mustGAN: multi-stream generative adversarial networks for MR image synthesis

Simple item page
buir.contributor.authorYurt, Mahmut
buir.contributor.authorDar, Salman Uh
buir.contributor.authorOğuz, Kader K.
buir.contributor.authorÇukur, Tolga
buir.contributor.orcidYurt, Mahmut|0000-0003-3280-4217
buir.contributor.orcidÇukur, Tolga|0000-0002-2296-851X
dc.citation.epage101944-13en_US
dc.citation.spage101944-1en_US
dc.citation.volumeNumber70en_US
dc.contributor.authorYurt, Mahmut
dc.contributor.authorDar, Salman Uh
dc.contributor.authorErdem, A.
dc.contributor.authorErdem, E.
dc.contributor.authorOğuz, Kader K.
dc.contributor.authorÇukur, Tolga
dc.date.accessioned2022-02-18T09:16:36Z
dc.date.available2022-02-18T09:16:36Z
dc.date.issued2021-05
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractMulti-contrast MRI protocols increase the level of morphological information available for diagnosis. Yet, the number and quality of contrasts are limited in practice by various factors including scan time and patient motion. Synthesis of missing or corrupted contrasts from other high-quality ones can alleviate this limitation. When a single target contrast is of interest, common approaches for multi-contrast MRI involve either one-to-one or many-to-one synthesis methods depending on their input. One-to-one methods take as input a single source contrast, and they learn a latent representation sensitive to unique features of the source. Meanwhile, many-to-one methods receive multiple distinct sources, and they learn a shared latent representation more sensitive to common features across sources. For enhanced image synthesis, we propose a multi-stream approach that aggregates information across multiple source images via a mixture of multiple one-to-one streams and a joint many-to-one stream. The complementary feature maps generated in the one-to-one streams and the shared feature maps generated in the many-to-one stream are combined with a fusion block. The location of the fusion block is adaptively modified to maximize task-specific performance. Quantitative and radiological assessments on T1,- T2-, PD-weighted, and FLAIR images clearly demonstrate the superior performance of the proposed method compared to previous state-of-the-art one-to-one and many-to-one methods.en_US
dc.embargo.release2023-05-31
dc.identifier.doi10.1016/j.media.2020.101944en_US
dc.identifier.issn1361-8415
dc.identifier.urihttp://hdl.handle.net/11693/77499
dc.language.isoEnglishen_US
dc.publisherElsevier BVen_US
dc.relation.isversionofhttps://doi.org/10.1016/j.media.2020.101944en_US
dc.source.titleMedical Image Analysisen_US
dc.subjectMagnetic resonance imaging (MRI)en_US
dc.subjectMulti-contrasten_US
dc.subjectGenerative adversarial networks (GAN)en_US
dc.subjectImage synthesisen_US
dc.subjectMulti-streamen_US
dc.subjectFusionen_US
dc.titlemustGAN: multi-stream generative adversarial networks for MR image synthesisen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
mustGAN_multi-stream_Generative_Adversarial_Networks_for_MR_Image_Synthesis.pdf
Size:
3.37 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