A Machine Learning Approach to Distinguishing between Multiple Sclerosis and Cerebral Small Vessel Disease
Year: 2018
Type: dissertation
Abstract: We sought to develop an automatic diagnostic algorithm to distinguish between relapsing-remitting multiple sclerosis (RRMS) and cerebral small vessel disease (SVD) using neuroimaging and clinical features. A mixture of t-distributions and a spatial heuristic algorithm were developed for the automatic segmentation of lesions on two MRI sequences. Combined lesion probability maps of RRMS and SVD were subsequently developed using a derivation set of patients. A novel cross entropy image distance metric was used to quantify the similarity of new cases to each disease. Bayesian learning algorithms using non-informative priors were trained using neuroimaging features and clinical features. Model hyperparameters were tuned using Monte Carlo cross validation. The model consisting of both neuroimaging and clinical features misclassified one case out of 21 on the test set when distinguishing between RRMS and SVD. As the societal and monetary cost of both diseases is high, this work has real potential for clinical impact.
Source: TSpace (University of Toronto)
Author: Daniel Eftekhari
Language: English
Subfield: Clinical Neurology
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W2939033752