Gokberk Elmas

Gokberk Elmas

Auto-generated profile, based on publicly available information

Gokberk Elmas

Department of Electrical and Electronics Engineering, Bilkent University, Ankara 06800, Turkey; National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara 06800, Turkey

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 June 2023 in Medical Image Analysis
Verified
Journal Article
Closed access
AGAlper Güngör
Alper Güngör
SDSalman Uh Dar
Salman Uh Dar
ŞÖŞaban Öztürk
Şaban Öztürk
YKYilmaz Korkmaz
Yilmaz Korkmaz
HBHasan A. Bedel
Hasan A. Bedel
TÇTolga Çukur
Tolga Çukur

9 November 2022 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
GEGokberk Elmas
Gokberk Elmas
SDSalman U. H. Dar
Salman U. H. Dar
YKYilmaz Korkmaz
Yilmaz Korkmaz
ECEmir Ceyani
Emir Ceyani
BSBurak Susam
Burak Susam
TÇTolga Çukur
Tolga Çukur
Multi-institutional efforts can facilitate training of deep MRI reconstruction models, albeit privacy risks arise during cross-site sharing of imaging data. Federated learning (FL) has recently been introduced to address privacy concerns by enabling distributed training without transfer of imaging data. Existing FL methods employ conditional reconstruction models to map from undersampled to fully-sampled acquisitions via explicit knowledge of the accelerated imaging operator. Since conditional models generalize poorly across different acceleration rates or sampling densities, imaging operators must be fixed between training and testing, and they are typically matched across sites. To improve patient privacy, performance and flexibility in multi-site collaborations, here we introduce Federated learning of Generative IMage Priors (FedGIMP) for MRI reconstruction. FedGIMP leverages a two-stage approach: cross-site learning of a generative MRI prior, and prior adaptation following injection of the imaging operator. The global MRI prior is learned via an unconditional adversarial model that synthesizes high-quality MR images based on latent variables. A novel mapper subnetwork produces site-specific latents to maintain specificity in the prior. During inference, the prior is first combined with subject-specific imaging operators to enable reconstruction, and it is then adapted to individual cross-sections by minimizing a data-consistency loss. Comprehensive experiments on multi-institutional datasets clearly demonstrate enhanced performance of FedGIMP against both centralized and FL methods based on conditional models.

23 February 2024 in Medical Image Analysis
Verified
Journal Article
Closed access
ODOnat Dalmaz
Onat Dalmaz
MMMuhammad U. Mirza
Muhammad U. Mirza
GEGokberk Elmas
Gokberk Elmas
MOMuzaffer Ozbey
Muzaffer Ozbey
SDSalman U.H. Dar
Salman U.H. Dar
TÇTolga Çukur
Tolga Çukur

6 April 2022 in arXiv
Verified
Preprint
Open access
PDF file
GEGokberk Elmas
Gokberk Elmas
SDSalman Uh Dar
Salman Uh Dar
YKYilmaz Korkmaz
Yilmaz Korkmaz
ECEmir Ceyani
Emir Ceyani
BSBurak Susam
Burak Susam
TÇTolga Çukur
Tolga Çukur
Multi-institutional efforts can facilitate training of deep MRI reconstruction models, albeit privacy risks arise during cross-site sharing of imaging data. Federated learning (FL) has recently been introduced to address privacy concerns by enabling distributed training without transfer of imaging data. Existing FL methods for MRI reconstruction employ conditional models to map from undersampled to fully-sampled acquisitions via explicit knowledge of the imaging operator. Since conditional models generalize poorly across different acceleration rates or sampling densities, imaging operators must be fixed between training and testing, and they are typically matched across sites. To improve generalization and flexibility in multi-institutional collaborations, here we introduce a novel method for MRI reconstruction based on Federated learning of Generative IMage Priors (FedGIMP). FedGIMP leverages a two-stage approach: cross-site learning of a generative MRI prior, and subject-specific injection of the imaging operator. The global MRI prior is learned via an unconditional adversarial model that synthesizes high-quality MR images based on latent variables. Specificity in the prior is preserved via a mapper subnetwork that produces site-specific latents. During inference, the prior is combined with subject-specific imaging operators to enable reconstruction, and further adapted to individual test samples by minimizing data-consistency loss. Comprehensive experiments on multi-institutional datasets clearly demonstrate enhanced generalization performance of FedGIMP against site-specific and federated methods based on conditional models, as well as traditional reconstruction methods.