In this talk, I will overview our recent work on the development of automatic methods for the interpretation of biomedical data from multiple modalities and scales. At the cellular scale, I will present a structured matrix factorization method for segmenting neurons and finding their spiking patterns in calcium imaging videos, and a shape analysis method for classifying embryonic cardiomyocytes in optical imaging videos. At the organ scale, I will present a Riemannian framework for processing diffusion magnetic resonance images of the brain, and a stochastic tracking method for detecting Purkinje fibers in cardiac MRI. At the patient scale, I will present dynamical system and machine learning methods for recognizing surgical gestures and assessing surgeon skill in medical robotic motion and video data.
Professor Vidal received his B.S. degree in Electrical Engineering (highest honors) from the Pontificia Universidad Catolica de Chile in 1997 and his M.S. and Ph.D. degrees in Electrical Engineering and Computer Sciences from the University of California at Berkeley in 2000 and 2003, respectively. He was a research fellow at the National ICT Australia in 2003 and has been a faculty member in the Department of Biomedical Engineering and the Center for Imaging Science of The Johns Hopkins University since 2004. He has held several visiting faculty positions at Stanford, INRIA/ENS Paris, the Catholic University of Chile, Universite Henri Poincare, and the Australian National University. Dr. Vidal was co-editor (with Anders Heyden and Yi Ma) of the book “Dynamical Vision” and has co-authored more than 180 articles in biomedical image analysis, computer vision, machine learning, hybrid systems, robotics and signal processing. Dr. Vidal is or has been Associate Editor of Medical Image Analysis, the IEEE Transactions on Pattern Analysis and Machine Intelligence, the SIAM Journal on Imaging Sciences and the Journal of Mathematical Imaging and Vision, and guest editor of Signal Processing Magazine. He is or has been program chair for ICCV 2015, CVPR 2014, WMVC 2009, and PSIVT 2007. He was area chair for ICCV 2013, CVPR 2013, ICCV 2011, ICCV 2007 and CVPR 2005. Dr. Vidal is recipient of numerous awards for his work, including the 2012 J.K. Aggarwal Prize for “outstanding contributions to generalized principal component analysis (GPCA) and subspace clustering in computer vision and pattern recognition”, the 2012 Best Paper Award in Medical Robotics and Computer Assisted Interventions (with Benjamin Bejar and Luca Zappella), the 2011 Best Paper Award Finalist at the Conference on Decision and Control (with Roberto Tron and Bijan Afsari), the 2009 ONR Young Investigator Award, the 2009 Sloan Research Fellowship, the 2005 NFS CAREER Award and the 2004 Best Paper Award Honorable Mention (with Prof. Yi Ma) at the European Conference on Computer Vision. He also received the 2004 Sakrison Memorial Prize for “completing an exceptionally documented piece of research”, the 2003 Eli Jury award for “outstanding achievement in the area of Systems, Communications, Control, or Signal Processing”, the 2002 Student Continuation Award from NASA Ames, the 1998 Marcos Orrego Puelma Award from the Institute of Engineers of Chile, and the 1997 Award of the School of Engineering of the Pontificia Universidad Catolica de Chile to the best graduating student of the school. He is a fellow of the IEEE and a member of the ACM.
The seminar for this week is cancelled due to MICCAI 2016
Numerous physical systems are governed by partial differential equations or involve delays/transport. Such infinite-dimensional models have been a challenge to the ODE-accustomed control engineers who seek feedback designs that are both constructive and provide stability guarantees. About 15 years this situation changed with the emergence of “continuum backstepping” approach for PDEs. The backstepping designs, whose initial applications were for Navier-Stokes equations, yield explicit feedback laws which convert the original system into a desired well-behaved “target system” (for Navier-Stokes, the target is a heat equation system). I will present the basic methodological ideas of PDE backstepping and illustrate them with examples that come from fluid flows, phase change, 3D printing, multi-vehicle robotic swarms, microbial populations, and opinion spreading in online social networks.
Miroslav Krstic holds the Alspach endowed chair and is the founding director of the Cymer Center for Control Systems and Dynamics at UC San Diego. He also serves as Associate Vice Chancellor for Research at UCSD. As a graduate student, Krstic won the UC Santa Barbara best dissertation award and student best paper awards at CDC and ACC. Krstic is Fellow of IEEE, IFAC, ASME, SIAM, and IET (UK), Associate Fellow of AIAA, and foreign member of the Academy of Engineering of Serbia. He has received the PECASE, NSF Career, and ONR Young Investigator awards, the Axelby and Schuck paper prizes, the Chestnut textbook prize, the ASME Nyquist Lecture Prize, and the first UCSD Research Award given to an engineer. Krstic has also been awarded the Springer Visiting Professorship at UC Berkeley, the Distinguished Visiting Fellowship of the Royal Academy of Engineering, the Invitation Fellowship of the Japan Society for the Promotion of Science, and the Honorary Professorships from the Northeastern University (Shenyang), Chongqing University, and Donghua University, China. He serves as Senior Editor in IEEE Transactions on Automatic Control and Automatica, as editor of two Springer book series, and has served as Vice President for Technical Activities of the IEEE Control Systems Society and as chair of the IEEE CSS Fellow Committee. Krstic has coauthored eleven books on adaptive, nonlinear, and stochastic control, extremum seeking, control of PDE systems including turbulent flows, and control of delay systems.
