Dr. Natalia Trayanova gives keynote lecture at 2014 SIAM Annual Meeting
Date: July 23, 2014
Natalia A. Trayanova, Murray B. Sachs Professor of Biomedical Engineering and the Institute for Computational Medicine, presented a keynote lecture at the 2014 SIAM Annual Conference of the Society for Industrial and Applied Mathematics. The conference was held July 7-11 in Chicago, Illinois. Natalia's presentation entitled “Virtual Electrophysiology Laboratory” was scheduled for Thurs, July 10.
Click here to view more information about the SIAM conference.
To view the abstract from Dr. Trayanova's presentation, click here.
Daniel Tward awarded at 2014 XSEDE Conference for best "lightning talk"
Date: July 21, 2014
BME PhD student Daniel Tward attended the 2014 Extreme Science and Engineering Discovery Environment (XSEDE) conference in Atlanta, Georgia and received a prize for the best "Lightning Talk". His presentation "Computational Anatomy Gateway: Leveraging XSEDE Computational Resources for Shape Analysis" was authored with Saurabh Jain, David Lee, Anthony Kolasny, Timothy Brown, Tilak Ratnanather, Laurent Younes and Michael Miller.
Computational Anatomy (CA) is a discipline focused on the quantitative analysis of the variability in biological shape. The Large Deformation Diffeomorphic Metric Mapping (LDDMM) is the key algorithm which assigns computable descriptors of anatomical shapes and a metric distance between shapes. This is achieved by describing populations of anatomical shapes as a group of diffeomorphic transformations applied to a template, and using a metric on the space of diffeomorphisms. LDDMM is being used extensively in the neuroimaging (www.mristudio.org) and cardiovascular imaging (www.cvrgrid.org) communities. There are two major components involved in shape analysis using this paradigm. First is the estimation of the template, and second is calculating the diffeomorphisms mapping the template to each subject in the population. Template estimation is a computationally expensive problem, which involves an iterative process, where each iteration calculates one diffeomorphism for each target. These can be calculated in parallel and independently of each other, and XSEDE is providing the resources, in particular those provided by the cluster Stampede, that make these computations for large populations possible. Mappings from the estimated template to each subject can also be run in parallel. In addition, the use of NVIDIA Tesla GPUs available on Stampede present the possibility of speeding up certain convolution-like calculations which lend themselves well to the General Purpose GPU computation model. We are also exploring the use of the available Xeon Phi Co-processors to increase the efficiency of our codes. This will have a huge impact on both the neuroimaging and cardiac imaging communities as we bring these shape analysis tools online for use by these communities through our webservice (www.mricloud.org), with the XSEDE Computational Anatomy Gateway providing the resources to handle the computational demands for large populations.
To view other lightning talks and link to more information about the XSEDE conference, visit their site at http://conferences.xsede.org/lightning-talks.
Student work overseen by Dr. Tilak Ratnanather featured in WSE Summer News
Date: June 17, 2014
An article in the Summer 2014 issue of JHU Engineering Magazine highlights a promising iPad app designed by Hopkins undergrads to help train deaf adults with cochlear implants (CI) to understand speech from the electrical signals that CI devices provide. Student team members include Margo Heston, Rohit Bhattacharya, and Joanne Song, all of the Department of Biomedical Engineering. Their work is overseen by Dr. Tilak Ratnanather, an associate research professor in the Center for Imaging Science and ICM core faculty member.
According to Heston, the app – named Speech Banana after the term specialists use to describe the area where all human speech appears on an audiogram – is not intended to replace traditional in-person auditory training, “But we want to supplement it.”
To read the entire article, click here.
Prof. René Vidal elected to the 2014 Class of IEEE Fellows
Date: June 13, 2014
Dr. René Vidal receives award in Florence, Italy
René Vidal has been named to the 2014 class of IEEE Computer Society Fellows. The IEEE Grade of Fellow recognizes unusual distinction in the profession and is conferred by the IEEE Board of Directors upon a person of outstanding and extraordinary qualifications and experience in IEEE-designated fields, and who has made important individual contributions to one or more of these fields. Dr. Vidal has been recognized for contributions to subspace clustering and motion segmentation in computer vision. He was presented with the award at the IEEE International Conference on Acoustics, Speech and Signal Processing in Florence, Italy, on Tuesday, May 6, 2014.
Dr. Vidal is an Associate Professor in the Department of Biomedical Engineering of Johns Hopkins University, with joint appointments in Computer Science, Electrical and Computer Engineering, and Mechanical Engineering. He is the director of the Vision Dynamics and Learning Lab, and a faculty member in the Center for Imaging Science (CIS), the Institute for Computational Medicine (ICM), and the Laboratory for Computational Sensing and Robotics (LCSR). For more information on his research, please see http://www.vision.jhu.edu.
ICM teams with CS on successful IDIES Seed Funding proposal
Date: June 10, 2014
The Johns Hopkins Institute for Data Intensive Engineering and Science (IDIES) Seed Funding Program has announced that the proposal "SIRENIC: Stream Infrastructure for the Real-time Analysis of Intensive Care Unit Sensor Data" by Yanif Ahmad and Yair Amir, both of the Department of Computer Science, and Raimond Winslow of the Department Biomedical Engineering and Institute for Computational Medicine, is among those selected for the first 2014 round of competitive awards. The goals of the IDIES seed funding initiative, which provides $25,000 to each recipient team, are to support data-intensive computing projects that involve areas relevant to IDIES and JHU institutional research priorities, are multidisciplinary, and build ideas and teams with good prospects for successful external research funding.
