Statistical Analysis of Magnetic Resonance Imaging Data in Multiple Sclerosis Lesions (Elizabeth Sweeney - Weill Cornell Medical College)

Brain magnetic resonance imaging (MRI) is a tool that uses a magnetic field to produce detailed images of the brain. Patients with multiple sclerosis (MS) have lesions in their brains which are visible on MRI. In this talk, I will be discussing two projects analyzing data from MS lesions on MRI. The first project describes work to aid in the diagnosis of MS. In order to diagnosis MS, the current diagnostic criteria requires lesions on MRI must be found at different time points (referred to as dissemination in time). I will discuss an algorithm I developed to estimate the age of MS lesions from a single MRI scan using radiomic features generated from multisequence structural MRI and quantitative MRI data. The algorithm allows for a faster and more definitive diagnosis of the disease. For the second project, I will introduce a lesion repair biomarker that I developed. MS lesion formation is a complex process involving inflammation, tissue damage, and tissue repair — all of which are visible on MRI and potentially modifiable by pharmacological therapy. The lesion repair biomarker provides a voxel-level (or three-dimensional pixel-level) measurement of slow and persistent, long-term intensity changes within lesion voxels. I then relate the biomarker to clinical information in a mixed model framework. Treatment with disease-modifying therapies and steroids are both associated with lesion repair.

When 4:00 pm to 5:00 pm on Thursday, October 31, 2019
Location MCS B31, 111 Cummington Mall