Early Breast Cancer Detection in Thermogram Images using AdaBoost Classifier and Fuzzy C-Means Clustering Algorithm
Background: In this paper we compare a highly accurate supervised to an unsupervised technique that uses breast thermal images with the aim of assisting physicians in early detection of breast cancer. Methods: First, we segmented the images and determined the region of interest. Then, 23 feature...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Shiraz University of Medical Sciences
2016-07-01
|
Series: | Middle East Journal of Cancer |
Subjects: | |
Online Access: | http://mejc.sums.ac.ir/index.php/mejc/article/view/381/259 |
id |
doaj-a4d7f7dd25954ed597dc38de6820419f |
---|---|
record_format |
Article |
spelling |
doaj-a4d7f7dd25954ed597dc38de6820419f2020-11-25T02:12:48ZengShiraz University of Medical SciencesMiddle East Journal of Cancer 2008-67092008-66872016-07-0173113124Early Breast Cancer Detection in Thermogram Images using AdaBoost Classifier and Fuzzy C-Means Clustering AlgorithmAmir Ehsan Lashkari0Mohammad Firouzmand1Department of Bio-Medical Engineering, Institute of Electrical Engineering & Information Technology, Iranian Research Organization for Science and Technology (IROST), Tehran, IranDepartment of Bio-Medical Engineering, Institute of Electrical Engineering & Information Technology, Iranian Research Organization for Science and Technology (IROST), Tehran, IranBackground: In this paper we compare a highly accurate supervised to an unsupervised technique that uses breast thermal images with the aim of assisting physicians in early detection of breast cancer. Methods: First, we segmented the images and determined the region of interest. Then, 23 features that included statistical, morphological, frequency domain, histogram and gray-level co-occurrence matrix based features were extracted from the segmented right and left breasts. To achieve the best features, feature selection methods such as minimum redundancy and maximum relevance, sequential forward selection, sequential backward selection, sequential floating forward selection, sequential floating backward selection, and genetic algorithm were used. Contrast, energy, Euler number, and kurtosis were marked as effective features. Results: The selected features were evaluated by fuzzy C-means clustering as the unsupervised method and compared with the AdaBoost supervised classifier which has been previously studied. As reported, fuzzy C-means clustering with a mean accuracy of 75% can be suitable for unsupervised techniques. Conclusion: Fuzzy C-means clustering can be a suitable unsupervised technique to determine suspicious areas in thermal images compared to AdaBoost as the supervised technique with a mean accuracy of 88%.http://mejc.sums.ac.ir/index.php/mejc/article/view/381/259Breast cancerBreast thermographyThermogramFeature selectionClassificationTH |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Amir Ehsan Lashkari Mohammad Firouzmand |
spellingShingle |
Amir Ehsan Lashkari Mohammad Firouzmand Early Breast Cancer Detection in Thermogram Images using AdaBoost Classifier and Fuzzy C-Means Clustering Algorithm Middle East Journal of Cancer Breast cancer Breast thermography Thermogram Feature selection Classification TH |
author_facet |
Amir Ehsan Lashkari Mohammad Firouzmand |
author_sort |
Amir Ehsan Lashkari |
title |
Early Breast Cancer Detection in Thermogram Images using AdaBoost Classifier and Fuzzy C-Means Clustering Algorithm |
title_short |
Early Breast Cancer Detection in Thermogram Images using AdaBoost Classifier and Fuzzy C-Means Clustering Algorithm |
title_full |
Early Breast Cancer Detection in Thermogram Images using AdaBoost Classifier and Fuzzy C-Means Clustering Algorithm |
title_fullStr |
Early Breast Cancer Detection in Thermogram Images using AdaBoost Classifier and Fuzzy C-Means Clustering Algorithm |
title_full_unstemmed |
Early Breast Cancer Detection in Thermogram Images using AdaBoost Classifier and Fuzzy C-Means Clustering Algorithm |
title_sort |
early breast cancer detection in thermogram images using adaboost classifier and fuzzy c-means clustering algorithm |
publisher |
Shiraz University of Medical Sciences |
series |
Middle East Journal of Cancer |
issn |
2008-6709 2008-6687 |
publishDate |
2016-07-01 |
description |
Background: In this paper we compare a highly accurate supervised to an
unsupervised technique that uses breast thermal images with the aim of
assisting physicians in early detection of breast cancer.
Methods: First, we segmented the images and determined the region of
interest. Then, 23 features that included statistical, morphological, frequency
domain, histogram and gray-level co-occurrence matrix based features were
extracted from the segmented right and left breasts. To achieve the best
features, feature selection methods such as minimum redundancy and maximum
relevance, sequential forward selection, sequential backward selection,
sequential floating forward selection, sequential floating backward selection,
and genetic algorithm were used. Contrast, energy, Euler number, and kurtosis
were marked as effective features.
Results: The selected features were evaluated by fuzzy C-means clustering
as the unsupervised method and compared with the AdaBoost supervised
classifier which has been previously studied. As reported, fuzzy C-means
clustering with a mean accuracy of 75% can be suitable for unsupervised
techniques.
Conclusion: Fuzzy C-means clustering can be a suitable unsupervised
technique to determine suspicious areas in thermal images compared to
AdaBoost as the supervised technique with a mean accuracy of 88%. |
topic |
Breast cancer Breast thermography Thermogram Feature selection Classification TH |
url |
http://mejc.sums.ac.ir/index.php/mejc/article/view/381/259 |
work_keys_str_mv |
AT amirehsanlashkari earlybreastcancerdetectioninthermogramimagesusingadaboostclassifierandfuzzycmeansclusteringalgorithm AT mohammadfirouzmand earlybreastcancerdetectioninthermogramimagesusingadaboostclassifierandfuzzycmeansclusteringalgorithm |
_version_ |
1724908087493525504 |