Radiology and AI: An algorithm took my job

Radiology18

Radiologists and those who love them sometimes seem to be some of the most insecure people around and radiology seems consistently voted the specialty most likely to be made defunct by modern technology.

In Canada, this perception has been voiced repeatedly over the past decade or two, first with the perceived threat of radiologists on the other side of the world working during our night to interpret scans and provide results when Canadian radiologists are sleeping, and now with the widespread attention given to artificial intelligence (AI) and deep learning and its potential uses in health care.

At last year’s annual meeting of the Canadian Association of Radiologists (@CARadiologists) I pondered whether this year’s meeting of that organization would be leaving it too late to discuss the significant issues revolving around AI and radiology (see my post “(A) I, Radiologist”) given the speed with which the field is advancing.

I need not have worried.

Last week the CAR released a white paper on the role of AI in radiology in advance of its annual meeting this year to be held April 26-29 on the theme of AI in radiology with the learning objectives including: discussing the recent changes that have occurred in imaging as a result of the implementation of artificial intelligence, deep learning, and machine learning in imaging workflows and; discussing the opportunities of big data and artificial intelligence to improve on the diagnostic performance and predictive value of imaging.

As an extensive overview of the topic, the CAR document squarely confronts the main issue at hand, namely that “recent breakthroughs in image recognition introduced by deep learning techniques have been equated in the media with the imminent demise of radiologists.” The authors go on to state rightly that the work of radiologists goes far beyond that of just correctly interpreting images.

“… the complex work performed by radiologists includes many other tasks that require common sense and general intelligence for problem solving–tasks that cannot be achieved through AI. Understanding a case may require integration of medical concepts from different scientific fields (eg, anatomy, physiology, medical physics) and clinical specialties (eg, surgery, pathology, oncology) to provide plausible explanations for imaging findings. Such tasks accomplished by radiologists on a daily basis include consultation, protocoling, review of prior examinations, quality control, identification and dismissal of imaging artifacts, cancer staging, disease monitoring, interventional procedures for diagnostic or therapeutic purpose, reporting, management guidance, expertise in multidisciplinary discussions, and patient reassurance”

However, the white paper’s authors also fully appreciate the potential of AI and state that “to remain current Canadian radiologists will need to follow and contribute to health care AI research and development, embrace the changes in workflow that will be required to support the implementation of clinical AI and adapt to changes in their practice that will improve care of their patients.”

So, while the demise of radiology (again) does not seem imminent, the white paper will bear close reading by Canadian radiologists who wish to remain relevant with some of the most significant and fundamental advances in medicine currently underway.

(Image courtesy of the Canadian Association of Radiologists)

Advertisements

(A) I, Radiologist

2017-04-23 (2)

Born of the discovery of the x-ray by Wilhelm Roentgen in 1895, the specialty of radiology is suddenly facing perhaps its greatest challenge with advent of artificial intelligence (AI) and machine learning.

Radiologists who have adapted to all manner of new diagnostic modalities over the generations now find themselves facing the prospect of machines which read and interpret imaging results quicker and more accurately than they can.

The Canadian Association of Radiologists (@CARadiologists) recently held its 80th annual meeting in Montreal and among the posters was one advertising that next year’s meeting would focus on AI. One wonders, given the speed with which AI and other technologies such as 3D printing are transforming radiology and medicine in general, whether next year is maybe too late to grapple with the issues raised.

The program committee of the CAR may have unconsciously acknowledged this as many sessions at this year’s meeting dealt with advanced technologies and at least two speakers dealt directly with the future role of the radiologist.

In addition, one of the highlights of the exhibit hall was IBM Watson Health (@IBMWatsonHealth). Last year, IBM created the Watson Health medical imaging collaborative, a global initiative with more than 26 leading health systems, academic centres, and imaging companies (they are currently looking Canadian participants) to bring cognitive imaging into daily practice. Earlier this year, IBM launched the Watson Imaging Review to reduce practice-pattern variation and reconcile differences between a patient’s administrative record and his or her clinical diagnosis.

One of the IBM staff was heard telling a CAR delegate, Watson “is not here to take your job away, it’s here to make your job easier.”

Presentations on AI and machine learning were matched by discussions of 3D printing, another technology currently transforming radiology and health care delivery.

Dr. Frank Rybicki, chief of radiology at the University of Ottawa and chief of medical imaging at The Ottawa Hospital, gave a comprehensive overview of how 3D printing is transforming many areas of medicine. The Ottawa Hospital recently opened the first 3D printing program based at a Canadian hospital.

Dr. Rybicki predicted that soon every hospital would have such a program as 3D printing moves from niche interventions to a leading role in reconstructive surgery, and cardiovascular and neurological interventions as well as supplying models to improve physician-patient communications and reducing peri- and post-operative complications.

“3D printing is the information delivery system of the current radiology generation,” he said, such as the young radiologists from Memorial University of Newfoundland who presented a paper showing the value of 3D printing of blood vessels to help educate the public and medical students.

It was a past-president of CAR, Dr. Ted Lyons from the University of Manitoba who bluntly outlined the future facing radiologists as a result of all these changes.

He noted that one of the fundamental roles of radiologists – reading and interpreting x-ray film – has almost already totally disappeared with the advent of PACS (picture archiving and communication systems).  By 2035, he predicted, all x-rays, CT scans and MRIs will be read and interpreted by machines.

The way forward for radiologists is twofold according to Dr. Lyons; firstly by becoming more than a “faceless name” who interprets images in a darkened room and being more directly involved and engaged with other clinicians and patients at the bedside. The second fundamental need, he said, is for radiologists to become data scientists and lead the integration of AI into radiology practice.

Dr. Lyons presentation was complemented later in the meeting by a presentation from a SickKids Hospital, Toronto radiologist Dr. Erika Mann who reiterated how radiologists need to become more patient-centred if they wish to remain relevant.