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

Abstract

Objective To develop a deep learning algorithm for detection of active inflammatory sacroiliitis in short tau inversion recovery (STIR) sequence magnetic resonance imaging (MRI). Methods A 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 oedema, 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 oedema in the MR images. Results Inflammatory 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. Conclusion An MRI deep learning algorithm was developed for detection of inflammatory sacroiliitis in axial SpA.

ChatGPT: when artificial intelligence replaces the rheumatologist in medical writing

“…Indeed, the first part of this editorial (in quotation marks above) was obtained using AI software (namely, ChatGPT developed by openAI). To date, AI has been used in rheumatology to interpret imaging, for example, to search for erosions in RA1 or vertebral fractures,2 to identify sacroiliitis3 4 and to predict the progression of osteoarthritis 5. AI provides valuable clinical support6 in predicting response to therapeutics, identifying inflammatory diseases earlier7 and using Big Data 8 9.…”

Invited Speaker Presentation Abstracts

“…Deep learning has dramatically improved the ability of a computational model in processing images (2,3). Recently, deep learning has been applied to various imaging techniques such as magnetic resonance imaging (MRI) in axial spondyloarthritis (SpA) (4,5). AI technology may have applications in diagnosis, assessment of disease activity, and clinical research.…”

“…Santosa A 1,2 ; Tan T 1,3 ; Roslan N 4 ; Li J 1,5 1 Duke-NUS Medical School, Singapore, Singapore; 2 Division of Rheumatology, Department of General Medicine, Changi General Hospital, Singapore, Singapore; 3 Department of Rheumatology and Immunology, Singapore General Hospital, Singapore, Singapore; 4 Rheumatology Service, Department of General Medicine, Sengkang General Hospital, Singapore, Singapore; 5 Department of Gastroenterology and Hepatology, Changi General Hospital, Singapore, Singapore Background: AI-based conversational agents or chatbots have been used as digital healthcare interventions to deliver cost-efficient and personalized medical support. They have demonstrated benefits in disease diagnosis, monitoring and treatment support.…”

Comprehensive AI-assisted tool for ankylosing spondylitis based on multicenter research outperforms human experts

“…For early diagnosis, magnetic resonance imaging (MRI) can help identify the early lesions of sacroiliitis, specifically bone marrow edema ( 3 ). Deep learning (DL) techniques have been employed to create models that can increase the diagnostic effectiveness of MRI ( 17 , 18 ). These models perform well during validation; their area under curve (AUC) values are higher than 0.9.…”