A transfer-learning approach for accelerated MRI using deep neural networks

dc.citation.epage685en_US
dc.citation.issueNumber2en_US
dc.citation.spage663en_US
dc.citation.volumeNumber84en_US
dc.contributor.authorDar, Salman Ul Hassan
dc.contributor.authorÖzbey, Muzaffer
dc.contributor.authorÇatlı, Ahmet Burak
dc.contributor.authorÇukur, Tolga
dc.contributor.bilkentauthorDar, Salman Ul Hassan
dc.contributor.bilkentauthorÖzbey, Muzaffer
dc.contributor.bilkentauthorÇatlı, Ahmet Burak
dc.contributor.bilkentauthorÇukur, Tolga
dc.date.accessioned2021-03-05T11:14:26Z
dc.date.available2021-03-05T11:14:26Z
dc.date.issued2020
dc.departmentAysel Sabuncu Brain Research Center (BAM)en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.departmentInterdisciplinary Program in Neuroscience (NEUROSCIENCE)en_US
dc.departmentNational Magnetic Resonance Research Center (UMRAM)en_US
dc.description.abstractPurpose: Neural networks have received recent interest for reconstruction of undersampled MR acquisitions. Ideally, network performance should be optimized by drawing the training and testing data from the same domain. In practice, however, large datasets comprising hundreds of subjects scanned under a common protocol are rare. The goal of this study is to introduce a transfer‐learning approach to address the problem of data scarcity in training deep networks for accelerated MRI. Methods: Neural networks were trained on thousands (upto 4 thousand) of samples from public datasets of either natural images or brain MR images. The networks were then fine‐tuned using only tens of brain MR images in a distinct testing domain. Domain‐transferred networks were compared to networks trained directly in the testing domain. Network performance was evaluated for varying acceleration factors (4‐10), number of training samples (0.5‐4k), and number of fine‐tuning samples (0‐100). Results: The proposed approach achieves successful domain transfer between MR images acquired with different contrasts (T1‐ and T2‐weighted images) and between natural and MR images (ImageNet and T1‐ or T2‐weighted images). Networks obtained via transfer learning using only tens of images in the testing domain achieve nearly identical performance to networks trained directly in the testing domain using thousands (upto 4 thousand) of images. Conclusion: The proposed approach might facilitate the use of neural networks for MRI reconstruction without the need for collection of extensive imaging datasets.en_US
dc.embargo.release2021-08-01
dc.identifier.doi10.1002/mrm.28148en_US
dc.identifier.issn0740-3194
dc.identifier.urihttp://hdl.handle.net/11693/75833
dc.language.isoEnglishen_US
dc.publisherWileyen_US
dc.relation.isversionofhttps://dx.doi.org/10.1002/mrm.28148en_US
dc.source.titleMagnetic Resonance in Medicineen_US
dc.subjectAccelerated MRIen_US
dc.subjectCompressive sensingen_US
dc.subjectDeep learningen_US
dc.subjectImage reconstructionen_US
dc.subjectTransfer learningen_US
dc.titleA transfer-learning approach for accelerated MRI using deep neural networksen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
A_transfer_learning_approach_for_accelerated_MRI_using_deep_neural_networks.pdf
Size:
4.44 MB
Format:
Adobe Portable Document Format
Description:
View / Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: