Manifold Learning Combining Imaging with Non-Imaging Information

Recent work suggests that the space of brain magnetic resonance (MR) images can be described by a nonlinear and low-dimensional manifold. In the context of classifying Alzheimer's disease (AD) patients from healthy controls, we propose a method to incorporate subject meta-information into the manifold learning step. Information such as gender, age or genotype is often available in clinical studies and can inform the classification of a given query subject. In the proposed method, such information, whether discrete or continuous, can be used as an additional input to manifold learning and to enrich a distance measure derived from pairwise image similarities. Building on previous work, the Laplacian eigenmap objective function is extended to include the additional information. We use the ApoE genotype, the CSF-concentration of Aβ42 and hippocampal volume as meta-information to achieve significantly improved classification results for subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI) database.