Rediscovering radiology’s ‘soul’ in the AI era

Despite radiology’s love-hate relationship with artificial intelligence (AI), advances could afford the field an opportunity to “hit refresh” and reinvent itself, Emory University professor and radiologist Srini Tridandapani, PhD, MD, MSCR, wrote in Academic Radiology this month.

In the journal, Tridandapani draws parallels between “Hit Refresh”—Microsoft CEO Satya Nadella’s written take on the challenges and opportunities Microsoft faces in the technological era—and radiology, which is winding down after decades of perfecting medical imaging practices and PACS. 

“Clearly, a revolution is taking place in computing, and the current intellectual gold rush for these technology companies lies in developing and harnessing artificial intelligence tools in various fields,” Tridandapani wrote. “And just as Nadella posits that AI is the tool that will help Microsoft rediscover its soul, it is also the tool that will help us rediscover radiology’s soul.”

Tridandapani said radiology’s rapid development makes way for AI, since as imaging practices advance, so does the amount of data that will need to be processed. Hundreds of images can be shipped across the country in seconds with modern digital capabilities, he said. Many radiologists haven’t seen images printed on film in over a decade, and that’s if they remember them at all.

“We have made what may have seemed impossible 30 years ago a reality,” he wrote. “If PACS was our end goal, then we have arrived, and there are no more transformational challenges to tackle in radiology.”

Tridandapani said radiologists can develop short-term solutions—what he described as “low-hanging fruit”—to conquer the inevitable data overload from PACS, including tools that will help prioritize studies and patients, maintain worklists and “take out the drudgery in our jobs.” Eventually, he said, machines will take responsibility for those tasks and devise ways to complete them even more efficiently.

It might generate a good amount of buzz in the radiological community,  but Tridandapani said it’s actually a good thing that technology will take some of the busywork out of radiologists’ jobs.

“The advances in the future will free us to do what we should be doing more of, which is to reconnect with our patients and interpret test results for them,” he wrote. “AI will never replace us because we can and will provide this care with empathy.”

Even if AI continues to outpace radiologists’ handiwork, physicians can rest easy knowing the tech isn’t too far ahead.

“AI will not be able to replace us entirely, even technically,” Tridandapani said. “Current AI efforts have achieved limited success in narrowly focused image interpretation problems, and there is no indication that an AI system can practice general radiology. That having been said, radiology needs to do some soul-searching to redefine its role in healthcare given the increasingly prevalent role of computers.”