The goal of the SIRENIC project is to design and deploy an open-source data management framework as infrastructure for the real-time analysis of streaming patient physiological data in the intensive care unit (ICU) setting. The proposal aims at delivering a proof-of-concept data collection and analysis pipeline to support exploratory research activities in ICU healthcare, with the explicit capability to operate on live data and to empower alarms research and event detection in the real-time setting. The project brings together biomedical and computer science researchers with the capabilities to: i) instrument and capture patient physiology data with bedside sensor deployments in a Hopkins ICU, and ii) design a research-oriented stream analytics framework to assist medical and clinical researchers and practitioners in model development for rapidly evolving diseases with critical effects on patient health. Example diseases that exhibit both a rapid onset and evolution include infections such as sepsis, arrhythmias, seizures, pulmonary embolism, cardiogenic shock, and respiratory failure. Sepsis alone accounts for more than 200,000 deaths in the U.S. annually.
To read the full announcement on the JHU HUB website, click here.
Click here to read more about the IDIES Seed Funding Program on the IDIES website.
Sri Sarma appears on Today to promote Brain Games
Date: May 29, 2014
Dr. Sridevi Sarma, Assistant Professor of Biomedical Engineering and ICM core faculty member, guested on The Today Show with Kathy Lee & Hoda on Tuesday, May 27 in a segment promoting the National Geographic Channel series, Brain Games. Brain Games is a science entertainment television program that explores the components of the human brain. Episodes of Brain Games season 3 featuring Dr. Sarma will begin airing in July 2014. A video of Dr. Sarma’s appearance on The Today Show can be viewed below or here.
Clips of Dr. Sarma’s online episodes of Brain Games can be found here. Watch for Brain Games season 3 airing in July for additional episodes.
Medical Device Daily Features Research by Dr. Natalia Trayanova
Date: May 23, 2014
Research by Dr. Natalia Trayanova, Murray B. Sachs Professor of Biomedical Engineering and member of the Institute for Computational Medicine, was featured in the May 12 edition of Medical Device Daily. The story by Mark McCarty highlights her presentation at this year’s Heart Rhythm Society. From the story: "[Dr. Trayanova] remarked at the HRS session that the MRI effort in her lab is aimed at development of a multi-scale modeling platform, one possible use of which is to map out the optimal targets for ablation for ventricular tachycardia with a degree of precision she suggested is not currently available in clinical practice."
For more information about Dr. Trayanova’s presentation and for a link to the article,click here.
New Fall Course: Statistical Models in Molecular Medicine
Date: May 8, 2014
Professor Donald Geman of the Institute for Computational Medicine, Department of Applied Mathematics and Statistics, and Center for Imaging Science, Johns Hopkins University will be offering a new course this fall, Statistical Models in Molecular Medicine (EN.550.650)
As stated in the course announcement, "Computational systems biology has emerged as the dominant framework for analyzing high-dimensional ‘omics’ data in order to uncover the relationships among molecules, networks and disease. In particular, many of the core methodologies are based on statistical modeling, including machine learning, stochastic processes and statistical inference. We will cover the key aspects of this methodology, including measuring associations, testing multiple hypotheses, and learning predictors, Markov chains and graphical models. In addition, by studying recent important articles in cancer systems biology, we will illustrate how this approach enhances our ability to annotate genomes, discover molecular disease networks, detect disease, predict clinical outcomes, and characterize disease progression. Whereas a solid foundation in probability and statistics is necessary, no prior exposure to molecular biology is required (although helpful) and the course may be accessible to advanced undergraduates."
This course will be available in the first semester of AY14/15. We encourage interested students to check the JHU Course Schedule at http://web.jhu.edu/registrar/schedule/index.html, or ISIS, for further information as it becomes available.
Vote for Trayanova Lab in NIH Video Contest
Date: April 29, 2014
As part of the 10-Year Commemoration of the NIH Roadmap/Common Fund, the Trayanova lab is currently competing in an NIH-sponsored Video Competition. Recipients of funds from the NIH Common Fund (Natalia’s Pioneer Award) have been invited to make a video to explain their work in accessible but entertaining ways, and to promote what they do.
Their video is now live on the NIH Common Fund Website. This is a competition, and the video with the most LIKES will win.
The best songs and videos will be featured at the June 19, 2014 Commemoration Symposium and via live videocast, with songs performed by NIH Director Dr. Francis Collins, himself. The symposium will recognize 10 combined years of achievement by the NIH Roadmap and the NIH Common Fund, two programs designed to catalyze innovation in biomedical research. The NIH is proud of Roadmap and Common Fund grantees’ achievements including numerous publications in high-impact journals, prestigious awards, and new tools and programs developed for the research community.
Eranga Ukwatta named BME Centennial Postdoctoral Fellow
Date: April 28, 2014
Eranga Ukwatta of the Institute for Computational Medicine has been awarded the Johns Hopkins University Biomedical Engineering Centennial Postdoctoral Fellowship. The BME Fellowship is intended for rising stars who are recent or soon-to-be PhD graduates with a record of achievement, a strong desire for scientific discovery, and aspirations for societal impact.
Eranga joined the team of ICM core faculty members Natalia Trayanova and Fijoy Vadakkumpadan in late 2013. He is working to develop clinically applicable image processing methodologies for the generation of computational models of the heart, particularly in patients with structural disease, such as myocardial infarction. His research will address challenges such as segmentation of cardiac and torso images, and interpolation of infarct geometry.
Congratulations, Eranga, and good luck with your research!