The neurobiological basis of neuroticism in late-life depression (LLD) is understudied. We hypothesized that older depressed subjects scoring high in measures of neuroticism would have smaller hippocampal and prefrontal volumes compared with non-neurotic older depressed subjects and with nondepressed comparison subjects based on previous research. Non-demented subjects were recruited and were either depressed with high neuroticism (n = 65), depressed with low neuroticism (n = 36), or never depressed (n = 27). For imaging outcomes focused on volumetric analyses, we found no significant between-group differences in hippocampal volume. However, we found several frontal lobe regions for which depressed subjects with high neuroticism scores had smaller volumes compared with non-neurotic older depressed subjects and with nondepressed comparison subjects, controlling for age and gender. These regions included the frontal pole, medial orbitofrontal cortex, and left pars orbitalis. In addition, we found that non-neurotic depressed subjects had a higher volume of non-white matter hypointensities on T1-weighted images (possibly related to cerebrovascular disease) than did neurotic depressed subjects. Our finding that depressed subjects low in neuroticism had higher volumes of non-white matter hypointensities is consistent with prior literature on "vascular depression." In contrast, the finding that those high in neuroticism had smaller frontal volume than depressed subjects low in neuroticism and never-depressed subjects highlight the importance of frontal circuitry in the subgroup of older depressed individuals with comorbid neuroticism. Together, these results implicate different neural mechanisms in older neurotic and non-neurotic depressed groups and suggest that multiple biological pathologies may lead to different clinical expressions of LLD.