Self-supervised dynamic MRI reconstruction
buir.contributor.author | Acar, Mert | |
buir.contributor.author | Çukur, Tolga | |
buir.contributor.orcid | Çukur, Tolga|0000-0002-2296-851X | |
dc.citation.epage | 53 | en_US |
dc.citation.spage | 36 | en_US |
dc.citation.volumeNumber | 12964 | en_US |
dc.contributor.author | Acar, Mert | |
dc.contributor.author | Çukur, Tolga | |
dc.contributor.author | Öksüz, İlkay | |
dc.coverage.spatial | Strasbourg, France | en_US |
dc.date.accessioned | 2022-01-27T07:09:03Z | |
dc.date.available | 2022-01-27T07:09:03Z | |
dc.date.issued | 2021-09-25 | |
dc.department | Department of Electrical and Electronics Engineering | en_US |
dc.department | National Magnetic Resonance Research Center (UMRAM) | en_US |
dc.description | Conference Name: International Workshop on Machine Learning for Medical Image Reconstruction, MLMIR 2021 | en_US |
dc.description | Date of Conference: 1 October 2021 | en_US |
dc.description.abstract | Deep 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.doi | 10.1007/978-3-030-88552-6_4 | en_US |
dc.identifier.eisbn | 978-3-030-88552-6 | |
dc.identifier.eissn | 1611-3349 | en_US |
dc.identifier.isbn | 978-3-030-88551-9 | |
dc.identifier.isbn | 978-3-030-88551-9 | en_US |
dc.identifier.issn | 0302-9743 | en_US |
dc.identifier.uri | http://hdl.handle.net/11693/76819 | |
dc.language.iso | English | en_US |
dc.publisher | Springer | en_US |
dc.relation.ispartofseries | Lecture Notes in Computer Science (LNCS) | |
dc.relation.isversionof | https://dx.doi.org/10.1007/978-3-030-88552-6_4 | en_US |
dc.source.title | Lecture Notes in Computer Science | en_US |
dc.subject | Cardiac MRI | en_US |
dc.subject | Dynamic reconstruction | en_US |
dc.subject | Self-supervised learning | en_US |
dc.subject | Convolutional neural networks | en_US |
dc.title | Self-supervised dynamic MRI reconstruction | en_US |
dc.type | Conference Paper | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Self-supervised_Dynamic_MRI_Reconstruction.pdf
- Size:
- 4.63 MB
- Format:
- Adobe Portable Document Format
- Description:
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.69 KB
- Format:
- Item-specific license agreed upon to submission
- Description: