AI and big data join forces to improve radiology
Artificial intelligence (AI) isn’t confined to the realm of science fiction anymore—particularly in the rapidly evolving world of healthcare technology.
Physicians at Massachusetts General Hospital (MGH) in Boston will soon have the capability to compare a patient’s symptoms, tests and history with data insights from a vast population of other patients—all using AI technology—as part of the hospital’s new Clinical Data Science Center.
"We now have the ability to expand the field of radiology beyond its predominant state of providing visualization for human interpretation," said Keith Dreyer, MD, executive director of the center, in a press release. "Guided by precision healthcare, we are entering the radiological era of biometric quantification, where our interpretations will be enhanced by algorithms learned from the diagnostic data of vast patient populations. Without the processing capabilities of GPUs, this would not be possible."
The facility, known as the MGH Clinical Data Science Center, consists of a deep neural network trained using MGH’s phenotypic, genetics and imaging data, including a database containing some 10 billion medical images. Nvidia, which began as a graphics processing company in the gaming industry before branching out to other industries and the mobile computing space, will serve as technology partner. The Clinical Data Science Center will leverage Nvidia’s DGX-1 deep-learning supercomputer.
The project will initially focus on the fields of radiology and pathology before expanding into other relevant areas such as genomics and electronic health records.
Digital Editor
With nearly a decade of experience in print and digital publishing, John serves as Content Marketing Manager. His professional skill set includes feature writing, content marketing and social media strategy. A graduate of The Ohio State University, John enjoys spending time with his wife and daughter, along with a number of surprisingly mischievous indoor cacti.