Efrat Shimron

Postdoctoral Fellow

Department of Electrical Engineering and Computer Sciences (EECS)

UC Berkeley

Efrat Shimron

About

I am a postdoc in the Department of Electrical Engineering and Computer Sciences (EECS) at UC Berkeley. I have the pleasure of being co-advised by Prof. Michael (Miki) Lustig (UC Berkeley) and Prof. Shreyas Vasanawala (Stanford). I work with their collaborative groups on developing MRI reconstruction methods for rapid dynamic MRI scans. My research leverages Machine Learning, physics-based modelling and computational imaging.

In 2015-2019 I was a PhD student at the Technion - Israel Institute of Technology. I spent wonderful years in the lab of my PhD advisor Prof. Haim Azhari, where I developed sparsity-based methods for MR image reconstruction.

Research

This work received a Magna cum Laude Award at the International Society of Magnetic Resonance in Medicine (ISMRM) 2021 Annual Meeting

New! The Subtle Inverse Crimes paper is available online.

Recorded 5-min talk (requires registration to ISMRM'21 conference).

Efrat Shimron - TED Compressed Sensing

Temporal Differences (TED) Compressed Sensing

TED is a Compressed Sensing method for dynamic MRI, which enables accurate temperature reconstruction from sub-Nyquist k-space measurements. Our paper demonstrated that TED is highly suitable for temperature monitoring in MR-guided High Intensity Focused Ultrasound (MRgHIFU) treatments.

TED is generally applicable to dynamic MRI scans and can therefore be applied for different scan types. Our code is simple & fast. Let us know if you find a cool new app!

Efrat Shimron - CORE-PI method

CORE-PI

CORE-PI is a parallel imaging method for MRI. It enables reconstruction from subsampled k-space data acquired with multi-coil arrays in 2D Cartesian scans. CORE-PI is parameter-free, i.e. you there's no to calibrate any hyperparamer in order to use it. Check out our code!

Efrat Shimron - CORE-Deblur

CORE-Deblur

CORE-Deblur is a Parallel Imaging Compressed Sensing (PI-CS) method.

Our paper introduced the concept of MR image reconstruction by deblurring using Compressed Sensing (CS), and showed that CORE-Deblur can expedite CS computations: the number of required iterations is reduced by a factor of 10.

News

  • Upcoming: I will give a talk about Subtle Inverse Crimes at the MRI Together conference (Dec 14, 2021).

  • October 2021: I gave a talk titled "Subtle Inverse Crimes: When AI is Overly-optimistic" at the Utah Imaging Elevated Symposium for Emerging Investigators. I really enjoyed this wonderful in-person conference!

  • September 2021: our Subtle Inverse Crimes paper (preprint) is available online - here.

  • September 2021: I gave a talk at Harvard's Workshop on MRI Acquisition and Reconstruction.

  • June 2021: I was named as an Emerging Investigator by the committee of the Imaging Elevated: Utah Symposium for Emerging Investigators (October 2021).

  • May 2021: our "Subtle Inverse Crimes" abstract received a magna cum laude award in the ISMRM conference and was selected as a finalist in the Magnetic Moments competition. Check it out to see our surprising results! The abstract is here and the video is is here .

  • May 2021: I co-organized the MR-Pub Competition for Interactive Code Demos.

  • March 2021: I was elected for the ISMRM Reproducible Research Study Group Governing Committee, as the Trainee Representative.

  • December 2020: I gave a tutorial on advanced regularization methods for dynamic MRI using BART, an open-source toolbox for MRI. The python tutorial and slides are available here.

  • September 2020: I was awarded the Israel Council for Higher Education (Vatat) National Fellowship for Excelling Post-doctoral Researchers in Data Science for my postdoctoral studies in UC Berkeley and Stanford.

Contact & social media: Email (efrat.s at berkeley dot edu), LinkedIn, Twitter

Software: GitHub

Collaborations

Copyright Efrat Shimron, 2020