Malignancy and Abnormality Detection of Mammograms using Classifier Ensembling
The breast cancer detection and diagnosis is a critical and complex procedure that demands high degree of accuracy. In computer aided diagnostic systems, the breast cancer detection is a two stage procedure. First, to classify the malignant and benign mammograms, while in second stage, the type o...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Mehran University of Engineering and Technology
2011-07-01
|
Series: | Mehran University Research Journal of Engineering and Technology |
Subjects: | |
Online Access: | http://publications.muet.edu.pk/research_papers/pdf/pdf135.pdf |
id |
doaj-2722fb4428ee4002970ce06c224d6bb8 |
---|---|
record_format |
Article |
spelling |
doaj-2722fb4428ee4002970ce06c224d6bb82020-11-24T22:27:32ZengMehran University of Engineering and TechnologyMehran University Research Journal of Engineering and Technology0254-78212413-72192011-07-01303499510138Malignancy and Abnormality Detection of Mammograms using Classifier EnsemblingNawazish NaveedMuhammad Arfan JaffarFaisal Karim ShaikhThe breast cancer detection and diagnosis is a critical and complex procedure that demands high degree of accuracy. In computer aided diagnostic systems, the breast cancer detection is a two stage procedure. First, to classify the malignant and benign mammograms, while in second stage, the type of abnormality is detected. In this paper, we have developed a novel architecture to enhance the classification of malignant and benign mammograms using multi-classification of malignant mammograms into six abnormality classes. DWT (Discrete Wavelet Transformation) features are extracted from preprocessed images and passed through different classifiers. To improve accuracy, results generated by various classifiers are ensembled. The genetic algorithm is used to find optimal weights rather than assigning weights to the results of classifiers on the basis of heuristics. The mammograms declared as malignant by ensemble classifiers are divided into six classes. The ensemble classifiers are further used for multiclassification using one-against-all technique for classification. The output of all ensemble classifiers is combined by product, median and mean rule. It has been observed that the accuracy of classification of abnormalities is more than 97% in case of mean rule. The Mammographic Image Analysis Society dataset is used for experimentation.http://publications.muet.edu.pk/research_papers/pdf/pdf135.pdfBreast CancerMammogramSupport Vector MachineDiscrete Wavelet TransformsEnsemble Classifier. |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Nawazish Naveed Muhammad Arfan Jaffar Faisal Karim Shaikh |
spellingShingle |
Nawazish Naveed Muhammad Arfan Jaffar Faisal Karim Shaikh Malignancy and Abnormality Detection of Mammograms using Classifier Ensembling Mehran University Research Journal of Engineering and Technology Breast Cancer Mammogram Support Vector Machine Discrete Wavelet Transforms Ensemble Classifier. |
author_facet |
Nawazish Naveed Muhammad Arfan Jaffar Faisal Karim Shaikh |
author_sort |
Nawazish Naveed |
title |
Malignancy and Abnormality Detection of Mammograms using
Classifier Ensembling |
title_short |
Malignancy and Abnormality Detection of Mammograms using
Classifier Ensembling |
title_full |
Malignancy and Abnormality Detection of Mammograms using
Classifier Ensembling |
title_fullStr |
Malignancy and Abnormality Detection of Mammograms using
Classifier Ensembling |
title_full_unstemmed |
Malignancy and Abnormality Detection of Mammograms using
Classifier Ensembling |
title_sort |
malignancy and abnormality detection of mammograms using
classifier ensembling |
publisher |
Mehran University of Engineering and Technology |
series |
Mehran University Research Journal of Engineering and Technology |
issn |
0254-7821 2413-7219 |
publishDate |
2011-07-01 |
description |
The breast cancer detection and diagnosis is a critical and complex procedure that
demands high degree of accuracy. In computer aided diagnostic systems, the breast
cancer detection is a two stage procedure. First, to classify the malignant and benign
mammograms, while in second stage, the type of abnormality is detected. In this paper,
we have developed a novel architecture to enhance the classification of malignant and
benign mammograms using multi-classification of malignant mammograms into six
abnormality classes. DWT (Discrete Wavelet Transformation) features are extracted
from preprocessed images and passed through different classifiers. To improve accuracy,
results generated by various classifiers are ensembled. The genetic algorithm is used
to find optimal weights rather than assigning weights to the results of classifiers on
the basis of heuristics. The mammograms declared as malignant by ensemble classifiers
are divided into six classes. The ensemble classifiers are further used for multiclassification
using one-against-all technique for classification. The output of all
ensemble classifiers is combined by product, median and mean rule. It has been observed
that the accuracy of classification of abnormalities is more than 97% in case of mean
rule. The Mammographic Image Analysis Society dataset is used for experimentation. |
topic |
Breast Cancer Mammogram Support Vector Machine Discrete Wavelet Transforms Ensemble Classifier. |
url |
http://publications.muet.edu.pk/research_papers/pdf/pdf135.pdf |
work_keys_str_mv |
AT nawazishnaveed malignancyandabnormalitydetectionofmammogramsusingclassifierensembling AT muhammadarfanjaffar malignancyandabnormalitydetectionofmammogramsusingclassifierensembling AT faisalkarimshaikh malignancyandabnormalitydetectionofmammogramsusingclassifierensembling |
_version_ |
1725749486598225920 |