Breast mass classification in mammograms using ensemble convolutional neural networks

Andrik Rampun; Bryan W. Scotney; Philip J. Morrow; Hui Wang

doi:10.1109/HealthCom.2018.8531154

Breast mass classification in mammograms using ensemble convolutional neural networks

Andrik Rampun
, Bryan W. Scotney
, Philip J. Morrow
, Hui Wang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

54 Citations (Scopus)

Abstract

The paper presents quantitative results of a preliminary study undertaken as part of Decision Support and Information Management System for Breast Cancer (DESIREE). DESIREE is a European-funded project to improve the management of primary breast cancer through image-based, guideline-based, experience-based, and case-based information systems. In this study we explore the use of ensemble deep learning for breast mass classification in mammograms. The proposed method is based on AlexNet with some modifications in order to adapt it to our classification problem. Subsequently, model selection is performed to select the best three results based on the highest validation accuracies during the validation phase. Finally, the prediction is based on the average probability of the models. Experimental evaluation shows that accuracy from individual models ranges between 75% and 77%, but combining the best models (ensemble networks) results in over 80% classification accuracy and aura under the curve.

Original language	English
Title of host publication	2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538642948
DOIs	https://doi.org/10.1109/HealthCom.2018.8531154
Publication status	Published - 11 Nov 2018
Externally published	Yes
Event	20th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2018 - Ostrava, Czech Republic Duration: 17 Sept 2018 → 20 Sept 2018

Publication series

Name	IEEE International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings

Conference

Conference	20th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2018
Country/Territory	Czech Republic
City	Ostrava
Period	17/09/2018 → 20/09/2018

Bibliographical note

Funding Information:
This research was undertaken as part of the Decision Support and Information Management System for Breast Cancer (DESIREE) project. The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 690238.

Publisher Copyright:
© 2018 IEEE.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

ASJC Scopus subject areas

Health(social science)
Signal Processing
Health Informatics
Computer Networks and Communications
Computer Science Applications
Hardware and Architecture

Access to Document

10.1109/HealthCom.2018.8531154Licence: Unspecified

Cite this

Rampun, A., Scotney, B. W., Morrow, P. J., & Wang, H. (2018). Breast mass classification in mammograms using ensemble convolutional neural networks. In 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings Article 8531154 (IEEE International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HealthCom.2018.8531154

Rampun, Andrik ; Scotney, Bryan W. ; Morrow, Philip J. et al. / Breast mass classification in mammograms using ensemble convolutional neural networks. 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. (IEEE International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings).

@inproceedings{f2f19902e5724edba8169f1159c901ee,

title = "Breast mass classification in mammograms using ensemble convolutional neural networks",

abstract = "The paper presents quantitative results of a preliminary study undertaken as part of Decision Support and Information Management System for Breast Cancer (DESIREE). DESIREE is a European-funded project to improve the management of primary breast cancer through image-based, guideline-based, experience-based, and case-based information systems. In this study we explore the use of ensemble deep learning for breast mass classification in mammograms. The proposed method is based on AlexNet with some modifications in order to adapt it to our classification problem. Subsequently, model selection is performed to select the best three results based on the highest validation accuracies during the validation phase. Finally, the prediction is based on the average probability of the models. Experimental evaluation shows that accuracy from individual models ranges between 75\% and 77\%, but combining the best models (ensemble networks) results in over 80\% classification accuracy and aura under the curve.",

author = "Andrik Rampun and Scotney, \{Bryan W.\} and Morrow, \{Philip J.\} and Hui Wang",

note = "Funding Information: This research was undertaken as part of the Decision Support and Information Management System for Breast Cancer (DESIREE) project. The project has received funding from the European Union{\textquoteright}s Horizon 2020 research and innovation programme under grant agreement No 690238. Publisher Copyright: {\textcopyright} 2018 IEEE.; 20th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2018 ; Conference date: 17-09-2018 Through 20-09-2018",

year = "2018",

month = nov,

day = "11",

doi = "10.1109/HealthCom.2018.8531154",

language = "English",

series = "IEEE International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings",

address = "United States",

}

Rampun, A, Scotney, BW, Morrow, PJ & Wang, H 2018, Breast mass classification in mammograms using ensemble convolutional neural networks. in 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings., 8531154, IEEE International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings, Institute of Electrical and Electronics Engineers Inc., 20th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2018, Ostrava, Czech Republic, 17/09/2018. https://doi.org/10.1109/HealthCom.2018.8531154

Breast mass classification in mammograms using ensemble convolutional neural networks. / Rampun, Andrik; Scotney, Bryan W.; Morrow, Philip J. et al.
2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. 8531154 (IEEE International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Breast mass classification in mammograms using ensemble convolutional neural networks

AU - Rampun, Andrik

AU - Scotney, Bryan W.

AU - Morrow, Philip J.

AU - Wang, Hui

N1 - Funding Information: This research was undertaken as part of the Decision Support and Information Management System for Breast Cancer (DESIREE) project. The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 690238. Publisher Copyright: © 2018 IEEE.

PY - 2018/11/11

Y1 - 2018/11/11

N2 - The paper presents quantitative results of a preliminary study undertaken as part of Decision Support and Information Management System for Breast Cancer (DESIREE). DESIREE is a European-funded project to improve the management of primary breast cancer through image-based, guideline-based, experience-based, and case-based information systems. In this study we explore the use of ensemble deep learning for breast mass classification in mammograms. The proposed method is based on AlexNet with some modifications in order to adapt it to our classification problem. Subsequently, model selection is performed to select the best three results based on the highest validation accuracies during the validation phase. Finally, the prediction is based on the average probability of the models. Experimental evaluation shows that accuracy from individual models ranges between 75% and 77%, but combining the best models (ensemble networks) results in over 80% classification accuracy and aura under the curve.

AB - The paper presents quantitative results of a preliminary study undertaken as part of Decision Support and Information Management System for Breast Cancer (DESIREE). DESIREE is a European-funded project to improve the management of primary breast cancer through image-based, guideline-based, experience-based, and case-based information systems. In this study we explore the use of ensemble deep learning for breast mass classification in mammograms. The proposed method is based on AlexNet with some modifications in order to adapt it to our classification problem. Subsequently, model selection is performed to select the best three results based on the highest validation accuracies during the validation phase. Finally, the prediction is based on the average probability of the models. Experimental evaluation shows that accuracy from individual models ranges between 75% and 77%, but combining the best models (ensemble networks) results in over 80% classification accuracy and aura under the curve.

U2 - 10.1109/HealthCom.2018.8531154

DO - 10.1109/HealthCom.2018.8531154

M3 - Conference contribution

AN - SCOPUS:85058305906

T3 - IEEE International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings

BT - 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 20th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2018

Y2 - 17 September 2018 through 20 September 2018

ER -

Rampun A, Scotney BW, Morrow PJ, Wang H. Breast mass classification in mammograms using ensemble convolutional neural networks. In 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. 8531154. (IEEE International Conference on e-Health Networking, Applications and Services (Healthcom): proceedings). doi: 10.1109/HealthCom.2018.8531154

Breast mass classification in mammograms using ensemble convolutional neural networks

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this