Diagnosis and prognosis using brain scans based on robust regional measures
We have been developing methods for pattern recognition of medical images based on regional measures of structural, functional, and metabolic information. We examine medical images at various spatial scales based on robust regional features and identify most informative ones using feature selection techniques for pattern recognition. Our methods have been successfully applied to a variety of pattern recognition studies based on structural images, functional images, and multimodal images [1-5].
- Yong Fan
- Lao, Z., et al., Morphological classification of brains via high-dimensional shape transformations and machine learning methods. Neuroimage, 2004. 21(1): 46-57.
- Davatzikos, C., et al., Classifying spatial patterns of brain activity for lie-detection. Neuroimage, 2005. 28(3): 663-668.
- Fan, Y., et al., COMPARE: Classification Of Morphological Patterns using Adaptive Regional Elements, IEEE Transactions on Medical Imaging, 2007. 26(1): 93-105
- Fan, Y., et al., Multivariate examination of brain abnormality using both structural and functional MRI, 2007. Neuroimage, 36(4):1189-1199
- Wang, Y., et al., High-dimensional pattern regression using machine learning: from medical images to continuous clinical variables, Neuroimage, 2010. 50 (4):1519-1535
- Liu, L., et al., Combination of dynamic 11 C-PIB PET and structural MRI improves diagnosis of Alzheimer’s disease, 2015. Psychiatry Research: Neuroimaging 233 (2):131-140