Opportunistic Screening of Low Bone Mineral Density From Standard X-Rays.

BACKGROUND: Osteoporosis, characterized by loss of bone mineral density (BMD), is underscreened. Osteoporosis and low bone mass are diagnosed by a BMD T-score ≤ -2.5, and between -1.0 and -2.5, respectively, at the femoral neck or lumbar vertebrae (L1-4), using dual energy x-ray absorptiometry (DXA). The ability to estimate BMD at those anatomic sites from standard radiographs would enable opportunistic screening of low BMD (T-score < -1) in individuals undergoing x-ray for any clinical indication. METHODS: Radiographs of the lumbar spine, thoracic spine, chest, pelvis, hand, and knee, with a paired DXA acquired within 1 year, were obtained from community imaging centers (62,023 x-ray-DXA pairs of patients). A software program called Rho was developed that uses x-ray, age, and sex as inputs, and outputs a score of 1 to 10 that corresponds with the likelihood of low BMD. The program's performance was assessed using receiver-operating characteristic analyses in three independent test sets, as follows: patients from community imaging centers (n = 3,729; 83% female); patients in the Canadian Multicentre Osteoporosis Study (n = 1,780; 71% female); and patients in the Osteoarthritis Initiative (n = 591; 50% female). RESULTS: The areas under the receiver-operating characteristic curves were 0.89 (0.87-0.90), 0.87 (0.85-0.88), and 0.82 (0.79-0.85), respectively, and subset analyses showed similar results for each sex, body part, and race. CONCLUSION: Rho can opportunistically screen patients at risk of low BMD (at femoral neck or L1-4) from radiographs of the lumbar spine, thoracic spine, chest, pelvis, hand, or knee.

Canadian Association of Radiologists White Paper on Artificial Intelligence in Radiology.

Artificial intelligence (AI) is rapidly moving from an experimental phase to an implementation phase in many fields, including medicine. The combination of improved availability of large datasets, increasing computing power, and advances in learning algorithms has created major performance breakthroughs in the development of AI applications. In the last 5 years, AI techniques known as deep learning have delivered rapidly improving performance in image recognition, caption generation, and speech recognition. Radiology, in particular, is a prime candidate for early adoption of these techniques. It is anticipated that the implementation of AI in radiology over the next decade will significantly improve the quality, value, and depth of radiology's contribution to patient care and population health, and will revolutionize radiologists' workflows. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI working group with the mandate to discuss and deliberate on practice, policy, and patient care issues related to the introduction and implementation of AI in imaging. This white paper provides recommendations for the CAR derived from deliberations between members of the AI working group. This white paper on AI in radiology will inform CAR members and policymakers on key terminology, educational needs of members, research and development, partnerships, potential clinical applications, implementation, structure and governance, role of radiologists, and potential impact of AI on radiology in Canada.