Self-supervised dynamic MRI reconstruction

Simple item page
buir.contributor.authorAcar, Mert
buir.contributor.authorÇukur, Tolga
buir.contributor.orcidÇukur, Tolga|0000-0002-2296-851X
dc.citation.epage53en_US
dc.citation.spage36en_US
dc.citation.volumeNumber12964en_US
dc.contributor.authorAcar, Mert
dc.contributor.authorÇukur, Tolga
dc.contributor.authorÖksüz, İlkay
dc.coverage.spatialStrasbourg, Franceen_US
dc.date.accessioned2022-01-27T07:09:03Z
dc.date.available2022-01-27T07:09:03Z
dc.date.issued2021-09-25
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.departmentNational Magnetic Resonance Research Center (UMRAM)en_US
dc.descriptionConference Name: International Workshop on Machine Learning for Medical Image Reconstruction, MLMIR 2021en_US
dc.descriptionDate of Conference: 1 October 2021en_US
dc.description.abstractDeep learning techniques have recently been adopted for accelerating dynamic MRI acquisitions. Yet, common frameworks for model training rely on availability of large sets of fully-sampled MRI data to construct a ground-truth for the network output. This heavy reliance is undesirable as it is challenging to collect such large datasets in many applications, and even impossible for high spatiotemporal-resolution protocols. In this paper, we introduce self-supervised training to deep neural architectures for dynamic reconstruction of cardiac MRI. We hypothesize that, in the absence of ground-truth data, elevating complexity in self-supervised models can instead constrain model performance due to the deficiencies in training data. To test this working hypothesis, we adopt self-supervised learning on recent state-of-the-art deep models for dynamic MRI, with varying degrees of model complexity. Comparison of supervised and self-supervised variants of deep reconstruction models reveals that compact models have a remarkable advantage in reliability against performance loss in self-supervised settings.en_US
dc.identifier.doi10.1007/978-3-030-88552-6_4en_US
dc.identifier.eisbn978-3-030-88552-6
dc.identifier.eissn1611-3349en_US
dc.identifier.isbn978-3-030-88551-9
dc.identifier.isbn978-3-030-88551-9en_US
dc.identifier.issn0302-9743en_US
dc.identifier.urihttp://hdl.handle.net/11693/76819
dc.language.isoEnglishen_US
dc.publisherSpringeren_US
dc.relation.ispartofseriesLecture Notes in Computer Science (LNCS)
dc.relation.isversionofhttps://dx.doi.org/10.1007/978-3-030-88552-6_4en_US
dc.source.titleLecture Notes in Computer Scienceen_US
dc.subjectCardiac MRIen_US
dc.subjectDynamic reconstructionen_US
dc.subjectSelf-supervised learningen_US
dc.subjectConvolutional neural networksen_US
dc.titleSelf-supervised dynamic MRI reconstructionen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Self-supervised_Dynamic_MRI_Reconstruction.pdf
Size:
4.63 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
National Magnetic Resonance Research Center (UMRAM)