AI Algorithm Detects Erosions, Ankylosis With High Accuracy in Patients With Sacroiliitis
Together with researcher dr. ir. Danilo Babin from IPI, researchers from University Hospital Ghent, Peking University Shenzhen Hospital, University of Alberta, Ruhr-University Bochum, and the Vlaams Instituut voor Biotechnologie (Flemish Institute for Biotechnology, VIB) have recently published the article Neural network algorithm for detection of erosions and ankylosis on CT of the sacroiliac joints: multicentre development and validation of diagnostic accuracy in the journal European Radiology.
Their algorithm achieves 95% sensitivity in identifying erosions in patients with clinical symptoms of sacroiliitis -- inflammation of the sacroiliac joint and a common source of lower back pain. Earlier and more robust detection could lead to more timely treatment and better patient outcomes.
📰 Their conference paper on this work, An AI-based algorithm for automatic detection of erosion and ankylosis on CT images of the sacroiliac joints : multicentre development and validation, was presented at the 13th International Congress on Spondyloarthritides and covered in the media: