POS0990 Deep learning algorithms for magnetic resonance imaging of inflammatory sacroiliitis in axial spondyloarthritis.

Abstract

BackgroundMagnetic resonance imaging (MRI) of the sacroiliac (SI) joints is increasingly important in the management of axial spondyloarthritis (SpA). Artificial intelligence (AI) may be the next crucial step in enabling the widespread application of MRI.ObjectivesTo develop a deep learning algorithm for detection of active inflammatory sacroiliitis in short tau inversion recovery (STIR) sequence MRI.MethodsA total of 326 participants with axial spondyloarthritis (SpA), and 63 participants with non-specific back pain (NSBP) were recruited. STIR MRI of the SI joints was performed and clinical data were collected. Region of interests (ROIs) were drawn outlining bone marrow edema, a reliable marker of active inflammation, which formed the ground truth masks from which “fake-colour” images were derived. Both the original and “fake-colour” images were randomly allocated into either the training and validation dataset or the testing dataset. Attention U-net was used for the development of deep learning algorithms. As comparison, an independent radiologist and rheumatologist blinded to the ground truth masks, were tasked with identifying bone marrow edema in the MR images.ResultsInflammatory sacroiliitis were identified in 1398 MR images from 228 participants. No inflammation was found in 3944 MR images from 161 participants. The mean sensitivity of algorithms derived from the original dataset and “fake-colour” image dataset were 0.86±0.02, and 0.90±0.01 respectively. The mean specificity of algorithms derived from the original and “fake-colour” image dataset were 0.92±0.02, and 0.93±0.01 respectively. The mean testing dice coefficients were 0.48± 0.27 for the original dataset and 0.51±0.25 for the “fake-colour” image dataset. The area under the curve of the receiver operating characteristic (AUC-ROC) curve of the algorithms using original dataset and “fake-colour” image dataset were 0.92 and 0.96 respectively. Sensitivity and specificity of algorithms were comparable to interpretation by a radiologist, but outperformed the rheumatologist.ConclusionAn MRI deep learning algorithm was developed for detection of inflammatory sacroiliitis in axial SpA.Disclosure of InterestsNone declared