Cargando…
Toward Sharing Brain Images: Differentially Private TOF-MRA Images With Segmentation Labels Using Generative Adversarial Networks
Sharing labeled data is crucial to acquire large datasets for various Deep Learning applications. In medical imaging, this is often not feasible due to privacy regulations. Whereas anonymization would be a solution, standard techniques have been shown to be partially reversible. Here, synthetic data...
Autores principales: | , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9108458/ https://www.ncbi.nlm.nih.gov/pubmed/35586223 http://dx.doi.org/10.3389/frai.2022.813842 |
_version_ | 1784708708596449280 |
---|---|
author | Kossen, Tabea Hirzel, Manuel A. Madai, Vince I. Boenisch, Franziska Hennemuth, Anja Hildebrand, Kristian Pokutta, Sebastian Sharma, Kartikey Hilbert, Adam Sobesky, Jan Galinovic, Ivana Khalil, Ahmed A. Fiebach, Jochen B. Frey, Dietmar |
author_facet | Kossen, Tabea Hirzel, Manuel A. Madai, Vince I. Boenisch, Franziska Hennemuth, Anja Hildebrand, Kristian Pokutta, Sebastian Sharma, Kartikey Hilbert, Adam Sobesky, Jan Galinovic, Ivana Khalil, Ahmed A. Fiebach, Jochen B. Frey, Dietmar |
author_sort | Kossen, Tabea |
collection | PubMed |
description | Sharing labeled data is crucial to acquire large datasets for various Deep Learning applications. In medical imaging, this is often not feasible due to privacy regulations. Whereas anonymization would be a solution, standard techniques have been shown to be partially reversible. Here, synthetic data using a Generative Adversarial Network (GAN) with differential privacy guarantees could be a solution to ensure the patient's privacy while maintaining the predictive properties of the data. In this study, we implemented a Wasserstein GAN (WGAN) with and without differential privacy guarantees to generate privacy-preserving labeled Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) image patches for brain vessel segmentation. The synthesized image-label pairs were used to train a U-net which was evaluated in terms of the segmentation performance on real patient images from two different datasets. Additionally, the Fréchet Inception Distance (FID) was calculated between the generated images and the real images to assess their similarity. During the evaluation using the U-Net and the FID, we explored the effect of different levels of privacy which was represented by the parameter ϵ. With stricter privacy guarantees, the segmentation performance and the similarity to the real patient images in terms of FID decreased. Our best segmentation model, trained on synthetic and private data, achieved a Dice Similarity Coefficient (DSC) of 0.75 for ϵ = 7.4 compared to 0.84 for ϵ = ∞ in a brain vessel segmentation paradigm (DSC of 0.69 and 0.88 on the second test set, respectively). We identified a threshold of ϵ <5 for which the performance (DSC <0.61) became unstable and not usable. Our synthesized labeled TOF-MRA images with strict privacy guarantees retained predictive properties necessary for segmenting the brain vessels. Although further research is warranted regarding generalizability to other imaging modalities and performance improvement, our results mark an encouraging first step for privacy-preserving data sharing in medical imaging. |
format | Online Article Text |
id | pubmed-9108458 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-91084582022-05-17 Toward Sharing Brain Images: Differentially Private TOF-MRA Images With Segmentation Labels Using Generative Adversarial Networks Kossen, Tabea Hirzel, Manuel A. Madai, Vince I. Boenisch, Franziska Hennemuth, Anja Hildebrand, Kristian Pokutta, Sebastian Sharma, Kartikey Hilbert, Adam Sobesky, Jan Galinovic, Ivana Khalil, Ahmed A. Fiebach, Jochen B. Frey, Dietmar Front Artif Intell Artificial Intelligence Sharing labeled data is crucial to acquire large datasets for various Deep Learning applications. In medical imaging, this is often not feasible due to privacy regulations. Whereas anonymization would be a solution, standard techniques have been shown to be partially reversible. Here, synthetic data using a Generative Adversarial Network (GAN) with differential privacy guarantees could be a solution to ensure the patient's privacy while maintaining the predictive properties of the data. In this study, we implemented a Wasserstein GAN (WGAN) with and