Maximum-uncertainty linear discrimination analysis of first-episode schizophrenia subjects

Recent techniques of image analysis brought the possibility to recognize subjects based on discriminative image features. We performed a magnetic resonance imaging (MRI)-based classification study to assess its usefulness for outcome prediction of first-episode schizophrenia patients (FES). We included 39 FES patients and 39 healthy controls (HC) and performed the maximum-uncertainty linear discrimination analysis (MLDA) of MRI brain intensity images. The classification accuracy index (CA) was correlated with the Positive and Negative Syndrome Scale (PANSS) and the Global Assessment of Functioning scale (GAF) at 1-year follow-up. The rate of correct classifications of patients with poor and good outcomes was analyzed using chi-square tests. MLDA classification was significantly better than classification by chance. Leave-one-out accuracy was 72%. CA correlated significantly with PANSS and GAF scores at the 1-year follow-up. Moreover, significantly more patients with poor outcome than those with good outcome were classified correctly. MLDA of brain MR intensity features is, therefore, able to correctly classify a significant number of FES patients, and the discriminative features are clinically relevant for clinical presentation 1 year after the first episode of schizophrenia. The accuracy of the current approach is, however, insufficient to be used in clinical practice immediately. Several methodological issues need to be addressed to increase the usefulness of this classification approach.

[1]  S. Kay,et al.  The positive and negative syndrome scale (PANSS) for schizophrenia. , 1987, Schizophrenia bulletin.

[2]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

[3]  Matcheri S. Keshavan,et al.  Dorsolateral prefrontal cortex morphology and short-term outcome in first-episode schizophrenia , 2005, Psychiatry Research: Neuroimaging.

[4]  Masao Iwase,et al.  Discriminant analysis in schizophrenia and healthy subjects using prefrontal activation during frontal lobe tasks: A near-infrared spectroscopy , 2010, Schizophrenia Research.

[5]  Tyrone D. Cannon,et al.  Elucidating a Magnetic Resonance Imaging-Based Neuroanatomic Biomarker for Psychosis: Classification Analysis Using Probabilistic Brain Atlas and Machine Learning Algorithms , 2009, Biological Psychiatry.

[6]  Adam M. Brickman,et al.  Volume of the cingulate and outcome in schizophrenia , 2005, Schizophrenia Research.

[7]  Karl J. Friston,et al.  Dysfunctional connectivity in schizophrenia. , 2002, World psychiatry : official journal of the World Psychiatric Association.

[8]  S. Charles Schulz,et al.  Classification of adolescent psychotic disorders using linear discriminant analysis , 2006, Schizophrenia Research.

[9]  T. Asada,et al.  Progressive brain changes in schizophrenia: a 1-year follow-up study of diffusion tensor imaging , 2009, Acta Neuropsychiatrica.

[10]  Ferath Kherif,et al.  Multivariate voxel-based morphometry successfully differentiates schizophrenia patients from healthy controls , 2007, NeuroImage.

[11]  Yasuhiro Kawasaki,et al.  Differentiation of first-episode schizophrenia patients from healthy controls using ROI-based multiple structural brain variables , 2010, Progress in Neuro-Psychopharmacology and Biological Psychiatry.

[12]  M. Mikl,et al.  Gray matter morphology and the level of functioning in one-year follow-up of first-episode schizophrenia patients , 2009, Progress in Neuro-Psychopharmacology and Biological Psychiatry.

[13]  André J. W. van der Kouwe,et al.  Age-associated alterations in cortical gray and white matter signal intensity and gray to white matter contrast , 2009, NeuroImage.

[14]  Carlos E. Thomaz,et al.  Hyperplane navigation: A method to set individual scores in fMRI group datasets , 2008, NeuroImage.

[15]  William M. Wells,et al.  Medical Image Computing and Computer-Assisted Intervention — MICCAI’98 , 1998, Lecture Notes in Computer Science.

[16]  Peng Wang,et al.  On Classifying Disease-Induced Patterns in the Brain Using Diffusion Tensor Images , 2008, MICCAI.

[17]  Vince D. Calhoun,et al.  A method to classify schizophrenia using inter-task spatial correlations of functional brain images , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[18]  Nick C Fox,et al.  Automatic classification of MR scans in Alzheimer's disease. , 2008, Brain : a journal of neurology.

[19]  Gareth J. Barker,et al.  INFORMATION PROCESSING IN MEDICAL IMAGING, PROCEEDINGS , 1999 .

[20]  Jacquie Kurland,et al.  Neural Mechanisms Underlying Learning Following Semantic Mediation Treatment in a Case of Phonologic Alexia , 2008, Brain Imaging and Behavior.

