Synthetic data augmentation using GAN for improved liver lesion classification

Maayan Frid-Adar; Eyal Klang; Michal Amitai; Jacob Goldberger; Hayit Greenspan

doi:10.1109/ISBI.2018.8363576

Synthetic data augmentation using GAN for improved liver lesion classification

Maayan Frid-Adar, Eyal Klang, Michal Amitai, Jacob Goldberger, Hayit Greenspan

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

546 Scopus citations

Abstract

In this paper, we present a data augmentation method that generates synthetic medical images using Generative Adversarial Networks (GANs). We propose a training scheme that first uses classical data augmentation to enlarge the training set and then further enlarges the data size and its diversity by applying GAN techniques for synthetic data augmentation. Our method is demonstrated on a limited dataset of computed tomography (CT) images of 182 liver lesions (53 cysts, 64 metastases and 65 hemangiomas). The classification performance using only classic data augmentation yielded 78.6% sensitivity and 88.4% specificity. By adding the synthetic data augmentation the results significantly increased to 85.7% sensitivity and 92.4% specificity.

Original language	English
Title of host publication	2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
Publisher	IEEE Computer Society
Pages	289-293
Number of pages	5
ISBN (Electronic)	9781538636367
DOIs	https://doi.org/10.1109/ISBI.2018.8363576
State	Published - 23 May 2018
Event	15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States Duration: 4 Apr 2018 → 7 Apr 2018

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2018-April
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
Country/Territory	United States
City	Washington
Period	4/04/18 → 7/04/18

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

Keywords

Data augmentation
Generative adversarial network
Image synthesis
Lesion classification
Liver lesions

Access to Document

10.1109/ISBI.2018.8363576

Cite this

Frid-Adar, M., Klang, E., Amitai, M., Goldberger, J., & Greenspan, H. (2018). Synthetic data augmentation using GAN for improved liver lesion classification. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018 (pp. 289-293). (Proceedings - International Symposium on Biomedical Imaging; Vol. 2018-April). IEEE Computer Society. https://doi.org/10.1109/ISBI.2018.8363576

@inproceedings{a30d3207482d448991739883cd6b8322,

title = "Synthetic data augmentation using GAN for improved liver lesion classification",

abstract = "In this paper, we present a data augmentation method that generates synthetic medical images using Generative Adversarial Networks (GANs). We propose a training scheme that first uses classical data augmentation to enlarge the training set and then further enlarges the data size and its diversity by applying GAN techniques for synthetic data augmentation. Our method is demonstrated on a limited dataset of computed tomography (CT) images of 182 liver lesions (53 cysts, 64 metastases and 65 hemangiomas). The classification performance using only classic data augmentation yielded 78.6% sensitivity and 88.4% specificity. By adding the synthetic data augmentation the results significantly increased to 85.7% sensitivity and 92.4% specificity.",

keywords = "Data augmentation, Generative adversarial network, Image synthesis, Lesion classification, Liver lesions",

author = "Maayan Frid-Adar and Eyal Klang and Michal Amitai and Jacob Goldberger and Hayit Greenspan",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 ; Conference date: 04-04-2018 Through 07-04-2018",

year = "2018",

month = may,

day = "23",

doi = "10.1109/ISBI.2018.8363576",

language = "אנגלית",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "289--293",

booktitle = "2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018",

address = "ארצות הברית",

}

Frid-Adar, M, Klang, E, Amitai, M, Goldberger, J & Greenspan, H 2018, Synthetic data augmentation using GAN for improved liver lesion classification. in 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Proceedings - International Symposium on Biomedical Imaging, vol. 2018-April, IEEE Computer Society, pp. 289-293, 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018, Washington, United States, 4/04/18. https://doi.org/10.1109/ISBI.2018.8363576

Synthetic data augmentation using GAN for improved liver lesion classification. / Frid-Adar, Maayan; Klang, Eyal; Amitai, Michal et al.
2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. IEEE Computer Society, 2018. p. 289-293 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2018-April).

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

TY - GEN

T1 - Synthetic data augmentation using GAN for improved liver lesion classification

AU - Frid-Adar, Maayan

AU - Klang, Eyal

AU - Amitai, Michal

AU - Goldberger, Jacob

AU - Greenspan, Hayit

PY - 2018/5/23

Y1 - 2018/5/23

N2 - In this paper, we present a data augmentation method that generates synthetic medical images using Generative Adversarial Networks (GANs). We propose a training scheme that first uses classical data augmentation to enlarge the training set and then further enlarges the data size and its diversity by applying GAN techniques for synthetic data augmentation. Our method is demonstrated on a limited dataset of computed tomography (CT) images of 182 liver lesions (53 cysts, 64 metastases and 65 hemangiomas). The classification performance using only classic data augmentation yielded 78.6% sensitivity and 88.4% specificity. By adding the synthetic data augmentation the results significantly increased to 85.7% sensitivity and 92.4% specificity.

AB - In this paper, we present a data augmentation method that generates synthetic medical images using Generative Adversarial Networks (GANs). We propose a training scheme that first uses classical data augmentation to enlarge the training set and then further enlarges the data size and its diversity by applying GAN techniques for synthetic data augmentation. Our method is demonstrated on a limited dataset of computed tomography (CT) images of 182 liver lesions (53 cysts, 64 metastases and 65 hemangiomas). The classification performance using only classic data augmentation yielded 78.6% sensitivity and 88.4% specificity. By adding the synthetic data augmentation the results significantly increased to 85.7% sensitivity and 92.4% specificity.

KW - Data augmentation

KW - Generative adversarial network

KW - Image synthesis

KW - Lesion classification

KW - Liver lesions

UR - http://www.scopus.com/inward/record.url?scp=85048075788&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2018.8363576

DO - 10.1109/ISBI.2018.8363576

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85048075788

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 289

EP - 293

BT - 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018

PB - IEEE Computer Society

T2 - 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018

Y2 - 4 April 2018 through 7 April 2018

ER -

Synthetic data augmentation using GAN for improved liver lesion classification

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this