TY - JOUR
T1 - Breast Cancer Detection Using Extreme Learning Machine Based on Feature Fusion with CNN Deep Features
AU - Wang, Zhiqiong
AU - Li, Mo
AU - Wang, Huaxia
AU - Jiang, Hanyu
AU - Yao, Yudong
AU - Zhang, Hao
AU - Xin, Junchang
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2019
Y1 - 2019
N2 - A computer-aided diagnosis (CAD) system based on mammograms enables early breast cancer detection, diagnosis, and treatment. However, the accuracy of the existing CAD systems remains unsatisfactory. This paper explores a breast CAD method based on feature fusion with convolutional neural network (CNN) deep features. First, we propose a mass detection method based on CNN deep features and unsupervised extreme learning machine (ELM) clustering. Second, we build a feature set fusing deep features, morphological features, texture features, and density features. Third, an ELM classifier is developed using the fused feature set to classify benign and malignant breast masses. Extensive experiments demonstrate the accuracy and efficiency of our proposed mass detection and breast cancer classification method.
AB - A computer-aided diagnosis (CAD) system based on mammograms enables early breast cancer detection, diagnosis, and treatment. However, the accuracy of the existing CAD systems remains unsatisfactory. This paper explores a breast CAD method based on feature fusion with convolutional neural network (CNN) deep features. First, we propose a mass detection method based on CNN deep features and unsupervised extreme learning machine (ELM) clustering. Second, we build a feature set fusing deep features, morphological features, texture features, and density features. Third, an ELM classifier is developed using the fused feature set to classify benign and malignant breast masses. Extensive experiments demonstrate the accuracy and efficiency of our proposed mass detection and breast cancer classification method.
KW - Mass detection
KW - computer-aided diagnosis
KW - deep learning
KW - extreme learning machine
KW - fusion feature
UR - http://www.scopus.com/inward/record.url?scp=85097349393&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097349393&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2019.2892795
DO - 10.1109/ACCESS.2019.2892795
M3 - Article
AN - SCOPUS:85097349393
VL - 7
SP - 105146
EP - 105158
JO - IEEE Access
JF - IEEE Access
M1 - 8613773
ER -