Multiple Sclerosis (MS) is a disease of the central nervous system characterized by inflammation and neuroaxonal degeneration in both grey and white matter structures. MS affects over 2.5 million people worldwide and over 250,000 people in the United States. Those afflicted may experience a wide range of debilitating symptoms including cognitive impairments, partial or complete vision loss, weakness in limbs, dizziness, and fatigue. These symptoms often occur sporadically at the onset of the disease but can worsen over time with respect to both frequency and intensity. In vivo MR acquisitions have shown that whole brain and cortical atrophy, an increased presence of white matter lesions, and a reduction in white matter connectivity occur in MS patients. Quantitative characterization of these brain changes, however, remains a challenge because of the lack of accurate and reliable image analysis tools that effectively model the anatomical changes that occur in MS. To address these issues, we propose to develop, validate, and apply software tools for the longitudinal analysis of MR brain images acquired from MS patients. We will leverage the experience of our research team in whole brain and lesion segmentation, reconstruction of the cerbral cortex, segmentation of white matter tracts, and software engineering to create a suite of tools that will benefit both MS researchers, clinicians, and ultimately the MS patient population. Over the duration of this R01 project, we will accomplish the following specific aims: 1) develop image analysis tools specifically designed for the quantitative longitudinal analysis of brain images with MS;2) provide tools and data for validating single time point and longitudinal MS image analysis algorithms;3) apply the developed tools to an ongoing MS longitudinal study that will reveal associations between brain volumes, lesion volume and location, cortical atrophy, and clinical outcomes on both a cross-sectional and longitudinal scale. The proposed tools will fill critical gaps in MS brain image analysis technology by allowing accurate and stable measurements of lesion volume, brain tissue volumes, cortical geometry, and white matter connectivity. This project will significantly impact the neurology, neuroscience, and image analysis communities. The released tools will enable a better understanding of the anatomical changes that occur during the progression of MS, potentially leading to early detection of functionally specific systems of disability. Furthermore, not only will clinical trials for MS drug therapies be greatly facilitated, but the developed tools may also be used to identify subsets of patients suitable for specific drug therapies. The released data and validation tools will also allow for a comparison of existing and newly developed methods, not only in MS patients, but also in healthy populations.
Multiple Sclerosis is a debilitating neurological disease that affects over 250,000 people in the United States alone. The development of robust and accurate algorithms for quantitatively analyzing brain images in MS patients will lead to a better understanding of the anatomical changes that occur during the progression of MS, and will facilitate clinical trials for MS drug therapies. This will ultimately lead to improved diagnosis and treatment of MS.
|Jog, Amod; Carass, Aaron; Pham, Dzung L et al. (2014) RANDOM FOREST FLAIR RECONSTRUCTION FROM T 1, T 2, AND PD -WEIGHTED MRI. Proc IEEE Int Symp Biomed Imaging 2014:1079-1082|
|Roy, Snehashis; Wang, Wen-Tung; Carass, Aaron et al. (2014) PET attenuation correction using synthetic CT from ultrashort echo-time MR imaging. J Nucl Med 55:2071-7|
|Shiee, Navid; Bazin, Pierre-Louis; Cuzzocreo, Jennifer L et al. (2014) Reconstruction of the human cerebral cortex robust to white matter lesions: method and validation. Hum Brain Mapp 35:3385-401|
|Sweeney, Elizabeth M; Vogelstein, Joshua T; Cuzzocreo, Jennifer L et al. (2014) A comparison of supervised machine learning algorithms and feature vectors for MS lesion segmentation using multimodal structural MRI. PLoS One 9:e95753|
|Chen, Min; Carass, Aaron; Oh, Jiwon et al. (2013) Automatic magnetic resonance spinal cord segmentation with topology constraints for variable fields of view. Neuroimage 83:1051-62|
|Chen, Min; Carass, Aaron; Reich, Daniel S et al. (2013) Voxel-Wise Displacement as Independent Features in Classification of Multiple Sclerosis. Proc SPIE Int Soc Opt Eng 8669:|
|Bazin, Pierre-Louis; Ye, Chuyang; Bogovic, John A et al. (2011) Direct segmentation of the major white matter tracts in diffusion tensor images. Neuroimage 58:458-68|