Michael Lustig

Michael Lustig is an Associate Professor in the Department of Electrical Engineering and Computer Science at UC Berkeley. His research focuses on computational imaging methods in magnetic resonance imaging (MRI), with emphasis on compressed sensing, motion correction, and machine learning applications in medical imaging. He has contributed significantly to the development of open-source tools like SparseMRI and reconstruction algorithms such as ENLIVE and DSLR+.

• PhD in Electrical Engineering, Stanford University (2008)
• MSc in Electrical Engineering, Stanford University (2004)
• BSc in Electrical Engineering, Technion, Israel Institute of Technology (2002)

Lustig’s work spans advanced MRI techniques including ultra-short echo time (UTE) imaging, low-rank reconstruction, and physics-informed neural networks. He has pioneered methods for integrating RF motion sensing via beat pilot tones during MRI scans and developed tools for memory-efficient large-scale image reconstruction.

His recent publications focus on MRDust (wireless implantable interfaces), Twstr coils (discrete-component-free MRI hardware), and Resonet (noise-trained off-resonance correction). These works reflect trends in self-supervised learning, contact-free motion detection, and hardware-software co-design for diagnostic imaging.

Scientific Awards & Fellowships

• International Society for MR in Medicine Gold Medal (2025)
• Pioneer Award (2023)
• ISMRM Fellow (2017)
• Electrical Engineering Outstanding Teaching Award (2016)
• Bakar Spark Award (2015)
• Okawa Research Grant (2014)
• Sloan Research Fellow (2013)
• Hellman Fellow (2012)

Lustig advises PhD students like Frank Ong and leads research at the MikLab, contributing to open-source software platforms such as SigPy and DeepInPy. His work bridges computational methods, hardware innovation, and clinical translation in MRI.