Rebecca Willett is a Professor of Statistics and Computer Science at the University of Chicago. Her research is focused on machine learning, signal processing, and large-scale data science. Willett received the National Science Foundation CAREER Award in 2007, was a member of the DARPA Computer Science Study Group, received an Air Force Office of Scientific Research Young Investigator Program award in 2010, and was named a Fellow of the Society of Industrial and Applied Mathematics in 2021. She is a co-principal investigator and member of the Executive Committee for the Institute for the Foundations of Data Science, helps direct the Air Force Research Lab University Center of Excellence on Machine Learning, and currently leads the University of Chicago’s AI+Science Initiative. She serves on advisory committees for the National Science Foundation’s Institute for Mathematical and Statistical Innovation, the AI for Science Committee for the US Department of Energy’s Advanced Scientific Computing Research program, the Sandia National Laboratories Computing and Information Sciences Program, and the University of Tokyo Institute for AI and Beyond. She completed her PhD in Electrical and Computer Engineering at Rice University in 2005 and was an Assistant then tenured Associate Professor of Electrical and Computer Engineering at Duke University from 2005 to 2013. She was an Associate Professor of Electrical and Computer Engineering, Harvey D. Spangler Faculty Scholar, and Fellow of the Wisconsin Institutes for Discovery at the University of Wisconsin-Madison from 2013 to 2018.
Talk Title: Deep Equilibrium Architectures for Inverse Problems in Imaging
Abstract: Recent efforts on solving inverse problems in imaging via deep neural networks use architectures inspired by a fixed number of iterations of an optimization method. The number of iterations is typically quite small due to difficulties in training networks corresponding to more iterations; the resulting solvers cannot be run for more iterations at test time without incurring significant errors. I will describe an alternative approach corresponding to an infinite number of iterations, yielding up to a 4dB PSNR improvement in reconstruction accuracy above state-of-the-art alternatives and where the computational budget can be selected at test time to optimize context-dependent trade-offs between accuracy and computation. The proposed approach leverages ideas from Deep Equilibrium Models, where the fixed-point iteration is constructed to incorporate a known forward model and insights from classical optimization-based reconstruction methods. This is joint work with Davis Gilton and Greg Ongie.
Zhizhen Zhao is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign. She joined University of Illinois in 2016. From 2014 to 2016, she was a Courant Instructor at the Courant Institute of Mathematical Sciences, New York University. She received the B.A. and M.Sc. degrees in physics from Trinity College, Cambridge University in 2008, and the Ph.D. degree in physics from Princeton University in 2013. She is a recipient of Alfred P. Sloan Research Fellowship (2020--2022). Her research interests include geometric data analysis, signal processing, and machine learning, with applications to imaging sciences and inverse problems, including cryo-electron microscopy image processing and data-driven methods for dynamical systems.
Talk Title: An Adversarial Learning Approach for Unknown View Tomography
Abstract: The goal of 2D tomographic reconstruction is to recover an image given its projections from various views. It is often presumed that projection angles associated with the projections are known in advance. Under certain situations, however, these angles are known only approximately or are completely unknown. It becomes challenging to reconstruct the image from a collection of unordered random projections. We introduce an adversarial learning approach to recover the image and the projection angle distribution by matching the empirical distribution of the measurements with the generated data. Fitting the distributions is achieved through solving a min-max game between a generator and a critic based on Wasserstein generative adversarial network structure. To accommodate the update of the projection angle distribution through gradient back propagation, we approximate the loss using the Gumbel-softmax reparameterization of samples from discrete distributions. Our theoretical analysis verifies the unique recovery of the image and the projection distribution up to a global rotation and reflection upon convergence.
Laura Waller an Associate Professor of Electrical Engineering and Computer Sciences (EECS) at UC Berkeley, and affiliated with the UCB/UCSF Bioengineering Graduate Group and Applied Sciences & Technology program. She received B.S., M.Eng. and Ph.D. degrees from the Massachusetts Institute of Technology (MIT) in 2004, 2005 and 2010, and was a Postdoctoral Researcher and Lecturer of Physics at Princeton University from 2010-2012. She is a Packard Fellow for Science & Engineering, Moore Foundation Data-driven Investigator, Bakar Fellow, OSA Fellow, AIMBE Fellow and Chan-Zuckerberg Biohub Investigator. She has recieved the Carol D. Soc Distinguished Graduate Mentoring Award, Agilent Early Career Profeessor Award (Finalist), OSA Adolph Lomb Medal, NSF CAREER Award and the SPIE Early Career Achievement Award.
Talk Title: Computational 3D fluorescence microscopy
Abstract: We describe a compact and inexpensive computational microscope that encodes 3D information into a single 2D sensor measurement, then exploits sparsity to reconstruct the volume with good resolution across a large volume. Our system uses simple hardware and scalable software for easy reproducibility and adoption. The inverse algorithm is based on large-scale nonlinear optimization with self-calibration of aberrations and we discuss computational optical design approaches for optimizing the system’s performance. We demonstrate applications in whole organism bioimaging and neural activity tracking in vivo.
Jeff Fessler is the William L. Root Professor of EECS at the University of Michigan. He received the BSEE degree from Purdue University in 1985, the MSEE degree from Stanford University in 1986, and the M.S. degree in Statistics from Stanford University in 1989. From 1985 to 1988 he was a National Science Foundation Graduate Fellow at Stanford, where he earned a Ph.D. in electrical engineering in 1990. He has worked at the University of Michigan since then. From 1991 to 1992 he was a Department of Energy Alexander Hollaender Post-Doctoral Fellow in the Division of Nuclear Medicine. From 1993 to 1995 he was an Assistant Professor in Nuclear Medicine and the Bioengineering Program. He is now a Professor in the Departments of Electrical Engineering and Computer Science, Radiology, and Biomedical Engineering. He became a Fellow of the IEEE in 2006, for contributions to the theory and practice of image reconstruction. He received the Francois Erbsmann award for his IPMI93 presentation, and the Edward Hoffman Medical Imaging Scientist Award in 2013. He has served as an associate editor for the IEEE Transactions on Medical Imaging, the IEEE Signal Processing Letters, the IEEE Transactions on Image Processing, the IEEE Transactions on Computational Imaging, and is currently serving as an associate editor for SIAM J. on Imaging Science. He has chaired the IEEE T-MI Steering Committee and the ISBI Steering Committee. He was co-chair of the 1997 SPIE conference on Image Reconstruction and Restoration, technical program co-chair of the 2002 IEEE International Symposium on Biomedical Imaging (ISBI), and general chair of ISBI 2007. His research interests are in statistical aspects of imaging problems, and he has supervised doctoral research in PET, SPECT, X-ray CT, MRI, and optical imaging problems.
Title: Joint Optimization of Learning-Based Image Reconstruction and Sampling for MRI
Abstract: Machine learning approaches to medical image reconstruction are of considerable recent interest, especially supervised approaches that use a corpus of training data. Accelerated MRI scans, where fewer k-space points than image voxels are acquired, is a natural setting for such reconstruction methods. Recently, machine learning methods for optimizing the k-space sampling have also had growing interest.
This talk will summarize recent work where we jointly optimize non-Cartesian k-space sampling, heeding physical constraints like gradient slew rate, and a learning-based image reconstruction method that originates from a large-scale optimization approach. Joint work with Guanhua Wang Tianrui Luo Jon-Fredrik Nielsen Douglas C Noll