To increase injection site positioning preciseness, and thus the effectiveness, of these new treatments the Biorobotics and Human Modeling Lab, under the direction of George W. Woodruff School of Mechanical Engineering Professor Jun Ueda, have developed a patient mounted injection needle robot for use in magnetic resonance elastography (MRE), a technology that combines MRI imaging and low-frequency vibrations to create a map (elastogram) that images the stiffness of soft tissues. Working in conjunction with the Stevens Institute of Technology and the Mount Sinai Hospital, the team developed non-ferromagnetic lead zirconate titanate (PZT) actuators that allow for usage in the magnetic field area produced by MR imaging. The team used the prototype in a demonstration MRE scan for improved diagnosis of degenerative disc diseases. Multi-source shear wave propagation for examination of the pathological state of the patient tissue is achieved by tunable resonant frequency of the individual actuators. This allows for a minimally invasive procedure with a significant increase in precision needle positioning than that available via a human clinician.
In a related project with Emory University and the Georgia Tech Research Institute, Professor Ueda and team developed a patient mounted, minimally invasive, injection needle robot for spinal cellular therapeutics that is fully MRI compatible due to the non-ferromagnetic materials comprising the robotic actuators. High-precision in-vivo performance has been achieved by a PZT-driven parallel-plane needle-orientation mechanism and an iterative super-resolution computer vision algorithm. Preclinical evaluation on a suidae model showed mounting and controller functionality with respiration, while laboratory evaluation demonstrated placement precision of ~14μm of the desired location.
It is hoped that the high accuracy of this needle positioning robot and visual feedback method will result in a significant improvement to the workflow of spinal injection procedures. The dual results of precise positioning and images in near real time combined with a decreased procedure time promise to provide ease of use to clinicians and relief for millions of back-pain sufferers.
- Christa Ernst
Professor Jun Ueda would like to thank Ai-Ping Hu, Daniel Martinez and Waiman Meinhold for their contributions to this study.
W. Meinhold, D. E. Martinez, J. N. Oshinski, A. Hu and J. Ueda, "A direct drive parallel plane piezoelectric needle positioning robot for MRI guided intraspinal injection," in IEEE Transactions on Biomedical Engineering, doi: 10.1109/TBME.2020.3020926.
This Research was Sponsored by the following: NSF 1662029, CDMRP FY 2019 Discovery Award, IRIM seed grant FY 2018 & FY 2019, NSF 1545287 (student fellowship | Meinhold, Martinez)
]]>The goals of this collaborative arrangement are to:
This five-year agreement was acknowledged during a virtual memorandum of understanding (MOU) signing event on Oct. 23, organized by Georgia Tech’s Strategic Energy Institute (SEI).
“This MOU provides a basis for both parties to engage in research collaborations, and the joint creation and administration of intellectual property,” said Tim Lieuwen, SEI’s executive director.
Leaders of both institutions emphasized that the MOU leverages existing relationships and takes advantage of synergies. PNNL and Georgia Tech already have a long history of collaboration, with more than 100 journal articles, conference papers, and the like coauthored by PNNL and Georgia Tech researchers over the past decade. PNNL also boasts 32 current staff members who earned a bachelor’s, master’s, or doctoral degree from Georgia Tech.
The MOU lays out several potential topics of mutual interest to both institutions.
“Georgia Tech and Pacific Northwest National Laboratory share interests in many areas of science and technology, including data science and visual analytics, electrical grid technologies, cybersecurity, and processing for fuels, chemicals, and materials,” said Chaouki T. Abdallah, Georgia Tech’s executive vice president for research. “Through this MOU, we look forward to expanding our collaborations in these important research areas.”
The MOU also calls for expanded intellectual engagement, with PNNL and Georgia Tech students and researchers having a substantive presence on each other’s campuses, often in the form of joint appointments and internships. Personnel exchanges of this nature typically accelerate research efforts by making available to both parties the unique capabilities, facilities, and research communities that both have to offer.
“The complexity of the research problems we are tackling today requires cooperation among institutions. No one institution can solve the big problems alone,” Tony Peurrung, PNNL’s deputy director for science and technology, said. “We are pleased to elevate our partnership with Georgia Tech because with our combined strengths, we will be better prepared to solve some of world’s most difficult science and technology challenges.”
Several online seminars are planned in the coming months to boost awareness of this agreement among the research communities of both institutions and to foster connections between researchers with similar interests.
