Home > Research > Publications & Outputs > Classification of Breast Tumors Based on Histop...

Research

Links

Text available via DOI:

Keywords

View graph of relations

Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods. / Abbasniya, Mohammad Reza; Sheikholeslamzadeh, Sayed Ali; Nasiri, Hamid et al.
In: Computers and Electrical Engineering, Vol. 103, 108382, 31.10.2022.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Abbasniya, MR, Sheikholeslamzadeh, SA, Nasiri, H & Emami, S 2022, 'Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods', Computers and Electrical Engineering, vol. 103, 108382. https://doi.org/10.1016/j.compeleceng.2022.108382

APA

Abbasniya, M. R., Sheikholeslamzadeh, S. A., Nasiri, H., & Emami, S. (2022). Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods. Computers and Electrical Engineering, 103, Article 108382. https://doi.org/10.1016/j.compeleceng.2022.108382

Vancouver

Abbasniya MR, Sheikholeslamzadeh SA, Nasiri H, Emami S. Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods. Computers and Electrical Engineering. 2022 Oct 31;103:108382. Epub 2022 Sept 19. doi: 10.1016/j.compeleceng.2022.108382

Author

Abbasniya, Mohammad Reza ; Sheikholeslamzadeh, Sayed Ali ; Nasiri, Hamid et al. / Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods. In: Computers and Electrical Engineering. 2022 ; Vol. 103.

Bibtex

@article{b610ca3a05f34e8abf07942df96bccbd,
title = "Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods",
abstract = "Breast cancer is the most common cancer among women worldwide. Early-stage diagnosis of this disease can significantly improve the efficiency of treatment. Computer-Aided Diagnosis (CAD) Systems are adopted widely in this regard due to their reliability, accuracy and affordability. There are different imaging techniques for a breast cancer diagnosis; one of the most accurate ones is histopathology which is used in this paper. Deep feature transfer learning is used as the main idea of the proposed CAD system's feature extractor. As such, the present paper works on sixteen different pre-trained networks with a focus on their classification phase, something that has not been studied enough. The Inception-ResNet-v2, which has both residual and inception networks profits together, has shown the best feature extraction capability in the case of breast cancer histopathology images among all tested Convolutional neural networks (CNNs). In the classification phase, the ensemble of Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost) and Light Gradient boosting Machine (LightGBM) has given the best average accuracy. The Breast Cancer Histopathological Image Classification (BreakHis) dataset helps evaluating the proposed method, i.e., IRv2-CXL, with the experimental results indicating that IRv2-CXL outperforms other state-of-the-art methods.",
keywords = "BreakHis, Breast cancer, Ensemble classification, Grad-CAM, Inception-ResNet-v2, Transfer learning",
author = "Abbasniya, {Mohammad Reza} and Sheikholeslamzadeh, {Sayed Ali} and Hamid Nasiri and Samaneh Emami",
year = "2022",
month = oct,
day = "31",
doi = "10.1016/j.compeleceng.2022.108382",
language = "English",
volume = "103",
journal = "Computers and Electrical Engineering",
issn = "0045-7906",
publisher = "Elsevier Ltd",

}

RIS

TY - JOUR

T1 - Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods

AU - Abbasniya, Mohammad Reza

AU - Sheikholeslamzadeh, Sayed Ali

AU - Nasiri, Hamid

AU - Emami, Samaneh

PY - 2022/10/31

Y1 - 2022/10/31

N2 - Breast cancer is the most common cancer among women worldwide. Early-stage diagnosis of this disease can significantly improve the efficiency of treatment. Computer-Aided Diagnosis (CAD) Systems are adopted widely in this regard due to their reliability, accuracy and affordability. There are different imaging techniques for a breast cancer diagnosis; one of the most accurate ones is histopathology which is used in this paper. Deep feature transfer learning is used as the main idea of the proposed CAD system's feature extractor. As such, the present paper works on sixteen different pre-trained networks with a focus on their classification phase, something that has not been studied enough. The Inception-ResNet-v2, which has both residual and inception networks profits together, has shown the best feature extraction capability in the case of breast cancer histopathology images among all tested Convolutional neural networks (CNNs). In the classification phase, the ensemble of Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost) and Light Gradient boosting Machine (LightGBM) has given the best average accuracy. The Breast Cancer Histopathological Image Classification (BreakHis) dataset helps evaluating the proposed method, i.e., IRv2-CXL, with the experimental results indicating that IRv2-CXL outperforms other state-of-the-art methods.

AB - Breast cancer is the most common cancer among women worldwide. Early-stage diagnosis of this disease can significantly improve the efficiency of treatment. Computer-Aided Diagnosis (CAD) Systems are adopted widely in this regard due to their reliability, accuracy and affordability. There are different imaging techniques for a breast cancer diagnosis; one of the most accurate ones is histopathology which is used in this paper. Deep feature transfer learning is used as the main idea of the proposed CAD system's feature extractor. As such, the present paper works on sixteen different pre-trained networks with a focus on their classification phase, something that has not been studied enough. The Inception-ResNet-v2, which has both residual and inception networks profits together, has shown the best feature extraction capability in the case of breast cancer histopathology images among all tested Convolutional neural networks (CNNs). In the classification phase, the ensemble of Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost) and Light Gradient boosting Machine (LightGBM) has given the best average accuracy. The Breast Cancer Histopathological Image Classification (BreakHis) dataset helps evaluating the proposed method, i.e., IRv2-CXL, with the experimental results indicating that IRv2-CXL outperforms other state-of-the-art methods.

KW - BreakHis

KW - Breast cancer

KW - Ensemble classification

KW - Grad-CAM

KW - Inception-ResNet-v2

KW - Transfer learning

U2 - 10.1016/j.compeleceng.2022.108382

DO - 10.1016/j.compeleceng.2022.108382

M3 - Journal article

AN - SCOPUS:85138467414

VL - 103

JO - Computers and Electrical Engineering

JF - Computers and Electrical Engineering

SN - 0045-7906

M1 - 108382

ER -