Tolga Çukur

Biography

Dr. Çukur is a faculty member at Bilkent University, Turkey since 2013. Prior to that, he was a postdoctoral fellow at University of California, Berkeley, CA. He worked with Prof. Jack L. Gallant in the Helen Wills Neuroscience Institute between 2010-2013. He devised novel machine learning techniques to build quantitative models of the human visual system under natural stimulation, and to infer the visual contents of the human brain.

He received his PhD in Electrical Engineering at Stanford University, CA. He worked with Prof. Dwight G. Nishimura and Prof. John M. Pauly as a member of the Magnetic Resonance Systems Research Laboratory between 2003-2009. During his doctoral work, he developed novel MRI acquisition and reconstruction methods to diagnose peripheral arterial disease, and to monitor treatment of cancer and other inflammatory diseases. Prior to his PhD, he received his B.S. degree in Electrical and Electronics Engineering from Bilkent University in 2003, as the class valedictorian.

Dr. Çukur was awarded Rambus Stanford Graduate Fellowship for his graduate studies. As a faculty member, he has received numerous prestigious awards including TUBITAK Career Award (2015), TUBA-GEBIP Outstanding Young Scientist Award (2015), BAGEP Young Scientist Award (2017), IEEE Turkey Research Encouragement Award (2017), Science Heroes Association Young Scientist of the Year Award (2017), METU Prof. Dr. Mustafa Parlar Foundation Research Incentive Award (2019), and TUSEB Aziz Sancar Incentive Award (2021). He is a senior member of IEEE (since 2017).

Research

My lab develops cutting-edge computational imaging techniques for biomedical research. Using these tools, we study the anatomy and function of biological systems in both normal and disease states. We have active research programs focusing on basic science and medical applications.

We pursue a computational neuroscience program targeted toward a quantitative understanding of human brain function. We use functional MRI and modern machine learning tools to study human sensory and cognitive systems during complex natural behavior. Specifically, we aim to locate functionally distinct areas of the human brain, and to reveal the type of information represented in each area. We are interested in how the human brain represents visual, auditory, and linguistic information; and how higher cognitive processes including attention, learning, and memory modulate these representations.

Our efforts in the medical field are focused on development of non-invasive diagnostic and monitoring technologies. We design ultra-fast magnetic resonance imaging (MRI) techniques through state-of-the-art medical physics and deep learning approaches. We adapt these novel techniques for targeted diagnosis of vascular, musculoskeletal and neurological diseases, and for molecular/cellular imaging.

Teaching

• EEE 443 / EEE 543 Neural Networks.
• EEE 482 / EEE 582 Computational Neuroscience.
• GE 461 Introduction to Data Science.
• MATH 241 Engineering Mathematics I.
• EEE 351 Engineering Electromagnetics.
• EEE 202 Circuit Theory.

Selected Publications

• Ozbey M, Dalmaz O, Dar SUH, Bedel HA, Ozturk S, Gungor A, Çukur T. Unsupervised Medical Image Translation with Adversarial Diffusion Models. IEEE Transactions on Medical Imaging. 2023. doi: 10.1109/TMI.2023.3290149.
• Gungor A, Dar SUH, Ozturk S, Korkmaz Y, Bedel HA, Elmas G, Ozbey M, Çukur T. Adaptive Diffusion Priors for Accelerated MRI Reconstruction. Medical Image Analysis. 2023; 88:102872.
• Bedel HA, Sivgin I, Dalmaz O, Dar SUH, Çukur T. BolT: Fused Window Transformers for fMRI Time Series Analysis. Medical Image Analysis. 2023; 88:102841.
• Elmas G, Dar SUH, Korkmaz Y, Ceyani E, Susam B, Ozbey M, Avestimehr S, Çukur T. Federated Learning of Generative Image Priors for MRI Reconstruction. IEEE Transactions on Medical Imaging. 2023 Jul;42(7):1996-2009.
• Gungor A, Askin B, Soydan DA, Saritas EU, Top CB, Çukur T. TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging. IEEE Transactions on Medical Imaging. 2022 Dec;41(12):3562-3574.
• Dalmaz O, Yurt M, Çukur T. ResViT: Residual Vision Transformers for Multi-Modal Medical Image Synthesis. IEEE Transactions on Medical Imaging. 2022 Oct;41(10):2598-2614.
• Korkmaz Y, Dar SUH, Yurt M, Ozbey M, Çukur T. Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers. IEEE Transactions on Medical Imaging. 2022 Jul;41(7):1747-1763.
• Dar SUH, Ozbey M, Catli AB, Çukur T. A transfer-learning approach for accelerated MRI using deep neural networks. Magnetic Resonance in Medicine. 2020 Aug;84(2):663–685.
• Dar SUH, Yurt M, Karacan L, Erdem A, Erdem E, Çukur T. Image synthesis in multi-contrast MRI with conditional generative adversarial networks. IEEE Transaction on Medical Imaging. 2019 Oct;38(10):2375-2388.
• Çukur T, Nishimoto S, Huth AG, Gallant JL. Attention during natural vision warps semantic representation across the human brain. Nature Neuroscience. 2013 Jun;16(6):763-70.
• Çukur T, Lustig M, Nishimura DG. Improving non-contrast-enhanced steady-state free precession angiography with compressed sensing. Magnetic Resonance in Medicine. 2009 May;61(5):1122-31.