Meeting Banner
Abstract #0608

A unsupervised machine learning approach for classification of white matter hyperintensity patterns applied to Systemic Lupus Erythematosus.

Theodor Rumetshofer1, Francesca Inglese2, Jeroen de Bresser2, Peter Mannfolk3, Olof Strandberg4, Markus Nilsson1, Itamar Ronen2, Andreas Jönsen5, Linda Knutsson6,7, Tom Huizinga8, Gerda Steup-Beekman8, and Pia Sundgren1,9,10
1Clinical Science Lund / Diagnostic Radiology, Lund University, Lund, Sweden, 2Department of Radiology, Leiden University Medical Center, Leiden, Netherlands, 3Department of Medical Imaging and Physiology, Skåne University Hospital, Lund, Sweden, 4Clinical Memory Research Unit, Department of Clinical Sciences, Malmö, Lund University, Lund, Sweden, 5Department of Rheumatology, Lund University, Skåne University Hospital, Lund, Sweden, 6Department of Medical Radiation Physics, Lund University, Lund, Sweden, 7Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, MD, United States, 8Department of Rheumatology, Leiden University Medical Center, Leiden, Netherlands, 9Department of Clinical Sciences/Centre for Imaging and Function, Skåne University Hospital, Lund, Sweden, 10Lund University BioImaging Center, Lund University, Lund, Sweden

White Matter Hyperintensities (WMH) are common clinical neuroimaging brain markers. However, WMH in Systemic Lupus Erythematosus (SLE) are non-specific. For this purpose, we developed and unsupervised machine learning approach based on individual WMH distribution to unveil hidden MRI phenotypes. Cluster analysis was performed on a two-site SLE dataset with significant different WMH burden and MRI acquisition protocols. The resulting MRI phenotypes show a clear lesion pattern on distinct WM tracts. This approach reduces the influence of the total WMH burden and MRI acquisition parameters and improves WMH characterization in SLE.

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

Join Here