B1266
Title: Statistical approaches for diagnosing multiple sclerosis using magnetic resonance imaging
Authors: Russell Shinohara - University of Pennsylvania (United States) [presenting]
Abstract: Lesions in the brain's white matter, including lesions that arise in multiple sclerosis (MS), are abnormalities measurable on MRI. However, MS is prone to misdiagnosis due to clinicians' reliance on sometimes overly sensitive visual assessment of these lesions. As new imaging modalities allow for better lesion interrogation, new statistical modelling problems that include spatial constraints and overlapping analysis domains are increasingly important. Furthermore, other features, including morphology and morphometry of normal-appearing brain structures that are not detectable by the human eye, have recently been demonstrated to have diagnostic value. Leveraging multi-modal imaging approaches that focus on knowledge about etiology is critical for developing the next generation of robust and generalizable diagnostic imaging biomarkers.