Management of carotid artery disease, towards preventing strokes, currently relies on a simple algorithm, which has proved insufficient for a large number of mostly asymptomatic subjects, posing a significant clinical challenge. Ultrasound imaging in combination with image analysis hold promise for addressing this challenge, through the in vivo estimation of morphological, mechanical and anatomical features of the carotid artery, the artery that takes blood to the brain.
This presentation highlights various advanced image analysis techniques applied on carotid ultrasound, in an attempt to identify novel risk markers and optimise disease management. Texture features, estimated from static images, describe different patterns of tissue allocation, presumably as a consequence of exerted stresses. Mechanical features, estimated from temporal image sequences, characterise tissue elasticity and are more sensitive to early tissue changes due to ageing or disease. Anatomical features, including arterial diameters, wall thickness and lesion size, can be automatically extracted using segmentation tools. These methodologies, along with biochemical and clinical indices, are integrated in a web-based platform, which relies on a semantically-aided architecture and allows for intelligent archival and retrieval of data, thus facilitating and enhancing the entire diagnostic procedure.
In view of the valuable information on lesion composition and stability revealed by ultrasound-image-based features, and the noninvasiveness and low-cost of ultrasound imaging, these approaches are directed towards improved risk stratification, increased patient safety and cost-efficiency. Their clinical usefulness remains to be demonstrated in large trials.
Spyretta Golemati is Assistant Professor in Biomedical Engineering and a member of the First Intensive Care Unit of the Medical School of the University of Athens.
Dr Golemati holds a Diploma in Mechanical Engineering from the National Technical University of Athens, Greece, and a M.Sc. and a Ph.D. degree in Bioengineering from Imperial College London, UK.
Her research interests include (a) medical image analysis, with emphasis on vascular ultrasound image analysis, (b) biosignal processing, and (c) vascular physiology and pathophysiology. She has co-authored 32 papers published in international scientific peer-reviewed journals, 12 book chapters, and 44 papers published in international scientific peer-reviewed conference proceedings. She has participated in 7 funded national and international research projects (in one, as co-ordinator). Dr Golemati has acted as reviewer of national and international research proposals as well as of papers submitted to international scientific journals and conferences. She is a member of the Institute of Electrical and Electronic Engineers [Engineering in Medicine and Biology Society (IEEE-EMBS), Ultrasonics, Ferroelectrics and Frequency Control (IEEE-UFFC)], the Technical Chamber of Greece, and the Hellenic Atherosclerosis Society. She is Associate Editor of the journal Ultrasonics. She is a grantee of the Fulbright Foundation-Greece for the academic year 2016-2017.
Thanksgiving Break – no seminar
Catheters play a key role in diagnosing and treating cardiac arrhythmia. Intracardiac echo (ICE) catheters enable real-time 2D ultrasound image acquisition from within the heart, however, manually steering ICE catheters inside a beating heart is a complex and time consuming task. The clinical use of ICE catheters is therefore limited to only a few critical tasks, such as septal puncture. At the Harvard Biorobotics Lab, we built a robotic system that can automatically steer four degree-of-freedom catheters, enabling real-time tracking of instruments within the heart and 3D visualization of cardiac tissue. In this talk, I will walk you through the design process in preparing our system for in vivo trials, and present results from our latest live animal experiment. I will describe the control strategies we employed to accurately steer these flexible manipulators in the presence of external disturbances (e.g. respiratory motion) and unmodeled motion of the catheter body. Finally, I will describe the GPU-accelerated image processing pipeline we used to generate 3D volumetric images of the heart in real-time from the 2D images acquired by the ICE catheter.
Alperen Degirmenci is a PhD candidate in Engineering Sciences at the Harvard John A. Paulson School of Engineering and Applied Sciences. He has been working in the BioRobotics Laboratory since 2012 under the supervision of Prof. Robert D. Howe. Alperen earned his M.S. degree from Harvard University in 2015, and a B.S. degree in Mechanical Engineering from the Johns Hopkins University in 2012, with minors in mathematics, computer science, robotics, and computer-integrated surgery. Alperen’s research at Harvard focuses on real-time, high-performance algorithm development for medical ultrasound image processing and robotic procedure guidance in catheter-based cardiac interventions.