ; Jian Wang ; Gang Xu ; Yen-Wei Chen
Author_Institution :
Coll. of Inf. Sci. & Eng., Ritsumeikan Univ., Kasatsu, Japan
Volume :
61
Issue :
8
fYear :
2014
fDate :
Aug. 1 2014
Firstpage :
2223
Lastpage :
2234
Abstract :
This study addresses the classification problem of the HEp-2 cell using indirect immunofluorescent (IIF) image analysis, which can indicate the presence of autoimmune diseases by finding antibodies in the patient serum. Generally, the method used for IIF analysis remains subjective, and depends too heavily on the experience and expertise of the physician. Recently, studies have shown that it is possible to identify the cell patterns using IIF image analysis and machine learning techniques. However, it still has large gap in recognition rates to the physical experts´ one. This paper explores an approach in which the discriminative features of HEp-2 cell images in IIF are extracted and then, the patterns of the HEp-2 cell are identified using machine learning techniques. Motivated by the progress in the research field of computer vision, as a result of which small local pixel pattern distributions can now be highly discriminative, the proposed strategy employs a parametric probability process to model local image patches (textons: microstructures in the cell image) and extract the higher-order statistics of the model parameters for the image description. The proposed strategy can adaptively characterize the microtexton space of HEp-2 cell images as a generative probability model, and discover the parameters that yield a better fitting of the training space, which would lead to a more discriminant representation for the cell image. The simple linear support vector machine is used for cell pattern identification because of its low computational cost, in particular for large-scale datasets. Experiments using the open HEp-2 cell dataset used in the ICIP2013 contest validate that the proposed strategy can achieve a much better performance than the widely used local binary pattern (LBP) histogram and its extensions, rotation invariant co-occurrence LBP, and pairwise rotation invariant co-occurrence LBP, and that the achieved recognition error rate is even very significant- y below the observed intralaboratory variability.
Keywords :
adaptive systems; biomedical optical imaging; cellular biophysics; diseases; feature extraction; fluorescence; higher order statistics; image classification; learning (artificial intelligence); medical image processing; probability; support vector machines; HEp-2 cell classification problem; HEp-2 cell image discriminative feature extraction; HEp-2 cell pattern identification; HEp-2 staining pattern classification; ICIP2013 contest; IIF image analysis; LBP histogram extensions; adaptively microtexton space characterization; autoimmune diseases; cell image discriminant representation; cell image microstructures; cell image textons; computational cost; computer vision research; generative probability model; high-order statistics; image description; indirect immunofluorescent image analysis; intralaboratory variability; large-scale datasets; linear support vector machine; local binary pattern histogram; local image patch modelling; local pixel pattern distribution discrimination; machine learning techniques; model parameters; open HEp-2 cell dataset; pairwise rotation invariant cooccurrence LBP; parametric probability process; patient serum antibodies; recognition error rate; recognition rates; subjective IIF analysis; training space fitting; Adaptation models; Feature extraction; Histograms; Image analysis; Image representation; Pattern recognition; Vectors; HEp-2 cell; high-order statistics; microtexton; mixture model of Gaussian; parametric probability model;
fLanguage :
English
Journal_Title :
Biomedical Engineering, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9294
Type :
jour
DOI :
10.1109/TBME.2014.2320294
Filename :
6805614
Link To Document :
بازگشت