Luis Louro - Fotolia

News Stay informed about the latest enterprise technology news and product updates.

Radiology AI and deep learning take over RSNA 2017

AI and deep learning applications were superhot at RSNA 2017, as value-based medical imaging and PACS and VNA systems remained the top topics for imaging professionals.

CHICAGO -- As the medical imaging world debates whether machines are supplanting humans, veteran radiology AI thinker Curtis Langlotz, M.D., offered what is becoming a widely held view of the profession's technology future.

"To the question, will AI replace radiologists, I say the answer is no. But radiologists who do AI will replace radiologists who don't," Langlotz, professor of radiology and biomedical informatics at Stanford University School of Medicine, said to a packed hall at the RSNA 2017 conference.

The setting was a scientific panel during the 103rd Scientific Assembly and Annual Meeting of the Radiological Society of North America, held at the McCormick Place conference center.

RSNA show vigorous in its second century

RSNA, with more than 54,000 members from around the world, annually stages what is the biggest healthcare conference and exposition on the continent. This year, the event attracted some 50,000 attendees, with nearly half of them medical imaging professionals, and 667 exhibitors -- mostly vendors.

In addition to artificial intelligence and various forms of machine learning, RSNA 2017 was more deeply immersed than ever before in value-based imaging, the pursuit of quality over volume, as the U.S. healthcare system moves in that direction.

The RSNA 2017 exposition floor at the McCormick Place conference center in Chicago.
The RSNA 2017 exposition floor at the McCormick Place conference center in Chicago.

Deconstructing PACS

Also as strong as ever were picture archiving and communications systems (PACS) and vendor-neutral archive (VNA) technologies and systems for storing and viewing complex medical images, including the increasingly popular strategy of "deconstructing PACS" -- stitching together parts of PACS from various vendors.

But radiology AI and deep learning -- a subset of machine learning that uses advanced statistical techniques to enable computers to improve at tasks with experience -- were probably the hottest topics at RSNA 2017.

Indeed, Langlotz's session -- and dozens of other panels on AI, deep learning and machine learning in radiology and other imaging-intensive specialties -- drew overflow crowds.

Radiology AI excitement and reality

To the question, will AI replace radiologists, I say the answer is no. But radiologists who do AI will replace radiologists who don't.
Curtis LanglotzM.D., professor of radiology and biomedical informatics at Stanford University School of Medicine

"We're definitely right in the eye of the storm of the hype cycle," Rasu Shrestha, M.D., chief innovation officer at University of Pittsburgh Medical Center, told SearchHealthIT on the busy "technical exhibition," or show, floor. "Having said that, that hype is being driven by an immense amount of hope. Could AI and machine learning solve for the complexities of healthcare?"

Langlotz acknowledged that radiology AI has already been through a number of hype-bust cycles in recent decades, but his work and that of colleagues at the Mayo Clinic and The Ohio State University, among others, shows that AI and machine learning have made dramatic progress.

Luciano Prevedello, M.D., division chief for medical imaging informatics at The Ohio State University Wexner Medical Center, said at the same deep learning session that "from 2014 to 2015 is when the algorithms started surpassing the human ability to classify" medical image data.

Experts say AI can aid imaging now

The radiology AI and deep learning experts said the software technologies, which require supercomputer-level computing power, can help radiologists and other imaging professionals on a practical basis.

For example, today, AI and deep learning can help physicians more efficiently produce images, improve quality of images, triage and classify images, serve in computer-aided detection of medical problems, and perform automated report drafting, Langlotz said.

As for value-based imaging, one radiology IT expert, Jim Whitfill, M.D., chief medical officer at Innovation Care Partners, a physician-led accountable care organization in Scottsdale, Ariz., said radiologists have opportunities to benefit financially from value-based care if they take on financial risk as ACOs do.

Value-based care and imaging not going away

During a panel on ACOs and value-based care, Whitfill noted that despite recent moves by the administration of President Donald Trump to trim several value-based care programs, federal healthcare officials are still behind the healthcare reimbursement approach, which Whitfill said has firm supporters.

"It's absolutely critical that radiologists bring their talent around leadership, information technology and the larger healthcare system to bear as organizations begin to make this shift" toward value-based care, Whitfill said.

In an interview, Whitfill said one of the biggest technological advances in medical imaging that will help in the move toward value-based area is enterprise imaging.

"Historically we've been very focused on radiology in the PACS system," Whitfill said. "But now, organizations are not only adding cardiology images, but also ophthalmology images, dermatology images and others, so we're seeing a revolution in terms of the imaging platforms moving all these images into one place."

Dig Deeper on RSNA conference and annual meeting

Join the conversation

1 comment

Send me notifications when other members comment.

Please create a username to comment.

What impact do you think AI and deep learning will have on radiology and other imaging specialties?