Suvrit Sra awarded NSF TRIPODS + X grant for machine learning in medical imaging research

October 19, 2018

Building on the success of its 2017 Transdisciplinary Research in Principles of Data Science (TRIPODS) awards, the National Science Foundation (NSF) is awarding $8.5 million in TRIPODS+X grants to expand the scope of the cross-disciplinary TRIPODS institutes into broader areas of science, engineering and mathematics.

Suvrit Sra, an Assistant Professor of Electrical Engineering and Computer Science and member of the Laboratory for Information and Decision Systems (LIDS), has been awarded a TRIPODS + X grant for his research titled Learning with Expert-In-The-Loop for Multimodal Weakly Labeled Data and an Application to Massive Scale Medical Imaging.

“This project seeks to expand the theoretical foundations of learning with weak-labels, a setting inherent to many real-world applications of machine learning where obtaining strong-labels is very expensive but weak-supervision is easily available,” explains Sra. “The motivating application is medical image analysis, which will greatly aid radiologists, and help reduce errors due to work overload while improving resource utilization.”

Previously, the NSF TRIPODS awarded MIT multi-year grants to support collaborative research across mathematics, statistics, and computer science, with the goal of advancing the theoretical foundations of data science. Two of the co-principal investigators of the resulting MIT Institute for Foundations of Data Science (MIFODS) are members of the Laboratory for Information and Decision Systems (LIDS): Philippe Rigollet, a professor in the Department of Mathematics, and Devavrat Shah a professor in EECS.

“The multidisciplinary approach for addressing the increasing volume and complexity of data enabled through the TRIPODS+X projects will have a profound impact on the field of data science and its use,” said Jim Kurose, NSF assistant director for Computer and Information Science and Engineering (CISE). "This impact will be sure to grow as data continues to drive scientific discovery and innovation.”

For more information about this award, please see: