Cover Image

Semi-supervise d GAN-base d radiomics model for data augmentation in breast ultrasound mass classification

Background and Objective: The capability of deep learning radiomics (DLR) to extract high-level medical imaging features has promoted the use of computer-aided diagnosis of breast mass detected on ultrasound. Recently, generative adversarial network (GAN) has aided in tackling a general issue in DLR...

Full description

Saved in:
Bibliographic Details
Main Authors: Pang, Ting, Wong, Jeannie Hsiu Ding, Ng, Wei Lin, Chan, Chee Seng
Format: Article
Published: Elsevier 2021
Subjects:
R Medicine (General)
Online Access:http://eprints.um.edu.my/26625/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.26625
record_format eprints
spelling my.um.eprints.266252022-03-31T08:18:48Z http://eprints.um.edu.my/26625/ Semi-supervise d GAN-base d radiomics model for data augmentation in breast ultrasound mass classification Pang, Ting Wong, Jeannie Hsiu Ding Ng, Wei Lin Chan, Chee Seng R Medicine (General) Background and Objective: The capability of deep learning radiomics (DLR) to extract high-level medical imaging features has promoted the use of computer-aided diagnosis of breast mass detected on ultrasound. Recently, generative adversarial network (GAN) has aided in tackling a general issue in DLR, i.e., obtaining a sufficient number of medical images. However, GAN methods require a pair of input and labeled images, which require an exhaustive human annotation process that is very time-consuming. The aim of this paper is to develop a radiomics model based on a semi-supervised GAN method to perform data augmentation in breast ultrasound images. Methods: A total of 1447 ultrasound images, including 767 benign masses and 680 malignant masses were acquired from a tertiary hospital. A semi-supervised GAN model was developed to augment the breast ultrasound images. The synthesized images were subsequently used to classify breast masses using a convolutional neural network (CNN). The model was validated using a 5-fold cross-validation method. Results: The proposed GAN architecture generated high-quality breast ultrasound images, verified by two experienced radiologists. The improved performance of semi-supervised learning increased the quality of the synthetic data produced in comparison to the baseline method. We achieved more accurate breast mass classification results (accuracy 90.41%, sensitivity 87.94%, specificity 85.86%) with our synthetic data augmentation compared to other state-of-the-art methods. Conclusion: The proposed radiomics model has demonstrated a promising potential to synthesize and classify breast masses on ultrasound in a semi-supervised manner. (c) 2021 Elsevier B.V. All rights reserved. Elsevier 2021-05 Article PeerReviewed Pang, Ting and Wong, Jeannie Hsiu Ding and Ng, Wei Lin and Chan, Chee Seng (2021) Semi-supervise d GAN-base d radiomics model for data augmentation in breast ultrasound mass classification. Computer Methods and Programs in Biomedicine, 203. ISSN 0169-2607, DOI https://doi.org/10.1016/j.cmpb.2021.106018 <https://doi.org/10.1016/j.cmpb.2021.106018>. 10.1016/j.cmpb.2021.106018
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic R Medicine (General)
spellingShingle R Medicine (General)
Pang, Ting
Wong, Jeannie Hsiu Ding
Ng, Wei Lin
Chan, Chee Seng
Semi-supervise d GAN-base d radiomics model for data augmentation in breast ultrasound mass classification
description Background and Objective: The capability of deep learning radiomics (DLR) to extract high-level medical imaging features has promoted the use of computer-aided diagnosis of breast mass detected on ultrasound. Recently, generative adversarial network (GAN) has aided in tackling a general issue in DLR, i.e., obtaining a sufficient number of medical images. However, GAN methods require a pair of input and labeled images, which require an exhaustive human annotation process that is very time-consuming. The aim of this paper is to develop a radiomics model based on a semi-supervised GAN method to perform data augmentation in breast ultrasound images. Methods: A total of 1447 ultrasound images, including 767 benign masses and 680 malignant masses were acquired from a tertiary hospital. A semi-supervised GAN model was developed to augment the breast ultrasound images. The synthesized images were subsequently used to classify breast masses using a convolutional neural network (CNN). The model was validated using a 5-fold cross-validation method. Results: The proposed GAN architecture generated high-quality breast ultrasound images, verified by two experienced radiologists. The improved performance of semi-supervised learning increased the quality of the synthetic data produced in comparison to the baseline method. We achieved more accurate breast mass classification results (accuracy 90.41%, sensitivity 87.94%, specificity 85.86%) with our synthetic data augmentation compared to other state-of-the-art methods. Conclusion: The proposed radiomics model has demonstrated a promising potential to synthesize and classify breast masses on ultrasound in a semi-supervised manner. (c) 2021 Elsevier B.V. All rights reserved.
format Article
author Pang, Ting
Wong, Jeannie Hsiu Ding
Ng, Wei Lin
Chan, Chee Seng
author_facet Pang, Ting
Wong, Jeannie Hsiu Ding
Ng, Wei Lin
Chan, Chee Seng
author_sort Pang, Ting
title Semi-supervise d GAN-base d radiomics model for data augmentation in breast ultrasound mass classification
title_short Semi-supervise d GAN-base d radiomics model for data augmentation in breast ultrasound mass classification
title_full Semi-supervise d GAN-base d radiomics model for data augmentation in breast ultrasound mass classification
title_fullStr Semi-supervise d GAN-base d radiomics model for data augmentation in breast ultrasound mass classification
title_full_unstemmed Semi-supervise d GAN-base d radiomics model for data augmentation in breast ultrasound mass classification
title_sort semi-supervise d gan-base d radiomics model for data augmentation in breast ultrasound mass classification
publisher Elsevier
publishDate 2021
url http://eprints.um.edu.my/26625/
_version_ 1735409436812378112
score 13.211869

Similar Items