AI spots difficult-to-detect structural joint changes on X-ray exams

A new deep learning algorithm can help radiologists and other doctors spot a difficult-to-detect joint condition in patients with chronic back pain. 

Axial spondyloarthritis (SpA) involves structural changes in sacroiliac joints and can affect the spine, skin, intestines and eyes. Many will go on to suffer spinal fusion, which means providers must be sure to correctly diagnose joint changes on X-ray exams. An MRI is typically ordered if they’re unsure.

But researchers overseas found their neural network is highly accurate at spotting radiographic sacroiliitis, they reported during the American College of Rheumatology’s annual meeting this week. It may help radiologists spot joint problems before they become worse.

“X-rays of sacroiliac joints are difficult to interpret,” lead author Denis Poddubnyy, MD, head of Rheumatology at Charite Medical University Berlin, said Wednesday. “The neural network could be, therefore, considered as a supportive tool providing a standardized assessment of sacroiliac joints on the X-rays in the context of diagnostic or classification approach.”

For their investigation, the German team assessed sacroiliac X-rays taken from 361 patients with chronic back pain and suspected axial SpA. A consensus diagnosis from both a radiologist and rheumatologist were used to confirm axial SpA.

The neural network notched a 79% sensitivity for spotting axial SpA on X-rays and 94% specificity for detecting structural joint changes indicative of the condition.

Providers are beginning to shift their initial imaging strategy for suspected SpA, the authors noted, and the team is developing a new tool in response.

“The overall trend ... (is moving) toward a broader use of MRI as the first imaging tool if axial SpA is suspected, but interpretation of MRI can be challenging,” Poddubnyy added. “We are working on the development of an artificial neural network that would be able to recognize active inflammatory and structural changes on MRI of sacroiliac joints.”

""

Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.

Around the web

The two companies aim to improve patient access to high-quality MRI scans by combining their artificial intelligence capabilities.

Positron, a New York-based nuclear imaging company, will now provide Upbeat Cardiology Solutions with advanced PET/CT systems and services. 

The nuclear imaging isotope shortage of molybdenum-99 may be over now that the sidelined reactor is restarting. ASNC's president says PET and new SPECT technologies helped cardiac imaging labs better weather the storm.