The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection

Hao Chun Lu; El Wui Loh; Shih Chen Huang

doi:10.1109/ICAIBD.2019.8837000

The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection

Hao Chun Lu
, El Wui Loh
, Shih Chen Huang

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

58 Citations (Scopus)

Abstract

The incidence rate of breast cancer continued to rise in the last few decades. Current screening strategy of breast cancer is based on classic X-ray imaging. The sensitivity and specificity of the diagnosis are largely depend on the experiences of the radiologists, and uncertain diagnosis is quite frequent because of resolution limitations and the concerns of lawsuits arisen from wrong diagnosis or undetected lesions. The convolutional neural network is an effective technique for classification in deep learning model. In this study, we utilized median filter, contrast-limited adaptive histogram equalization, and data augmentation to preprocess over 9,000 mammograms, and trained a classified model by using convolutional neural network. The experiment results demonstrated that the accuracy of model with preprocessed images significantly outperformed the model without preprocessed images.

Original language	English
Title of host publication	2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	9-12
Number of pages	4
ISBN (Electronic)	9781728108315
DOIs	https://doi.org/10.1109/ICAIBD.2019.8837000
Publication status	Published - May 2019
Event	2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019 - Chengdu, China Duration: May 25 2019 → May 28 2019

Publication series

Name	2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019

Conference

Conference	2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019
Country/Territory	China
City	Chengdu
Period	5/25/19 → 5/28/19

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

breast cancer detection
convolution neural network
deep learning
mammograms

ASJC Scopus subject areas

Computer Science Applications
Information Systems and Management
Control and Optimization
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1109/ICAIBD.2019.8837000

Cite this

Lu, H. C., Loh, E. W., & Huang, S. C. (2019). The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection. In 2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019 (pp. 9-12). Article 8837000 (2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAIBD.2019.8837000

The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection. / Lu, Hao Chun; Loh, El Wui; Huang, Shih Chen.
2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 9-12 8837000 (2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019).

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

Lu, HC, Loh, EW & Huang, SC 2019, The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection. in 2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019., 8837000, 2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019, Institute of Electrical and Electronics Engineers Inc., pp. 9-12, 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019, Chengdu, China, 5/25/19. https://doi.org/10.1109/ICAIBD.2019.8837000

Lu HC, Loh EW, Huang SC. The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection. In 2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 9-12. 8837000. (2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019). doi: 10.1109/ICAIBD.2019.8837000

Lu, Hao Chun ; Loh, El Wui ; Huang, Shih Chen. / The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection. 2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 9-12 (2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019).

@inproceedings{25a888afc5ea4c059b9a131d0e16a207,

title = "The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection",

abstract = "The incidence rate of breast cancer continued to rise in the last few decades. Current screening strategy of breast cancer is based on classic X-ray imaging. The sensitivity and specificity of the diagnosis are largely depend on the experiences of the radiologists, and uncertain diagnosis is quite frequent because of resolution limitations and the concerns of lawsuits arisen from wrong diagnosis or undetected lesions. The convolutional neural network is an effective technique for classification in deep learning model. In this study, we utilized median filter, contrast-limited adaptive histogram equalization, and data augmentation to preprocess over 9,000 mammograms, and trained a classified model by using convolutional neural network. The experiment results demonstrated that the accuracy of model with preprocessed images significantly outperformed the model without preprocessed images.",

keywords = "breast cancer detection, convolution neural network, deep learning, mammograms",

author = "Lu, \{Hao Chun\} and Loh, \{El Wui\} and Huang, \{Shih Chen\}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019 ; Conference date: 25-05-2019 Through 28-05-2019",

year = "2019",

month = may,

doi = "10.1109/ICAIBD.2019.8837000",

language = "English",

series = "2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019",

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

pages = "9--12",

booktitle = "2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019",

address = "United States",

}

TY - GEN

T1 - The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection

AU - Lu, Hao Chun

AU - Loh, El Wui

AU - Huang, Shih Chen

PY - 2019/5

Y1 - 2019/5

N2 - The incidence rate of breast cancer continued to rise in the last few decades. Current screening strategy of breast cancer is based on classic X-ray imaging. The sensitivity and specificity of the diagnosis are largely depend on the experiences of the radiologists, and uncertain diagnosis is quite frequent because of resolution limitations and the concerns of lawsuits arisen from wrong diagnosis or undetected lesions. The convolutional neural network is an effective technique for classification in deep learning model. In this study, we utilized median filter, contrast-limited adaptive histogram equalization, and data augmentation to preprocess over 9,000 mammograms, and trained a classified model by using convolutional neural network. The experiment results demonstrated that the accuracy of model with preprocessed images significantly outperformed the model without preprocessed images.

AB - The incidence rate of breast cancer continued to rise in the last few decades. Current screening strategy of breast cancer is based on classic X-ray imaging. The sensitivity and specificity of the diagnosis are largely depend on the experiences of the radiologists, and uncertain diagnosis is quite frequent because of resolution limitations and the concerns of lawsuits arisen from wrong diagnosis or undetected lesions. The convolutional neural network is an effective technique for classification in deep learning model. In this study, we utilized median filter, contrast-limited adaptive histogram equalization, and data augmentation to preprocess over 9,000 mammograms, and trained a classified model by using convolutional neural network. The experiment results demonstrated that the accuracy of model with preprocessed images significantly outperformed the model without preprocessed images.

KW - breast cancer detection

KW - convolution neural network

KW - deep learning

KW - mammograms

UR - https://www.scopus.com/pages/publications/85073237870

UR - https://www.scopus.com/pages/publications/85073237870#tab=citedBy

U2 - 10.1109/ICAIBD.2019.8837000

DO - 10.1109/ICAIBD.2019.8837000

M3 - Conference contribution

AN - SCOPUS:85073237870

T3 - 2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019

SP - 9

EP - 12

BT - 2019 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Artificial Intelligence and Big Data, ICAIBD 2019

Y2 - 25 May 2019 through 28 May 2019

ER -

The Classification of Mammogram Using Convolutional Neural Network with Specific Image Preprocessing for Breast Cancer Detection

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this