Cargando…

Generation of synthetic ground glass nodules using generative adversarial networks (GANs)

BACKGROUND: Data shortage is a common challenge in developing computer-aided diagnosis systems. We developed a generative adversarial network (GAN) model to generate synthetic lung lesions mimicking ground glass nodules (GGNs). METHODS: We used 216 computed tomography images with 340 GGNs from the L...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Zhixiang, Zhang, Zhen, Feng, Ying, Hendriks, Lizza E. L., Miclea, Razvan L., Gietema, Hester, Schoenmaekers, Janna, Dekker, Andre, Wee, Leonard, Traverso, Alberto
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Vienna 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9708993/
https://www.ncbi.nlm.nih.gov/pubmed/36447082
http://dx.doi.org/10.1186/s41747-022-00311-y
_version_ 1784841052219244544
author Wang, Zhixiang
Zhang, Zhen
Feng, Ying
Hendriks, Lizza E. L.
Miclea, Razvan L.
Gietema, Hester
Schoenmaekers, Janna
Dekker, Andre
Wee, Leonard
Traverso, Alberto
author_facet Wang, Zhixiang
Zhang, Zhen
Feng, Ying
Hendriks, Lizza E. L.
Miclea, Razvan L.
Gietema, Hester
Schoenmaekers, Janna
Dekker, Andre
Wee, Leonard
Traverso, Alberto
author_sort Wang, Zhixiang
collection PubMed
description BACKGROUND: Data shortage is a common challenge in developing computer-aided diagnosis systems. We developed a generative adversarial network (GAN) model to generate synthetic lung lesions mimicking ground glass nodules (GGNs). METHODS: We used 216 computed tomography images with 340 GGNs from the Lung Image Database Consortium and Image Database Resource Initiative database. A GAN model retrieving information from the whole image and the GGN region was built. The generated samples were evaluated with visual Turing test performed by four experienced radiologists or pulmonologists. Radiomic features were compared between real and synthetic nodules. Performances were evaluated by area under the curve (AUC) at receiver operating characteristic analysis. In addition, we trained a classification model (ResNet) to investigate whether the synthetic GGNs can improve the performances algorithm and how performances changed as a function of labelled data used in training. RESULTS: Of 51 synthetic GGNs, 19 (37%) were classified as real by clinicians. Of 93 radiomic features, 58 (62.4%) showed no significant difference between synthetic and real GGNs (p ≥ 0.052). The discrimination performances of physicians (AUC 0.68) and radiomics (AUC 0.66) were similar, with no-significantly different (p = 0.23), but clinicians achieved a better accuracy (AUC 0.74) than radiomics (AUC 0.62) (p < 0.001). The classification model trained on datasets with synthetic data performed better than models without the addition of synthetic data. CONCLUSIONS: GAN has promising potential for generating GGNs. Through similar AUC, clinicians achieved better ability to diagnose whether the data is synthetic than radiomics.
format Online
Article
Text
id pubmed-9708993
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Springer Vienna
record_format MEDLINE/PubMed
spelling pubmed-97089932022-12-01 Generation of synthetic ground glass nodules using generative adversarial networks (GANs) Wang, Zhixiang Zhang, Zhen Feng, Ying Hendriks, Lizza E. L. Miclea, Razvan L. Gietema, Hester Schoenmaekers, Janna Dekker, Andre Wee, Leonard Traverso, Alberto Eur Radiol Exp Original Article BACKGROUND: Data shortage is a common challenge in developing computer-aided diagnosis systems. We developed a generative adversarial network (GAN) model to generate synthetic lung lesions mimicking ground glass nodules (GGNs). METHODS: We used 216 computed tomography images with 340 GGNs from the Lung Image Database Consortium and Image Database Resource Initiative database. A GAN model retrieving information from the whole image and the GGN region was built. The generated samples were evaluated with visual Turing test performed by four experienced radiologists or pulmonologists. Radiomic features were compared between real and synthetic nodules. Performances were evaluated by area under the curve (AUC) at receiver operating characteristic analysis. In addition, we trained a classification model (ResNet) to investigate whether the synthetic GGNs can improve the performances algorithm and how performances changed as a function of labelled data used in training. RESULTS: Of 51 synthetic GGNs, 19 (37%) were classified as real by clinicians. Of 93 radiomic features, 58 (62.4%) showed no significant difference between synthetic and real GGNs (p ≥ 0.052). The discrimination performances of physicians (AUC 0.68) and radiomics (AUC 0.66) were similar, with no-significantly different (p = 0.23), but clinicians achieved a better accuracy (AUC 0.74) than radiomics (AUC 0.62) (p < 0.001). The classification model trained on datasets with synthetic data performed better than models without the addition of synthetic data. CONCLUSIONS: GAN has promising potential for generating GGNs. Through similar AUC, clinicians achieved better ability to diagnose whether the data is synthetic than radiomics. Springer Vienna 2022-11-30 /pmc/articles/PMC9708993/ /pubmed/36447082 http://dx.doi.org/10.1186/s41747-022-00311-y Text en © The Author(s) under exclusive licence to European Society of Radiology 2022 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Original Article
Wang, Zhixiang
Zhang, Zhen
Feng, Ying
Hendriks, Lizza E. L.
Miclea, Razvan L.
Gietema, Hester
Schoenmaekers, Janna
Dekker, Andre
Wee, Leonard
Traverso, Alberto
Generation of synthetic ground glass nodules using generative adversarial networks (GANs)
title Generation of synthetic ground glass nodules using generative adversarial networks (GANs)
title_full Generation of synthetic ground glass nodules using generative adversarial networks (GANs)
title_fullStr Generation of synthetic ground glass nodules using generative adversarial networks (GANs)
title_full_unstemmed Generation of synthetic ground glass nodules using generative adversarial networks (GANs)
title_short Generation of synthetic ground glass nodules using generative adversarial networks (GANs)
title_sort generation of synthetic ground glass nodules using generative adversarial networks (gans)
topic Original Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9708993/
https://www.ncbi.nlm.nih.gov/pubmed/36447082
http://dx.doi.org/10.1186/s41747-022-00311-y
work_keys_str_mv AT wangzhixiang generationofsyntheticgroundglassnodulesusinggenerativeadversarialnetworksgans
AT zhangzhen generationofsyntheticgroundglassnodulesusinggenerativeadversarialnetworksgans
AT fengying generationofsyntheticgroundglassnodulesusinggenerativeadversarialnetworksgans
AT hendrikslizzael generationofsyntheticgroundglassnodulesusinggenerativeadversarialnetworksgans
AT miclearazvanl generationofsyntheticgroundglassnodulesusinggenerativeadversarialnetworksgans
AT gietemahester generationofsyntheticgroundglassnodulesusinggenerativeadversarialnetworksgans
AT schoenmaekersjanna generationofsyntheticgroundglassnodulesusinggenerativeadversarialnetworksgans
AT dekkerandre generationofsyntheticgroundglassnodulesusinggenerativeadversarialnetworksgans
AT weeleonard generationofsyntheticgroundglassnodulesusinggenerativeadversarialnetworksgans
AT traversoalberto generationofsyntheticgroundglassnodulesusinggenerativeadversarialnetworksgans