Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation

Abstract Privacy concerns around sharing personally identifiable information are a major barrier to data sharing in medical research. In many cases, researchers have no interest in a particular individual’s information but rather aim to derive insights at the level of cohorts. Here, we utilise gener...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	August DuMont Schütte, Jürgen Hetzel, Sergios Gatidis, Tobias Hepp, Benedikt Dietz, Stefan Bauer, Patrick Schwab
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/721655c14be5423b9ddfc61457485802
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:721655c14be5423b9ddfc61457485802
record_format	dspace
spelling	oai:doaj.org-article:721655c14be5423b9ddfc614574858022021-12-02T15:15:22ZOvercoming barriers to data sharing with medical image generation: a comprehensive evaluation10.1038/s41746-021-00507-32398-6352https://doaj.org/article/721655c14be5423b9ddfc614574858022021-09-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00507-3https://doaj.org/toc/2398-6352Abstract Privacy concerns around sharing personally identifiable information are a major barrier to data sharing in medical research. In many cases, researchers have no interest in a particular individual’s information but rather aim to derive insights at the level of cohorts. Here, we utilise generative adversarial networks (GANs) to create medical imaging datasets consisting entirely of synthetic patient data. The synthetic images ideally have, in aggregate, similar statistical properties to those of a source dataset but do not contain sensitive personal information. We assess the quality of synthetic data generated by two GAN models for chest radiographs with 14 radiology findings and brain computed tomography (CT) scans with six types of intracranial haemorrhages. We measure the synthetic image quality by the performance difference of predictive models trained on either the synthetic or the real dataset. We find that synthetic data performance disproportionately benefits from a reduced number of classes. Our benchmark also indicates that at low numbers of samples per class, label overfitting effects start to dominate GAN training. We conducted a reader study in which trained radiologists discriminate between synthetic and real images. In accordance with our benchmark results, the classification accuracy of radiologists improves with an increasing resolution. Our study offers valuable guidelines and outlines practical conditions under which insights derived from synthetic images are similar to those that would have been derived from real data. Our results indicate that synthetic data sharing may be an attractive alternative to sharing real patient-level data in the right setting.August DuMont SchütteJürgen HetzelSergios GatidisTobias HeppBenedikt DietzStefan BauerPatrick SchwabNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 August DuMont Schütte Jürgen Hetzel Sergios Gatidis Tobias Hepp Benedikt Dietz Stefan Bauer Patrick Schwab Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation
description	Abstract Privacy concerns around sharing personally identifiable information are a major barrier to data sharing in medical research. In many cases, researchers have no interest in a particular individual’s information but rather aim to derive insights at the level of cohorts. Here, we utilise generative adversarial networks (GANs) to create medical imaging datasets consisting entirely of synthetic patient data. The synthetic images ideally have, in aggregate, similar statistical properties to those of a source dataset but do not contain sensitive personal information. We assess the quality of synthetic data generated by two GAN models for chest radiographs with 14 radiology findings and brain computed tomography (CT) scans with six types of intracranial haemorrhages. We measure the synthetic image quality by the performance difference of predictive models trained on either the synthetic or the real dataset. We find that synthetic data performance disproportionately benefits from a reduced number of classes. Our benchmark also indicates that at low numbers of samples per class, label overfitting effects start to dominate GAN training. We conducted a reader study in which trained radiologists discriminate between synthetic and real images. In accordance with our benchmark results, the classification accuracy of radiologists improves with an increasing resolution. Our study offers valuable guidelines and outlines practical conditions under which insights derived from synthetic images are similar to those that would have been derived from real data. Our results indicate that synthetic data sharing may be an attractive alternative to sharing real patient-level data in the right setting.
format	article
author	August DuMont Schütte Jürgen Hetzel Sergios Gatidis Tobias Hepp Benedikt Dietz Stefan Bauer Patrick Schwab
author_facet	August DuMont Schütte Jürgen Hetzel Sergios Gatidis Tobias Hepp Benedikt Dietz Stefan Bauer Patrick Schwab
author_sort	August DuMont Schütte
title	Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation
title_short	Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation
title_full	Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation
title_fullStr	Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation
title_full_unstemmed	Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation
title_sort	overcoming barriers to data sharing with medical image generation: a comprehensive evaluation
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/721655c14be5423b9ddfc61457485802
work_keys_str_mv	AT augustdumontschutte overcomingbarrierstodatasharingwithmedicalimagegenerationacomprehensiveevaluation AT jurgenhetzel overcomingbarrierstodatasharingwithmedicalimagegenerationacomprehensiveevaluation AT sergiosgatidis overcomingbarrierstodatasharingwithmedicalimagegenerationacomprehensiveevaluation AT tobiashepp overcomingbarrierstodatasharingwithmedicalimagegenerationacomprehensiveevaluation AT benediktdietz overcomingbarrierstodatasharingwithmedicalimagegenerationacomprehensiveevaluation AT stefanbauer overcomingbarrierstodatasharingwithmedicalimagegenerationacomprehensiveevaluation AT patrickschwab overcomingbarrierstodatasharingwithmedicalimagegenerationacomprehensiveevaluation
_version_	1718387514012598272

Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation

Ejemplares similares