Recent imaging studies suggest that the so-called "soft" neurological signs in schizophrenia might have neuroanatomical validity. We examined gray matter volume correlates of neurological soft signs (NSS) in antipsychotic-naive schizophrenia patients using an automated image analysis technique. NSS were assessed using a modified neurological evaluation scale with good inter-rater reliability. Magnetic resonance images of 30 schizophrenia patients and 27 age-, sex-, education- and handedness-matched healthy controls were processed using optimized voxel-based morphometry (VBM). Logistic regression analysis showed that only the Motor Sequencing Signs (MSS) sub-score was a significant predictor of subject's status among the NSS sub-scores. Optimized VBM analysis showed that the MSS sub-score had a significant negative correlation with total and regional gray matter volumes (prefrontal, posterior cingulate, temporal cortices, putamen, and cerebellum) in schizophrenia patients but not in controls. Prefrontal and temporal cortices, putamen and cerebellum had significant volume deficits in patients. Cortical and cerebellar correlates of the sub-score MSS support the concept of "cognitive dysmetria" in schizophrenia.