# Tolga Çukur, Ph.D.

> Tolga Çukur is a Professor in the Department of Electrical and Electronics Engineering and the Department of Neuroscience at Bilkent University (Ankara, Türkiye), the Director of the National Magnetic Resonance Research Center (UMRAM), and Deputy Editor-in-Chief of IEEE Transactions on Medical Imaging. He leads ICON Lab, which develops deep learning and computational imaging methods for MRI, CT and functional MRI.

He received his PhD (2009) and MS (2005) in Electrical Engineering from Stanford University and his BSc (2003) from Bilkent University, and was a postdoctoral fellow in neuroscience at UC Berkeley (2010–2013). He is a Fellow of ISMRM (2024) and a Senior Member of IEEE.

## Research

- Physics-driven deep learning for MRI and CT reconstruction (diffusion priors, diffusion bridges, state-space models, zero-shot reconstruction)
- Multi-modal medical image synthesis and translation (GANs, vision transformers, diffusion models)
- Federated and privacy-preserving learning for medical imaging
- Medical vision-language models and image analysis
- Magnetic particle imaging (MPI)
- Functional MRI and computational neuroscience (natural vision, attention, fMRI time-series models)

## Selected publications

- Mirza MU et al., Çukur T. [Learning Fourier-Constrained Diffusion Bridges for MRI Reconstruction](https://doi.org/10.1109/TMI.2026.3673956). IEEE Transactions on Medical Imaging, 2026. Code: https://github.com/icon-lab/FDB
- Kabas B et al., Çukur T. [Physics-Driven Autoregressive State Space Models for Medical Image Reconstruction](https://doi.org/10.1109/TMI.2026.3716153). IEEE Transactions on Medical Imaging, 2026. Code: https://github.com/icon-lab/MambaRoll
- Atli OF et al., Çukur T. [I2I-Mamba: Multi-Modal Medical Image Synthesis via Selective State Space Modeling](https://doi.org/10.1109/TBME.2026.3698056). IEEE Transactions on Biomedical Engineering, 2026. Code: https://github.com/icon-lab/I2I-Mamba
- Arslan F et al., Çukur T. [Self-Consistent Recursive Diffusion Bridge for Medical Image Translation](https://www.icon.bilkent.edu.tr/docs/Arslan-2025.pdf). Medical Image Analysis, 2025. Code: https://github.com/icon-lab/SelfRDB
- Dalmaz O et al., Çukur T. [One Model to Unite Them All: Personalized Federated Learning of Multi-Contrast MRI Synthesis](https://www.icon.bilkent.edu.tr/docs/Dalmaz-2024.pdf). Medical Image Analysis, 2024. Code: https://github.com/icon-lab/pFLSynth
- Bedel HA, Çukur T. [DreaMR: Diffusion-Driven Counterfactual Explanation for Functional MRI](https://doi.org/10.1109/TMI.2024.3507008). IEEE Transactions on Medical Imaging, 2024. Code: https://github.com/icon-lab/DreaMR
- Ozbey M et al., Çukur T. [Unsupervised Medical Image Translation with Adversarial Diffusion Models](https://ieeexplore.ieee.org/document/10167641). IEEE Transactions on Medical Imaging, 2023. Code: https://github.com/icon-lab/SynDiff
- Dalmaz O, Yurt M, Çukur T. [ResViT: Residual Vision Transformers for Multi-Modal Medical Image Synthesis](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9758823). IEEE Transactions on Medical Imaging, 2022. Code: https://github.com/icon-lab/ResViT
- Dar SUH et al., Çukur T. [Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks](https://ieeexplore.ieee.org/document/8653423). IEEE Transactions on Medical Imaging, 2019. Code: https://github.com/icon-lab/pGAN-cGAN
- Çukur T, Nishimoto S, Huth AG, Gallant JL. [Attention During Natural Vision Warps Semantic Representation Across the Human Brain](https://www.nature.com/articles/nn.3381). Nature Neuroscience, 2013.

## Links

- [Personal page](https://kilyos.ee.bilkent.edu.tr/~cukur/)
- [ICON Lab](https://www.icon.bilkent.edu.tr/): research areas, full publication list with PDFs, people
- [ICON Lab llms.txt](https://www.icon.bilkent.edu.tr/llms.txt)
- [Code on GitHub](https://github.com/icon-lab)
- [Google Scholar](https://scholar.google.com/citations?user=5GLKJvwAAAAJ)
- [ORCID](https://orcid.org/0000-0002-2296-851X)
- [UMRAM](https://umram.bilkent.edu.tr/)
- Contact: cukur@ee.bilkent.edu.tr