Cargando…

Three-Class Mammogram Classification Based on Descriptive CNN Features

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural net...

Descripción completa

Detalles Bibliográficos
Autores principales: Jadoon, M. Mohsin, Zhang, Qianni, Haq, Ihsan Ul, Butt, Sharjeel, Jadoon, Adeel
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5274695/
https://www.ncbi.nlm.nih.gov/pubmed/28191461
http://dx.doi.org/10.1155/2017/3640901
_version_ 1782501948689219584
author Jadoon, M. Mohsin
Zhang, Qianni
Haq, Ihsan Ul
Butt, Sharjeel
Jadoon, Adeel
author_facet Jadoon, M. Mohsin
Zhang, Qianni
Haq, Ihsan Ul
Butt, Sharjeel
Jadoon, Adeel
author_sort Jadoon, M. Mohsin
collection PubMed
description In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques.
format Online
Article
Text
id pubmed-5274695
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher Hindawi Publishing Corporation
record_format MEDLINE/PubMed
spelling pubmed-52746952017-02-12 Three-Class Mammogram Classification Based on Descriptive CNN Features Jadoon, M. Mohsin Zhang, Qianni Haq, Ihsan Ul Butt, Sharjeel Jadoon, Adeel Biomed Res Int Research Article In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques. Hindawi Publishing Corporation 2017 2017-01-15 /pmc/articles/PMC5274695/ /pubmed/28191461 http://dx.doi.org/10.1155/2017/3640901 Text en Copyright © 2017 M. Mohsin Jadoon et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Jadoon, M. Mohsin
Zhang, Qianni
Haq, Ihsan Ul
Butt, Sharjeel
Jadoon, Adeel
Three-Class Mammogram Classification Based on Descriptive CNN Features
title Three-Class Mammogram Classification Based on Descriptive CNN Features
title_full Three-Class Mammogram Classification Based on Descriptive CNN Features
title_fullStr Three-Class Mammogram Classification Based on Descriptive CNN Features
title_full_unstemmed Three-Class Mammogram Classification Based on Descriptive CNN Features
title_short Three-Class Mammogram Classification Based on Descriptive CNN Features
title_sort three-class mammogram classification based on descriptive cnn features
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5274695/
https://www.ncbi.nlm.nih.gov/pubmed/28191461
http://dx.doi.org/10.1155/2017/3640901
work_keys_str_mv AT jadoonmmohsin threeclassmammogramclassificationbasedondescriptivecnnfeatures
AT zhangqianni threeclassmammogramclassificationbasedondescriptivecnnfeatures
AT haqihsanul threeclassmammogramclassificationbasedondescriptivecnnfeatures
AT buttsharjeel threeclassmammogramclassificationbasedondescriptivecnnfeatures
AT jadoonadeel threeclassmammogramclassificationbasedondescriptivecnnfeatures