Image synthesis in multi-contrast MRI with conditional generative adversarial networks

Simple item page
buir.contributor.authorDar, Salman UH.
buir.contributor.authorYurt, Mahmut
buir.contributor.authorÇukur, Tolga
dc.citation.epage2388en_US
dc.citation.issueNumber10en_US
dc.citation.spage2375en_US
dc.citation.volumeNumber38en_US
dc.contributor.authorDar, Salman UH.en_US
dc.contributor.authorYurt, Mahmuten_US
dc.contributor.authorÇukur, Tolgaen_US
dc.contributor.authorKaracan, L.en_US
dc.contributor.authorErdem, A.en_US
dc.contributor.authorErdem, E.en_US
dc.date.accessioned2020-02-04T13:32:57Z
dc.date.available2020-02-04T13:32:57Z
dc.date.issued2019-10
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractAcquiring images of the same anatomy with multiple different contrasts increases the diversity of diagnostic information available in an MR exam. Yet, the scan time limitations may prohibit the acquisition of certain contrasts, and some contrasts may be corrupted by noise and artifacts. In such cases, the ability to synthesize unacquired or corrupted contrasts can improve diagnostic utility. For multi-contrast synthesis, the current methods learn a nonlinear intensity transformation between the source and target images, either via nonlinear regression or deterministic neural networks. These methods can, in turn, suffer from the loss of structural details in synthesized images. Here, in this paper, we propose a new approach for multi-contrast MRI synthesis based on conditional generative adversarial networks. The proposed approach preserves intermediate-to-high frequency details via an adversarial loss, and it offers enhanced synthesis performance via pixel-wise and perceptual losses for registered multi-contrast images and a cycle-consistency loss for unregistered images. Information from neighboring cross-sections are utilized to further improve synthesis quality. Demonstrations on T 1 - and T 2 - weighted images from healthy subjects and patients clearly indicate the superior performance of the proposed approach compared to the previous state-of-the-art methods. Our synthesis approach can help improve the quality and versatility of the multi-contrast MRI exams without the need for prolonged or repeated examinations.en_US
dc.identifier.doi10.1109/TMI.2019.2901750en_US
dc.identifier.eissn1558-254X
dc.identifier.issn0278-0062
dc.identifier.urihttp://hdl.handle.net/11693/53059
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttps://doi.org/10.1109/TMI.2019.2901750en_US
dc.source.titleIEEE Transactions on Medical Imagingen_US
dc.subjectGenerative adversarial networken_US
dc.subjectImage synthesisen_US
dc.subjectMulti-contrast MRIen_US
dc.subjectPixel-wise lossen_US
dc.subjectCycleconsistency lossen_US
dc.titleImage synthesis in multi-contrast MRI with conditional generative adversarial networksen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Image_Synthesis_in_Multi-Contrast_MRI_with_Conditional_Generative_Adversarial_Networks.pdf
Size:
4.71 MB
Format:
Adobe Portable Document Format
Description:
Download

Collections

Department of Electrical and Electronics Engineering