Berkin Bilgic - BRAIN Lab

About me:

I am an Associate Professor in Radiology at Massachusetts General Hospital and Harvard Medical School. I head the BRAIN (Bilgic Reconstruction Acquisition for Imaging Neuroscience) lab at the Martinos Center for Biomedical Imaging.

I am interested in MRI data acquisition and reconstruction, in particular,

• Fast clinical imaging,
• Self-supervised machine learning,
• Quantitative parameter mapping,
• Diffusion imaging, and
• Open-source pulse sequence development.

• Associate Professor in Radiology, MGH/Harvard, Nov 2023 -
• Affiliated Faculty, Health Sciences & Technology, Harvard-MIT, Jun 2018 -
• Assistant Professor in Radiology, MGH/Harvard, Jun 2019 - Nov 2023
• Instructor in Radiology, MGH/Harvard, May 2016 - Jun 2019
• Research Fellow in Radiology, MGH/Harvard, Feb 2013 - May 2016
• PhD in EECS, MIT, Feb 2010 - Feb 2013
• SM in EECS, MIT, Sep 2008 - Feb 2010
• BS in EE, Bogazici University, Sep 2004 - Jun 2008
• BS in Physics, Bogazici University, Sep 2004 - Jun 2008

A research fellowship in novel acquisition and reconstruction strategies for high-fidelity MRI is open in our group, effective December 2024. Flyer

• Shohei wins the Prince-Meaney Translational Science Award
• Shohei wins the 2023-24 Clinical Translation Challenge: Unmet Needs
• Yohan becomes a Junior Fellow of ISMRM
• Yohan earns a Summa Cum Laude award for top 5% abstract, also selected among the AMPC Higlighted abstracts
• Yohan wins the Diffusion Study Group best trainee presentation award

• H Yu et al: SubZero: Subspace Zero-Shot MRI Reconstruction, #0829, power pitch Python code on GitHub
• A Heydari et al: Joint MR T1 and T2* Parameter Mapping with Scan Specific Unsupervised Networks, #1617, digital poster Python code on GitHub
• IA Vurankaya et al: Self-Supervised Deep Learning Reconstruction for Highly Accelerated Diffusion Imaging, #0831, power pitch Python code on GitHub
• Y Arefeen et al: Improved T1 and T2 mapping in 3D-QALAS using temporal subspaces and Cramer-Rao-bound flip angle optimization enabled by auto-differentiation, #0671, oral Python code on GitHub
• X Wang et al: Model-based phase-difference reconstruction for accelerated phase-based T2 mapping, #4960, digital poster BART code on GitHub
• X Wang et al: An Open-Source Self-navigated Multi-Echo Gradient Echo Acquisition for R2* and QSM mapping using Pulseq and Model-Based Reconstruction, #0420, combined educational & scientific session Matlab code on GitHub
• Y Jun et al: Zero-DeepSub: Zero-Shot Deep Subspace Reconstruction for Multiparametric Quantitative MRI Using QALAS, #1105, power pitch Python code on GitHub
• Y Jun et al: SSL-QALAS: Self-Supervised Learning for Multiparametric Quantitative MRI Using QALAS, #2155, digital poster Python code on GitHub
• TH Kim et al: Multi-echo MRI Reconstruction with Iteratively Refined Zero-shot Spatio-Temporal Deep Generative Prior, #0828, power pitch Python code on GitHub
• J Cho et al: VUDU-SAGE: Efficient T2 and T2* Mapping using Joint Reconstruction for Motion-Robust, Distortion-Free, Multi-Shot, Multi-Echo EPI, #2202, digital poster Matlab code on GitHub
• G Varela-Mattatall et al: Rapid Mesoscale MP2RAGE Imaging at Ultra High Field with Controlled Aliasing, #0539, oral Matlab code on GitLab

• Y Jun et al: Deep Subspace Reconstruction with Zero-Shot Learning for Multiparametric Quantitative MRI, oral PDF
• TH Kim et al: Zero-shot Prior Learning of Spatio-temporal Multi-echo/contrast MRI Reconstruction with Iterative Refinement PDF Code
• G Varela Mattatall et al: Parallel CS-Wave PDF
• X Wang et al: Model-Based Phase-Difference Reconstruction for Accelerated Phase-Based T2 Mapping PDF
• J Cho et al: VUDU-SAGE: Efficient T2 and T2* Mapping using Joint Reconstruction for Motion-Robust, Distortion-Free, Multi-Shot, Multi-Echo EPI PDF Code
• Y Arefeen et al: Improved T1 and T2 mapping in 3D-QALAS using temporal subspaces and flip angle optimization enabled by auto-differentiation PDF
• X Wang et al: Open-Source Self-navigated Multi-Echo GRE Acquisition for R2* and QSM mapping using Pulseq and Model-Based Reconstruction PDF Code
• X Wang et al: Model-Based Reconstruction for Joint Estimation of T1, T2 and B0 Inhomogeneity Maps Using Single-Shot Inversion-Recovery Multi-Echo Radial FLASH PDF

• Y Arefeen et al: Learning compact latent representations of signal evolution for improved shuffling reconstruction, #0247 Latent shuffling code on Github
• J Cho et al: Variable Flip, Blip-Up and -Down Undersampling (VUDU) Enables Motion-Robust, Distortion-Free Multi-Shot EPI, #0757 VUDU code on Github
• J Cho et al: Rapid Quantitative Imaging Using Wave-Encoded Model-Based Deep Learning for Joint Reconstruction, #0435 wave-MoDL code on Github
• MY Avci et al: Quantifying the uncertainty of neural networks using Monte Carlo dropout for safer and more accurate deep learning based quantitative MRI, #4978 Monte Carlo dropout code on Github
• A Lin et al: Bayesian sensitivity encoding enables parameter-free, highly accelerated joint multi-contrast reconstruction, #3444 joint Bayesian sensitivity encoding code on Github
• TH Kim et al: Accelerated MR Parameter Mapping with Scan-specific Unsupervised Networks, #4402 MAPLE code on Github
• G Varela-Mattatall et al: Rapid CS-Wave MPRAGE acquisition with automated parameter selection, #1604 CS-Wave code on Github

We gratefully acknowledge our completed or current funding: