Semi-supervised learning of MRI synthesis without fully-sampled ground truths

Simple item page
buir.contributor.authorYurt, Mahmut
buir.contributor.authorDalmaz, Onat
buir.contributor.authorDar, Salman
buir.contributor.authorÖzbey, Muzaffer
buir.contributor.authorÇukur, Tolga
buir.contributor.orcidÇukur, Tolga|0000-0002-2296-851X
buir.contributor.orcidÖzbey, Muzaffer|0000-0002-6262-8915
dc.citation.epage3906en_US
dc.citation.issueNumber12en_US
dc.citation.spage3895en_US
dc.citation.volumeNumber41en_US
dc.contributor.authorYurt, Mahmut
dc.contributor.authorDalmaz, Onat
dc.contributor.authorDar, Salman
dc.contributor.authorÖzbey, Muzaffer
dc.contributor.authorTınaz, Berk
dc.contributor.authorOğuz, Kader
dc.contributor.authorÇukur, Tolga
dc.date.accessioned2023-02-16T07:57:11Z
dc.date.available2023-02-16T07:57:11Z
dc.date.issued2022-08-16
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractLearning-based translation between MRI contrasts involves supervised deep models trained using high-quality source- and target-contrast images derived from fully-sampled acquisitions, which might be difficult to collect under limitations on scan costs or time. To facilitate curation of training sets, here we introduce the first semi-supervised model for MRI contrast translation (ssGAN) that can be trained directly using undersampled k-space data. To enable semi-supervised learning on undersampled data, ssGAN introduces novel multi-coil losses in image, k-space, and adversarial domains. The multi-coil losses are selectively enforced on acquired k-space samples unlike traditional losses in single-coil synthesis models. Comprehensive experiments on retrospectively undersampled multi-contrast brain MRI datasets are provided. Our results demonstrate that ssGAN yields on par performance to a supervised model, while outperforming single-coil models trained on coil-combined magnitude images. It also outperforms cascaded reconstruction-synthesis models where a supervised synthesis model is trained following self-supervised reconstruction of undersampled data. Thus, ssGAN holds great promise to improve the feasibility of learning-based multi-contrast MRI synthesis.en_US
dc.identifier.doi10.1109/TMI.2022.3199155en_US
dc.identifier.eissn1558-254X
dc.identifier.issn0278-0062
dc.identifier.urihttp://hdl.handle.net/11693/111406
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttps://www.doi.org/10.1109/TMI.2022.3199155en_US
dc.source.titleIEEE Transactions on Medical Imagingen_US
dc.subjectMagnetic resonance imagingen_US
dc.subjectImage synthesisen_US
dc.subjectSemi-superviseden_US
dc.subjectAdversarialen_US
dc.subjectUndersampleden_US
dc.titleSemi-supervised learning of MRI synthesis without fully-sampled ground truthsen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Semi-Supervised_Learning_of_MRI_Synthesis_Without_Fully-Sampled_Ground_Truths.pdf
Size:
8.44 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Electrical and Electronics Engineering