Breast cancer histopathology image classification using kernelized weighted extreme learning machine

被引:38
作者
Saxena, Shweta [1 ]
Shukla, Sanyam [1 ]
Gyanchandani, Manasi [1 ]
机构
[1] Maulana Azad Natl Inst Technol, Bhopal 462003, Madhya Pradesh, India
关键词
breast cancer; computer-aided diagnosis; histopathology; pretrained convolutional neural network; SYSTEMS;
D O I
10.1002/ima.22465
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Histopathology is considered as the gold standard for diagnosing breast cancer. Traditional machine learning (ML) algorithm provides a promising performance for cancer diagnosis if the training dataset is balanced. Nevertheless, if the training dataset is imbalanced the performance of the ML model is skewed toward the majority class. It may pose a problem for the pathologist because if the benign sample is misclassified as malignant, then a pathologist could make a misjudgment about the diagnosis. A limited investigation has been done in literature for solving the class imbalance problem in computer-aided diagnosis (CAD) of breast cancer using histopathology. This work proposes a hybrid ML model to solve the class imbalance problem. The proposed model employs pretrained ResNet50 and the kernelized weighted extreme learning machine for CAD of breast cancer using histopathology. The breast cancer histopathological images are obtained from publicly available BreakHis and BisQue datasets. The proposed method achieved a reasonable performance for the classification of the minority as well as the majority class instances. In comparison, the proposed approach outperforms the state-of-the-art ML models implemented in previous studies using the same training-testing folds of the publicly accessible BreakHis dataset.
引用
收藏
页码:168 / 179
页数:12
相关论文
共 29 条
[1]  
Ahmad Hafiz Mughees, 2019, 2019 16th International Bhurban Conference on Applied Sciences and Technology (IBCAST). Proceedings, P328, DOI 10.1109/IBCAST.2019.8667221
[2]   A systematic study of the class imbalance problem in convolutional neural networks [J].
Buda, Mateusz ;
Maki, Atsuto ;
Mazurowski, Maciej A. .
NEURAL NETWORKS, 2018, 106 :249-259
[3]   An analysis of "A feature reduced intrusion detection system using ANN classifier" by Akashdeep et al. expert systems with applications (2017) [J].
Chandak, Trupti ;
Shukla, Sanyam ;
Wadhvani, Rajesh .
EXPERT SYSTEMS WITH APPLICATIONS, 2019, 130 :79-83
[4]   Structured Literature Image Finder: Extracting Information from Text and Images in Biomedical Literature [J].
Coelho, Luis Pedro ;
Ahmed, Amr ;
Arnold, Andrew ;
Kangas, Joshua ;
Sheikh, Abdul-Saboor ;
Xing, Eric P. ;
Cohen, William W. ;
Murphy, Robert F. .
LINKING LITERATURE, INFORMATION, AND KNOWLEDGE FOR BIOLOGY, 2010, 6004 :23-+
[5]  
COOPER GM, 2000, DEV CAUSES CANC, pCH15
[6]   Automatic Breast Cancer Grading of Histopathological Images [J].
Dalle, Jean-Romain ;
Leow, Wee Kheng ;
Racoceanu, Daniel ;
Tutac, Adina Eunice ;
Putti, Thomas C. .
2008 30TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-8, 2008, :3052-+
[7]  
Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
[8]   MuDeRN: Multi-category classification of breast histopathological image using deep residual networks [J].
Gandomkar, Ziba ;
Brennan, Patrick C. ;
Mello-Thoms, Claudia .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2018, 88 :14-24
[9]  
Gelasca ED, 2008, IEEE IMAGE PROC, P1816, DOI 10.1109/ICIP.2008.4712130
[10]   Breast Cancer Histopathological Image Classification: Is Magnification Important? [J].
Gupta, Vibha ;
Bhavsar, Arnav .
2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, :769-776