Published : 2016-07-15

Feature Selection Methods in Image-Based Screening for the Detection of Hashimoto’s Thyroiditis in First-Contact Hospitals

Zbigniew Omiotek



Andrzej Burda



Abstract

In this paper, results of dimension reduction in feature space for thyroid ultrasound images using the heuristic identification of noisy variables, testing the significance of correlation coefficients and the method of Hellwig index of information capacity, have been compared. The best results were achieved using the Hellwig method. It enabled us to choose only 3 features from a large set of 283 discriminant ones. Classifiers built on the basis of this reduced set of features have the highest classification sensitivity (0,82 ) and the highest classification specificity (0,83 ) in comparison to other reduced datasets that we used in our research. Results showed that the Hellwig method can be used as an effective process for dimension reduction in feature space in classification of thyroid ultrasound images.

Keywords:

feature selection, texture classification, HINoV, Hellwig method, Spearman correlation, Hashimoto’s thyroiditis


Most read articles by the same author(s)

1 2 > >> 

Details

References

Statistics

Authors

Download files

PDF (Język Polski)

Citation rules

Omiotek, Z., & Burda, A. (2016). Feature Selection Methods in Image-Based Screening for the Detection of Hashimoto’s Thyroiditis in First-Contact Hospitals. Regional Barometer. Analyses & Prognoses, 14(2), 187–196. https://doi.org/10.56583/br.618

Altmetric indicators


Cited by / Share


Publisher
Wydawnictwo Akademii Zamojskiej
ul. Pereca 2, 22-400 Zamość
tel.: +48 84/638 34 44;
tel. kom. +48/ 790 331 087
fax: +48 84/ 638 35 00
University
Akademia Zamojska
ul. Pereca 2, 22-400 Zamość
tel. 84 638 34 44
fax 84 638 35 00
e-mail: rektorat@akademiazamojska.edu.pl
About:
Copyright 2021 by
OJS Support and Customization by LIBCOM
Platform & workfow by OJS/PKP