|
Abstract:
|
Magnetic resonance imaging is crucial for in vivo detection and characterization of white matter lesions (WML) in multiple sclerosis. While WML have been studied for over two decades using MRI technology, segmentation remains challenging. The majority of statistical techniques for the automated segmentation of WML are based on a single imaging modality. However, recent advances have used multimodal techniques for identifying WML. Complementary imaging modalities emphasize different tissue properties, that can help identify and characterize interrelated features of lesions. However, prior work has ignored relationships between imaging modalities, which may be informative in this context. To harness the coherent changes in these measurements, we utilized inter-modal coupling regression (IMCo) to estimate the covariance structure across modalities. We utilize a local logistic regression, MIMoSA, which leverages new covariance features from IMCo regression as well as the mean structure of each imaging modality in order to model the probability that any voxel is part of a lesion. Probability maps are then thresholded to produce hard segmentations using a novel thresholding algorithm.
|
