To assess regions and patterns of brain atrophy in patients with Parkinson disease (PD) with normal cognition (PD-NC), mild cognitive impairment (PD-MCI), and dementia-level cognitive deficits (PDD). Images were quantified using a region-of-interest approach and voxel-based morphometry analysis. We used a high-dimensional pattern classification approach to delineate brain regions that collectively formed the Spatial Pattern of Abnormalities for Recognition of PDD. The Parkinson's Disease and Movement Disorders Center at the University of Pennsylvania. Eighty-four PD patients (61 PD-NC, 12 PD-MCI, and 11 PDD) and 23 healthy control subjects (HCs) underwent magnetic resonance imaging of the brain. The PD-NC patients did not demonstrate significant brain atrophy compared with HCs. Compared with PD-NC patients, PD-MCI patients had hippocampal atrophy (β = -0.37; P = .001), and PDD patients demonstrated hippocampal (β = -0.32; P = .004) and additional medial temporal lobe atrophy (β = -0.36; P = .003). The PD-MCI patients had a different pattern of atrophy compared with PD-NC patients (P = .04) and a similar pattern to that of PDD patients (P = .81), characterized by hippocampal, prefrontal cortex gray and white matter, occipital lobe gray and white matter, and parietal lobe white matter atrophy. In nondemented PD patients, there was a correlation between memory-encoding performance and hippocampal volume. Hippocampal atrophy is a biomarker of initial cognitive decline in PD, including impaired memory encoding and storage, suggesting heterogeneity in the neural substrate of memory impairment. Use of a pattern classification approach may allow identification of diffuse regions of cortical gray and white matter atrophy early in the course of cognitive decline.