Pacific Northwest National Laboratory draws on signature capabilities in chemistry, earth sciences, and data analytics to advance scientific discovery and create solutions to the nation's toughest challenges in energy resiliency and national security. Founded in 1965, PNNL is operated by Battelle for the U.S. Department of Energy's Office of Science — the single largest supporter of basic research in the physical sciences in the United States — and is working to address some of the most pressing challenges of our time.
The Georgia Institute of Technology, also known as Georgia Tech, is one of the nation’s leading research universities, providing a focused, technologically based education to more than 36,000 undergraduate and graduate students. The Institute has many nationally recognized programs, all top-ranked by peers and publications alike, and is ranked among the nation’s top public universities by U.S. News & World Report. It offers degrees through the Colleges of Computing, Design, Engineering, Sciences, the Scheller College of Business, and the Ivan Allen College of Liberal Arts. As a leading technological university, Georgia Tech has hundreds of centers focused on interdisciplinary research that consistently contribute vital research and innovation to American government, industry, and business.
Research News
Georgia Institute of Technology
177 North Avenue
Atlanta, Georgia 30332-0181 USA
Media Relations Contacts: Georgia Tech - John Toon (jtoon@gatech.edu); PNNL - Greg Koller (greg.koller@pnnl.gov).
]]>Research News
(404) 894-6986
]]>Created by Georgia Tech and Oregon State University researchers over the course of a year, CNN Explainer is a robust interactive visualization tool uniquely developed for deep learning beginners.
By combining visualizations, animation, and transitions, CNN Explainer enables users to inspect the interplay between low-level mathematical operations and high-level model structures. Presenting views with different level of details gives users control over what technique they focus on and allows them to transition to others when they are ready.
“While there are other existing tools that help explain CNNs for beginners, this tool is quite different in how comprehensive its depth is and how it combines everything together,” said Zijie Jay Wang, the primary investigator of this work.
“Some tools only explain high level structures while others only focus on low level mathematical instruction. We wanted to build a tool that could integrate everything together and use transitions to help users navigate through different structures and their levels of detail,” he said.
While CNN Explainer was originally created with students and deep learning instructors in mind, general professionals and avid deep learning professionals are also showing excitement and interest in this new tool.
“Many professionals who want to find out more about deep learning, and machine learning are accessing and using CNN Explainer, and it is helping them get started in this field. Meanwhile, avid deep learning practitioners have been adapting CNN Explainer to debug their own models,” said Wang.
The traction CNN Explainer has gained across web communities is another undeniable testament to its usability and need. Since its public release on May 1st, it has received almost 5000 GitHub stars and an average of 300 daily visitors from more than 80 countries.
“The success of CNN Explainer has really shown me how the power of visualization can help people interact with their machine learning models,” continued Wang. “It is a very good interface for both beginners and experts, and in the future, I will try to design more tools for all levels to help them interpret, debug, and understand their models.”
Currently, CNN Explainer has also become a popular tool in deep learning courses—used by instructors from Georgia Tech, University of Wisconsin–Madison, University of Tokyo, and more.
School of Interactive Computing Associate Professor and Facebook AI Research Scientist Dhruv Batra is an early adopter of this tool and currently uses the tool in his Intro to Perception and Robotics course at Georgia Tech.
According to Batra, “I have used CNN Explainer and other visualization tools created by the Polo Club of Data Science in my class. I find such visualizations to be highly valuable in explaining ostensibly complicated concepts in a simple visual way.”
“I am visual learner myself; if I can picture things like the flow of spatial feature maps in a CNN, I can understand the concepts easily. And plenty of research in pedagogy suggests that I am not atypical. In CS 4803/7643 Deep Learning, I augment formal mathematical description with such visualizations, and I am highly appreciative of tools like the CNN Explainer,” said Batra.
The paper outlining CNN Explainer’s process and programming will be presented at the top visualization conference, IEEE VIS 2020. It is also among the selected VIS papers published at IEEE Transactions on Visualization and Computer Graphics, the top visualization journal.
]]>Communications Officer
]]>Qureshi joined the School of Computer Science in July to bring his expertise in this area.
The Quantum Connection
Quantum wasn’t always Qureshi’s research area. He received his Ph.D. from University of Texas at Austin, where he studied cache management. He then worked at IBM on emerging memory technology. When he started at the School of Electrical and Computer Engineering in 2011, Qureshi’s areas were memory systems, computer architecture, and hardware security.
