Dataset Information

Classification of First-Episode Schizophrenia Using Multimodal Brain Features: A Combined Structural and Diffusion Imaging Study.

ABSTRACT: Recent neuroanatomical pattern recognition studies have shown some promises for developing an objective neuroimaging-based classification related to schizophrenia. This study explored the feasibility of reliably identifying schizophrenia using single and multimodal multivariate neuroimaging features. Multiple brain measures including regional gray matter (GM) volume, cortical thickness, gyrification, fractional anisotropy (FA), and mean diffusivity (MD) were extracted using fully automated procedures. We used Gradient Boosting Decision Tree to identify the most frequently selected features of each set of neuroanatomical metric and fused multimodal measures. The current classification model was trained and validated based on 98 patients with first-episode schizophrenia (FES) and 106 matched healthy controls (HCs). The classification model was trained and tested in an independent dataset of 54 patients with FES and 48 HCs using imaging data acquired on a different magnetic resonance imaging scanner. Using the most frequently selected features from fused structural and diffusion tensor imaging metrics, a classification accuracy of 75.05% was achieved, which was higher than accuracy derived from a single imaging metric. Most prominent discriminative features included cortical thickness of left transverse temporal gyrus and right parahippocampal gyrus, the FA of left corticospinal tract and right external capsule. In the independent cohort, average accuracy was 76.54%, derived from combined features selected from cortical thickness, gyrification, FA, and MD. These features characterized by GM abnormalities and white matter disruptions have discriminative power with respect to the underlying pathological changes in the brain of individuals having schizophrenia. Our results further highlight the potential advantage of multimodal data fusion for identifying schizophrenia.

SUBMITTER: Liang S

PROVIDER: S-EPMC6483586 | biostudies-literature | 2019 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Classification of First-Episode Schizophrenia Using Multimodal Brain Features: A Combined Structural and Diffusion Imaging Study.

Liang Sugai S Li Yinfei Y Zhang Zhong Z Kong Xiangzhen X Wang Qiang Q Deng Wei W Li Xiaojing X Zhao Liansheng L Li Mingli M Meng Yajing Y Huang Feng F Ma Xiaohong X Li Xin-Min XM Greenshaw Andrew J AJ Shao Junming J Li Tao T

Schizophrenia bulletin 20190401 3

Recent neuroanatomical pattern recognition studies have shown some promises for developing an objective neuroimaging-based classification related to schizophrenia. This study explored the feasibility of reliably identifying schizophrenia using single and multimodal multivariate neuroimaging features. Multiple brain measures including regional gray matter (GM) volume, cortical thickness, gyrification, fractional anisotropy (FA), and mean diffusivity (MD) were extracted using fully automated proce ...[more]

PMID: 29947804

Similar Datasets

Project description:Recent data suggest that treatment with antipsychotics is associated with reductions in cortical gray matter in patients with schizophrenia. These findings have led to concerns about the effect of antipsychotic treatment on brain structure and function; however, no studies to date have measured cortical function directly in individuals with schizophrenia and shown antipsychotic-related reductions of gray matter.To examine the effects of antipsychotics on brain structure and function in patients with first-episode schizophrenia, using cortical thickness measurements and administration of the AX version of the Continuous Performance Task (AX-CPT) during event-related functional magnetic resonance imaging.This case-control cross-sectional study was conducted at the Imaging Research Center of the University of California, Davis, from November 2004 through July 2012. Participants were recruited on admission into the Early Diagnosis and Preventive Treatment Clinic, an outpatient clinic specializing in first-episode psychosis. Patients with first-episode schizophrenia who received atypical antipsychotics (medicated patient group) (n?=?23) and those who received no antipsychotics (unmedicated patient group) (n?=?22) and healthy control participants (n?=?37) underwent functional magnetic resonance imaging using a 1.5-T scanner.Behavioral performance was measured by trial accuracy, reaction time, and d'-context score. Voxelwise statistical parametric maps tested differences in functional activity during the AX-CPT, and vertexwise maps of cortical thickness tested differences in cortical thickness across the whole brain.Significant cortical thinning was identified in the medicated patient group relative to the control group in prefrontal (mean reduction [MR], 0.27 mm; P?<?.001), temporal (MR, 0.34 mm; P?=?.02), parietal (MR, 0.21 mm; P?=?.001), and occipital (MR, 0.24 mm; P?=?.001) cortices. The unmedicated patient group showed no significant cortical thickness differences from the control group after clusterwise correction. The medicated patient group showed thinner cortex compared with the unmedicated patient group in the dorsolateral prefrontal cortex (DLPFC) (MR, 0.26 mm; P?=?.001) and temporal cortex (MR, 0.33 mm; P?=?.047). During the AX-CPT, both patient groups showed reduced DLPFC activity compared with the control group (P?=?.02 compared with the medicated group and P?<?.001 compared with the unmedicated group). However, the medicated patient group demonstrated higher DLPFC activation (P?=?.02) and better behavioral performance (P?=?.02) than the unmedicated patient group.These findings highlight the complex relationship between antipsychotic treatment and the structural, functional, and behavioral deficits repeatedly identified in schizophrenia. Although short-term treatment with antipsychotics was associated with prefrontal cortical thinning, treatment was also associated with better cognitive control and increased prefrontal functional activity. This study adds important context to the growing literature on the effects of antipsychotics on the brain and suggests caution in interpreting neuroanatomical changes as being related to a potentially adverse effect on brain function.

Project description:Reduced fractional anisotropy (FA) is a well-established correlate of schizophrenia, but it remains unclear whether these tensor-based differences are the result of axon damage and/or organizational changes and whether the changes are progressive in the adult course of illness. Diffusion MRI data were collected in 81 schizophrenia patients (54 first episode and 27 chronic) and 64 controls. Analysis of FA was combined with "fixel-based" analysis, the latter of which leverages connectivity and crossing-fiber information to assess both fiber bundle density and organizational complexity (i.e., presence and magnitude of off-axis diffusion signal). Compared with controls, patients with schizophrenia displayed clusters of significantly lower FA in the bilateral frontal lobes, right dorsal centrum semiovale, and the left anterior limb of the internal capsule. All FA-based group differences overlapped substantially with regions containing complex fiber architecture. FA within these clusters was positively correlated with principal axis fiber density, but inversely correlated with both secondary/tertiary axis fiber density and voxel-wise fiber complexity. Crossing fiber complexity had the strongest (inverse) association with FA (r?=?-0.82). When crossing fiber structure was modeled in the MRtrix fixel-based analysis pipeline, patients exhibited significantly lower fiber density compared to controls in the dorsal and posterior corpus callosum (central, postcentral, and forceps major). Findings of lower FA in patients with schizophrenia likely reflect two inversely related signals: reduced density of principal axis fiber tracts and increased off-axis diffusion sources. Whereas the former confirms at least some regions where myelin and or/axon count are lower in schizophrenia, the latter indicates that the FA signal from principal axis fiber coherence is broadly contaminated by macrostructural complexity, and therefore does not necessarily reflect microstructural group differences. These results underline the need to move beyond tensor-based models in favor of acquisition and analysis techniques that can help disambiguate different sources of white matter disruptions associated with schizophrenia.

Dataset Information

Classification of First-Episode Schizophrenia Using Multimodal Brain Features: A Combined Structural and Diffusion Imaging Study.

Publications

Classification of First-Episode Schizophrenia Using Multimodal Brain Features: A Combined Structural and Diffusion Imaging Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure