Show simple item record

dc.contributor.authorThambawita, Vajira L B
dc.contributor.authorSalehi, Pegah
dc.contributor.authorSheshkal, Sajad Amouei
dc.contributor.authorHicks, Steven
dc.contributor.authorHammer, Hugo Lewi
dc.contributor.authorParasa, Sravanthi
dc.contributor.authorde Lange, Thomas
dc.contributor.authorHalvorsen, Pål
dc.contributor.authorRiegler, Michael
dc.date.accessioned2022-12-22T14:36:56Z
dc.date.available2022-12-22T14:36:56Z
dc.date.created2022-10-10T13:02:31Z
dc.date.issued2022-05-02
dc.identifier.citationPLOS ONE. 2022, 17 (5), 1-24.en_US
dc.identifier.issn1932-6203
dc.identifier.urihttps://hdl.handle.net/11250/3039279
dc.description.abstractAnalyzing medical data to find abnormalities is a time-consuming and costly task, particularly for rare abnormalities, requiring tremendous efforts from medical experts. Therefore, artificial intelligence has become a popular tool for the automatic processing of medical data, acting as a supportive tool for doctors. However, the machine learning models used to build these tools are highly dependent on the data used to train them. Large amounts of data can be difficult to obtain in medicine due to privacy reasons, expensive and time-consuming annotations, and a general lack of data samples for infrequent lesions. In this study, we present a novel synthetic data generation pipeline, called SinGAN-Seg, to produce synthetic medical images with corresponding masks using a single training image. Our method is different from the traditional generative adversarial networks (GANs) because our model needs only a single image and the corresponding ground truth to train. We also show that the synthetic data generation pipeline can be used to produce alternative artificial segmentation datasets with corresponding ground truth masks when real datasets are not allowed to share. The pipeline is evaluated using qualitative and quantitative comparisons between real data and synthetic data to show that the style transfer technique used in our pipeline significantly improves the quality of the generated data and our method is better than other state-of-the-art GANs to prepare synthetic images when the size of training datasets are limited. By training UNet++ using both real data and the synthetic data generated from the SinGAN-Seg pipeline, we show that the models trained on synthetic data have very close performances to those trained on real data when both datasets have a considerable amount of training data. In contrast, we show that synthetic data generated from the SinGAN-Seg pipeline improves the performance of segmentation models when training datasets do not have a considerable amount of data. All experiments were performed using an open dataset and the code is publicly available on GitHub.en_US
dc.language.isoengen_US
dc.publisherPublic Library of Scienceen_US
dc.relation.ispartofseriesPLOS ONE;17(5): e0267976
dc.rightsNavngivelse 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.no*
dc.subjectImaging techniquesen_US
dc.titleSinGAN-Seg: Synthetic training data generation for medical image segmentationen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionpublishedVersionen_US
dc.rights.holder© 2022 Thambawita et al.en_US
dc.source.articlenumbere0267976en_US
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode1
dc.identifier.doihttps://doi.org/10.1371/journal.pone.0267976
dc.identifier.cristin2060056
dc.source.journalPLOS ONEen_US
dc.source.volume17en_US
dc.source.issue5en_US
dc.source.pagenumber1-24en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Navngivelse 4.0 Internasjonal
Except where otherwise noted, this item's license is described as Navngivelse 4.0 Internasjonal