• Christos Davatzikos, Dinggang Shen, Ruben C Gur, Xiaoying Wu, Dengfeng Liu, Yong Fan, Paul Hughett, Bruce I Turetsky, and Raquel E Gur.
• Section of Biomedical Image Analysis, Department of Radiology, University of Pennsylvania Medical Center, 3600 Market Street, Philadelphia, PA 19104, USA. christos@rad.upenn.edu
• Arch Gen Psychiat. 2005 Nov 1; 62 (11): 1218-27.

ContextNeuroanatomic abnormalities in schizophrenia may underlie behavioral manifestations. Characterization of such abnormalities is required for interpreting functional data. Frontotemporal abnormalities have been documented by using predetermined region-of-interest approaches, but deformation-based morphometry permits examination of the entire brain.ObjectivesTo perform whole-brain analyses of structural differences between patients with schizophrenia and controls, to examine sex and medication effects, and to apply a high-dimensional nonlinear pattern classification technique to quantify the degree of separation between patients and controls, thereby testing the potential of this new technique as an aid to diagnostic procedures.DesignWhole-brain morphologic analysis using high-dimensional shape transformations.SettingSchizophrenia Research Center, University of Pennsylvania Medical Center.ParticipantsNeuroleptic-naïve and previously treated patients with DSM-IV schizophrenia (n = 69) and sociodemographically matched controls (n = 79).Main Outcome MeasuresGray matter, white matter, and ventricular cerebrospinal fluid volumes in the brain.ResultsMagnetic resonance images showed reduced gray matter and increased ventricular cerebrospinal fluid volumes in patients with schizophrenia in the whole brain and in specific foci: the hippocampus and adjacent white matter, the cingulate and orbitofrontal cortex, the frontotemporal and parietotemporal areas, and the occipital areas near the lingual gyrus. The classifier had a mean classification accuracy of 81.1% for men and women combined (82% for women and 85% for men, when each group was treated separately), determined via cross-validation.ConclusionsThis study confirms previous findings of reduced frontotemporal volumes and suggests new hypotheses, especially involving occipital association and speech production areas. It also suggests finer localization of volume reduction in the hippocampus and other limbic structures and in the frontal lobe. Pattern classification showed high sensitivity and specificity for the diagnosis of schizophrenia, suggesting the potential utility of magnetic resonance imaging as a diagnostic aid.

36 keywords...

hide…