without differential privacy guarantees to generate privacy-preserving labeled Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) image patches for brain vessel segmentation. The synthesized image-label pairs were used to train a U-net which was evaluated in terms of the segmentation performance on real patient images from two different datasets. Additionally, the Fréchet Inception Distance (FID) was calculated between the generated images and the real images to assess their similarity. During the evaluation using the U-Net and the FID, we explored the effect of different levels of privacy which was represented by the parameter ϵ. With stricter privacy guarantees, the segmentation performance and the similarity to the real patient images in terms of FID decreased. Our best segmentation model, trained on synthetic and private data, achieved a Dice Similarity Coefficient (DSC) of 0.75 for ϵ = 7.4 compared to 0.84 for ϵ = ∞ in a brain vessel segmentation paradigm (DSC of 0.69 and 0.88 on the second test set, respectively). We identified a threshold of ϵ <5 for which the performance (DSC <0.61) became unstable and not usable. Our synthesized labeled TOF-MRA images with strict privacy guarantees retained predictive properties necessary for segmenting the brain vessels. Although further research is warranted regarding generalizability to other imaging modalities and performance improvement, our results mark an encouraging first step for privacy-preserving data sharing in medical imaging. Frontiers Media S.A. 2022-05-02 /pmc/articles/PMC9108458/ /pubmed/35586223 http://dx.doi.org/10.3389/frai.2022.813842 Text en Copyright © 2022 Kossen, Hirzel, Madai, Boenisch, Hennemuth, Hildebrand, Pokutta, Sharma, Hilbert, Sobesky, Galinovic, Khalil, Fiebach and Frey. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Artificial Intelligence Kossen, Tabea Hirzel, Manuel A. Madai, Vince I. Boenisch, Franziska Hennemuth, Anja Hildebrand, Kristian Pokutta, Sebastian Sharma, Kartikey Hilbert, Adam Sobesky, Jan Galinovic, Ivana Khalil, Ahmed A. Fiebach, Jochen B. Frey, Dietmar Toward Sharing Brain Images: Differentially Private TOF-MRA Images With Segmentation Labels Using Generative Adversarial Networks |
title | Toward Sharing Brain Images: Differentially Private TOF-MRA Images With Segmentation Labels Using Generative Adversarial Networks |
title_full | Toward Sharing Brain Images: Differentially Private TOF-MRA Images With Segmentation Labels Using Generative Adversarial Networks |
title_fullStr | Toward Sharing Brain Images: Differentially Private TOF-MRA Images With Segmentation Labels Using Generative Adversarial Networks |
title_full_unstemmed | Toward Sharing Brain Images: Differentially Private TOF-MRA Images With Segmentation Labels Using Generative Adversarial Networks |
title_short | Toward Sharing Brain Images: Differentially Private TOF-MRA Images With Segmentation Labels Using Generative Adversarial Networks |
title_sort | toward sharing brain images: differentially private tof-mra images with segmentation labels using generative adversarial networks |
topic | Artificial Intelligence |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9108458/ https://www.ncbi.nlm.nih.gov/pubmed/35586223 http://dx.doi.org/10.3389/frai.2022.813842 |
work_keys_str_mv | AT kossentabea towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT hirzelmanuela towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT madaivincei towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT boenischfranziska towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT hennemuthanja towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT hildebrandkristian towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT pokuttasebastian towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT sharmakartikey towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT hilbertadam towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT sobeskyjan towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT galinovicivana towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT khalilahmeda towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT fiebachjochenb towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks AT freydietmar towardsharingbrainimagesdifferentiallyprivatetofmraimageswithsegmentationlabelsusinggenerativeadversarialnetworks |