Keynotes

Yonina Eldar is a Professor in the Department of Mathematics and Computer Science, Weizmann Institute of Science, Rehovot, Israel, where the heads the center for biomedical engineering. She was previously a Professor in the Department of Electrical Engineering at the Technion, where she held the Edwards Chair in Engineering. She is also a Visiting Professor at MIT, a Visiting Scientist at the Broad Institute, and an Adjunct Professor at Duke University and was a Visiting Professor at Stanford. She received the B.Sc. degree in physics and the B.Sc. degree in electrical engineering both from Tel-Aviv University (TAU), Tel-Aviv, Israel, in 1995 and 1996, respectively, and the Ph.D. degree in electrical engineering and computer science from the Massachusetts Institute of Technology (MIT), Cambridge, in 2002. She is a member of the Israel Academy of Sciences and Humanities, an IEEE Fellow and a EURASIP Fellow. She has received many awards for excellence in research and teaching, including the IEEE Signal Processing Society Technical Achievement Award (2013), the IEEE/AESS Fred Nathanson Memorial Radar Award (2014) and the IEEE Kiyo Tomiyasu Award (2016). She was a Horev Fellow of the Leaders in Science and Technology program at the Technion and an Alon Fellow. She received the Michael Bruno Memorial Award from the Rothschild Foundation, the Weizmann Prize for Exact Sciences, the Wolf Foundation Krill Prize for Excellence in Scientific Research, the Henry Taub Prize for Excellence in Research (twice), the Hershel Rich Innovation Award (three times), the Award for Women with Distinguished Contributions, the Andre and Bella Meyer Lectureship, the Career Development Chair at the Technion, the Muriel & David Jacknow Award for Excellence in Teaching, and the Technion’s Award for Excellence in Teaching (two times). She received several best paper awards and best demo awards together with her research students and colleagues, was selected as one of the 50 most influential women in Israel, and was a member of the Israel Committee for Higher Education. She is the Editor in Chief of Foundations and Trends in Signal Processing and a member of several IEEE Technical Committees and Award Committees.

Prof. Yonina Eldar

Weizmann Institute of Science

Model Based Deep Learning with Applications to Imaging

Abstract:

Deep neural networks provide unprecedented performance gains in many real-world problems in signal and image processing. Despite these gains, the future development and practical deployment of deep networks are hindered by their black-box nature, i.e., a lack of interpretability and the need for very large training sets. On the other hand, signal processing and communications have traditionally relied on classical statistical modeling techniques that utilize mathematical formulations representing the underlying physics, prior information and additional domain knowledge. Simple classical models are useful but sensitive to inaccuracies and may lead to poor performance when real systems display complex or dynamic behavior. Here we introduce various approaches to model based learning which merge parametric models with optimization tools leading to efficient, interpretable networks from reasonably sized training sets. We will consider examples of such model-based deep networks to image deblurring, image separation, super resolution in ultrasound and microscopy, and finally we will see how model-based methods can also be used for efficient diagnosis of COVID19 using X-ray and ultrasound.

Dr. Jongho Lee is a Professor at the Department of Electrical and Computer Engineering, Seoul National University. He received his Ph.D in Electrical Engineering at Stanford University (2007). He worked at National Institutes of Health as a research fellow (2007 to 2010) and then at the Department of Radiology, University Pennsylvania as Assistant Professor (2010 to 2014). In 2014, he moved back to Korea to join a faculty position at Seoul National University. His lab is focused on the exploration of novel contrast in MRI and development of novel neuroimaging methods. His recent works include the investigation of myelin and iron contrasts via novel magnetic susceptibility imaging and advance in deep learning for image acquisition and reconstruction. He is a recipient of Young Investigator Award at the Workshop of ISMRM (2013) and Young Investigator Grant Award from KSEA (2012). He has been active in international societies, chairing Electro-Magnetic Tissue Properties Study Group at ISMRM, serving as an annual meeting program committee for ISMRM, and working as an editorial board member of NeuroImage, a review editor of Frontiers in Neuroscience and an associate editor of Journal of Translational Medicine, etc. He gave a number of invited presentations at international workshops and conferences including a most recent plenary talk at ISMRM (2021).

Prof. Jongho Lee

Seoul National University

Deep Designed RF for MRI

Abstract:

Over the last five years, we have experienced unprecedented upspring of deep learning research in medical imaging, engulfing not only image diagnosis but also image reconstruction to which this community has substantial contribution. In this lecture, I will present another area of deep learning research in MRI which is played ahead of the reconstruction: data acquisition. After a brief overview of various proposals of deep learning in acquisition, ranging from active undersampling of k-space to sequence timing optimization, I will introduce research efforts in building a sequence or a part of a sequence. Then, a new approach of designing an RF pulse, the simplest but complete design by itself, will be explained. This method, which is referred to as DeepRF, combines deep reinforcement learning and optimization to find a new RF pulse for a given specification by self-training. DeepRF has demonstrated to design well-known RF pulses (e.g., slice selective excitation and inversion, and B1-insensitive inversion) with improved energy deposition. Compared to conventional approaches, the method requires no design rules (e.g. SLR transform or adiabatic condition) nor training dataset and reveals new ways of manipulating magnetization, revealing advantages of deep learning in data acquisition. Additional expansions of the method toward more complex RF design or RF-gradient design will be suggested with a future direction toward designing a whole four axes of MRI acquisition (i.e., RF and three gradients).

Page updated

Google Sites

Report abuse