[21]  Carlos E. Thomaz,et al.  Evaluating SVM and MLDA in the extraction of discriminant regions for mental state prediction , 2009, NeuroImage.

[22]  E. Bullmore,et al.  The anatomy of first-episode and chronic schizophrenia: an anatomical likelihood estimation meta-analysis. , 2008, The American journal of psychiatry.

[23]  Dinggang Shen,et al.  Multivariate examination of brain abnormality using both structural and functional MRI , 2007, NeuroImage.

[24]  B. Turetsky,et al.  Whole-brain morphometric study of schizophrenia revealing a spatially complex set of focal abnormalities. , 2005, Archives of general psychiatry.

[25]  Deanne K. Thompson,et al.  Abnormal White Matter Signal on MR Imaging Is Related to Abnormal Tissue Microstructure , 2009, American Journal of Neuroradiology.

[26]  J B Poline,et al.  Evidence for abnormal cortical functional connectivity during working memory in schizophrenia. , 2001, The American journal of psychiatry.

[27]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[28]  Christian Gaser,et al.  Distinct pattern of brain structural deficits in subsyndromes of schizophrenia delineated by psychopathology , 2010, NeuroImage.

[29]  D. Weinberger,et al.  Remission in schizophrenia: proposed criteria and rationale for consensus. , 2005, The American journal of psychiatry.

[30]  Stephan Heckers,et al.  White matter abnormalities and neurocognitive deficits associated with the passivity phenomenon in schizophrenia: A diffusion tensor imaging study , 2009, Psychiatry Research: Neuroimaging.

[31]  Feng Shi,et al.  Regional Homogeneity and Anatomical Parcellation for fMRI Image Classification: Application to Schizophrenia and Normal Controls , 2007, MICCAI.

[32]  K. Krishnan,et al.  MR signal intensity of gray matter/white matter contrast and intracranial fat: effects of age and sex , 2002, Psychiatry Research: Neuroimaging.

[33]  Yasuhiro Kawasaki,et al.  Multiple structural brain measures obtained by three-dimensional magnetic resonance imaging to distinguish between schizophrenia patients and normal subjects. , 2004, Schizophrenia bulletin.

[34]  Carlos E. Thomaz,et al.  Multivariate Statistical Differences of MRI Samples of the Human Brain , 2007, Journal of Mathematical Imaging and Vision.

[35]  C. Leonard,et al.  Cumulative effect of anatomical risk factors for schizophrenia: an MRI study , 1999, Biological Psychiatry.

[36]  G. Bartzokis,et al.  In vivo evidence of differential impact of typical and atypical antipsychotics on intracortical myelin in adults with schizophrenia , 2009, Schizophrenia Research.

[37]  F. Turkheimer,et al.  Classification of schizophrenic patients and healthy controls using [18F] fluorodopa PET imaging , 2008, Schizophrenia Research.

[38]  Mert R. Sabuncu,et al.  A Unified Framework for MR Based Disease Classification , 2009, IPMI.

[39]  Cheng-Ta Li,et al.  White matter abnormalities in schizophrenia patients with tardive dyskinesia: A diffusion tensor image study , 2009, Schizophrenia Research.

[40]  H. Möller,et al.  Use of neuroanatomical pattern classification to identify subjects in at-risk mental states of psychosis and predict disease transition. , 2009, Archives of general psychiatry.

[41]  E. Bullmore,et al.  Meta-analysis of diffusion tensor imaging studies in schizophrenia , 2009, Schizophrenia Research.

[42]  V. Calhoun,et al.  A Review of Challenges in the Use of fMRI for Disease Classification / Characterization and A Projection Pursuit Application from A Multi-site fMRI Schizophrenia Study , 2008, Brain Imaging and Behavior.

[43]  R. Murray,et al.  Meta-analysis of regional brain volumes in schizophrenia. , 2000, The American journal of psychiatry.

[44]  V. Calhoun,et al.  Aberrant localization of synchronous hemodynamic activity in auditory cortex reliably characterizes schizophrenia , 2004, Biological Psychiatry.

[45]  A. Mizota,et al.  Quantitative Evaluation of Signal Intensity of Magnetic Resonance Images in Optic Neuritis , 2007, The open ophthalmology journal.

[46]  John Ashburner,et al.  A fast diffeomorphic image registration algorithm , 2007, NeuroImage.

[47]  H. Fukuyama,et al.  Link between Linear Hyperintensity Objects in Cerebral White Matter and Hypertensive Intracerebral Hemorrhage , 2004, Cerebrovascular Diseases.

[48]  R. Kikinis,et al.  A review of diffusion tensor imaging studies in schizophrenia. , 2007, Journal of psychiatric research.

[49]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .