Meeting Banner
Abstract #1692

Volume of hyperintense inflammation (VHI): a deep learning-enabled quantitative imaging biomarker of inflammation load

Timothy JP Bray1,2, Carolyna JP Hepburn1, Alexis Jones3, Alan Bainbridge4, Hui Zhang5, and Margaret A Hall-Craggs1,2
1Centre for Medical Imaging, University College London, London, United Kingdom, 2Department of Imaging, University College London Hospital, London, United Kingdom, 3Rheumatology, University College London Hospital, London, United Kingdom, 4Medical Physics, University College London Hospital, London, United Kingdom, 5Centre for Medical Image Computing, University College London, London, United Kingdom

Synopsis

Short inversion time inversion recovery (STIR) MRI is widely used in clinical practice to identify and quantify inflammation in patients with axial spondyloarthritis. However, assessment of STIR images is limited by the qualitative nature of image interpretation, which depends on observer expertise, and can be biased by the clinical setting. To address this, we propose the volume of hyperintense inflammation (VHI) as a quantitative imaging biomarker of inflammation load, underpinned by a recently-described segmentation method incorporating deep learning and intensity-based segmentation.

This abstract and the presentation materials are available to members only; a login is required.

Join Here