It wasn’t until 2016 when a student came back from a Microsoft internship with a new interest in memory system for quantum computers that Qureshi started working in the area. Until 2016, research in quantum computing had mostly a theoretical bent, and Qureshi was skeptical of the practical implementation and use. That all changed once IBM made the 5-qubit machine available via cloud for public use and users could run programs on real quantum computers. Since then, companies such as IBM and Google have demonstrated machines with 50+ qubits, and the progress in machine capacity is expected to accelerate in the coming years.
“My background is computer systems, not quantum physics or quantum information,” he said. “Before 2016, there was no obvious bridge to do system-level research in quantum computing”
“Quantum computers became really exciting for system research with the advent of the cloud-based IBM quantum machines,” Qureshi said.
Moving from Engineering to Computing
As Qureshi’s research shifted more into quantum, it became clear he could make more headway in the field if he joined the College of Computing, where it would be easier to work with researchers in programming languages and software.
“The chance of collaboration, the chance of learning and doing impactful research, and teaching quantum computing courses is higher in College,” he said.
Qureshi’s goal is to improve software to make quantum computation less susceptible to errors. Some of his recent work uses diversity to reduce the errors in quantum computation. Qureshi also led a collaboration with Oak Ridge National Labs (ORNL) that allows Georgia Tech employees to have access to the state-of-the-art quantum computers from IBM.
Qureshi wants to make quantum accessible to students.
“The content on quantum computing can be intimidating, and sometimes it may feel like you need a Ph.D. in physics and another Ph.D. in mathematics to make sense of the material” said Qureshi. “However, if you are interested in doing research at the system and software level, then the problems are similar to typical systems and abstractions can go a long way in making progress.”
With this in mind, Qureshi is teaching an Introduction to Quantum Computing graduate class this fall and hopes to bring quantum to the Online Master of Science Computer Science (OMSCS) program by 2021.
“The exciting aspect of doing systems research in quantum computing is that the field is only getting defined right now, and you have more of a chance of making a bigger contribution in a field of when you go in early,” he said.
]]>"I think studying the theory and history of international affairs helped me to make sense of the US and multinational response that I became a part of," said Macander. "It also made me more effective at working with other nations' militaries, comfortable living and working abroad, and a better, more open-minded leader of the diverse group of Marines I would serve alongside."
During her career, Macander has served in many roles, including a Marine Officer Instructor, Operations Officer, Commanding Officer for the 1st Combat Engineer Battalion, and now the first female Ground Combat Battalion Commander.
"In my time as a student at Georgia Tech and ROTC, I learned self-reliance and discipline, both skills that have served me well over my 20-year career, and that made me ready to serve as the first female commander in a Marine Division."
Macander, who was born and raised in New York, decided to enroll at Georgia Tech because she wanted to attend a technical school in a new place.
"Atlanta was very different from my suburban, upstate New York upbringing, but I loved being in a vibrant city, and I definitely enjoyed the southern hospitality," said Macander.
During her time as a student, she stayed busy by running cross-country and track, working on campus, and joining the Navy ROTC. Her decision to move from the athlete dorms into the freshman experience dorm helped her meet other students, including Katie Rodgers, a Nunn School alumna, who would later convince her to change her major.
Macander, who began as a Chemical Engineering student, changed her major to International Affairs when Georgia Tech moved from a trimester to semester system between her sophomore and junior year, causing her to lose credits.
If she remained in the chemical engineering program, she would have needed to stay a fifth year to complete the required Navy ROTC classes.
"My roommate and good friend Katie Rodgers was in the Nunn School and knew I was struggling with the decision, but helped make a case for me that it was a challenging, exciting program that fits well with my goal of being a Marine Corps Officer," said Macander.
Moving in this direction meant that Macander could graduate within a reasonable time and begin her career with the Marines.
"The Nunn School program proved much more valuable as a Marine Corps officer than an engineering degree would have," said Macander.
Seek mentors: "I would not be where I am today if I wasn't blessed with incredible mentors from the moment I stopped by the NROTC building my freshman year. Captain Aaron Potter (retired as a lieutenant colonel) was the Marine Officer Instructor at Georgia Tech who helped me earn my commission, and whose voice I still hear reminding me to push myself out of my comfort zone, but to always be humble."
Step out of your comfort zone: "My advice, no matter the occupation, would be to work hard and know there might be sacrifices to be successful and not to be afraid to do something new and challenging. I had the choice of commanding a unit that I had served in before and knew inside and out the comfortable choice, or the unit I ultimately requested."
Written by Jessica Palacios and edited by Nunn School student Maria Winstead.
]]>