Elucidating a Magnetic Resonance Imaging-Based
Neuroanatomic Biomarker for Psychosis: Classification
Analysis Using Probabilistic Brain Atlas and Machine
Daqiang Sun, Theo G.M. van Erp, Paul M. Thompson, Carrie E. Bearden, Melita Daley, Leila Kushan,
Molly E. Hardt, Keith H. Nuechterlein, Arthur W. Toga, and Tyrone D. Cannon
Background: No objective diagnostic biomarkers or laboratory tests have yet been developed for psychotic illness. Magnetic resonance
Recently, efforts have been made to discriminate psychotic patients from healthy individuals using machine-learning-based pattern
classification methods on MRI data.
sex- and age-matched control subjects using a cortical pattern matching method. Between-group differences in GMD were evaluated.
Second, the sparse multinomial logistic regression classifier included in the Multivariate Pattern Analysis in Python machine-learning
package was applied to the cortical GMD maps to discriminate psychotic patients from control subjects.
Results: Patients showed significantly lower GMD, particularly in prefrontal, cingulate, and lateral temporal brain regions. Pattern classifi-
cation analysis achieved 86.1% accuracy in discriminating patients from controls using leave-one-out cross-validation.
Conclusions: These results suggest that even at the early stage of illness, psychotic patients present distinct patterns of regional cortical
gray matter changes that can be discriminated from the normal pattern. These findings indicate that we can detect complex patterns of
ultra-high risk for developing psychosis/schizophrenia.
Key Words: Classification, cortical pattern matching, MRI, psycho-
sis, PyMVPA, schizophrenia
the basis of clinical evaluation of symptoms and functional
impairment, and no objective diagnostic biomarkers or labora-
tory tests have yet been developed. Patients show significant
group differences, relative to healthy control subjects, on a range
of neurobiological and cognitive measures, but at the individual
level, these measures show extensive overlap with the normal
range and are therefore nondiagnostic. Recently, however, ef-
forts have been made to discriminate patients from healthy
individuals by applying multivariate analysis to various data sets
of combined measures (1–3).
It is well established that schizophrenia and other psychoses
are associated with brain structural abnormalities. Neuroimaging
studies have found brain volume decreases in schizophrenia
patients compared with healthy controls, with the most pro-
chizophrenia and other psychotic disorders are severe
mental illnesses that cause tremendous human suffering
and economic burden. These diseases are diagnosed on
nounced abnormalities in the hippocampus, superior temporal
gyrus, prefrontal lobe, and cingulate gyrus (4,5). Thus far, most
structural magnetic resonance imaging magnetic resonance im-
aging (MRI) studies of schizophrenia/psychosis have adopted a
region-of-interest analysis or a mass-univariate method, in which
statistics are performed on each region/voxel independently.
These approaches are advantageous in identifying region-spe-
cific differences between groups (6) but can miss signals from
different regions/voxels that are spatially correlated and tend to
occur together. Further, because there is usually extensive group
overlap even for the regions/voxels showing the most pro-
nounced differences, univariate methods are unlikely to satisfac-
torily discriminate patients from healthy control subjects at the
individual subject level.
Multivariate classification methods have been applied to
neuroimaging data to address these limitations. Rather than
treating each voxel independently from the others, multivariate
analysis of image data seeks the best group classification by
taking into account multiple voxels simultaneously. Machine-
learning-based multivariate methods have been successfully
used to differentiate task-specific brain activity in functional MRI
studies (7,8), to segment brain structures (9), and to classify with
high accuracy individuals in the prodromal phase of Alzheimer’s
Recently, these methods have been applied to brain structural
images from schizophrenia patients and have resulted in a high
accuracy of classification (81.1%) from images of healthy subjects
(2). In a follow-up report by the same group, the pattern
recognized in schizophrenia–control classification was applied
to unaffected family members of schizophrenia patients, and a
similar-to-patient pattern was found in family members (11).
From the Departments of Psychology (DS, TGMvE, CEB, LK, MEH, KHN, TDC)
and of Psychiatry and Biobehavioral Sciences (CEB, MD, KHN, TDC), and
the Semel Institute for Neuroscience and Human Behavior (CEB, MD,
Neuro Imaging (PMT, AWT), Department of Neurology, University of
California at Los Angeles School of Medicine.
Address correspondence to Tyrone D. Cannon, Ph.D., Department of Psy-
les, CA 90095; E-mail: email@example.com.
Received Apr 13, 2009; revised Jul 15, 2009; accepted Jul 19, 2009.
BIOL PSYCHIATRY 2009;xx:xxx
© 2009 Society of Biological Psychiatry
ARTICLE IN PRESS
Instead of using voxel data as predictors, composite measures
including principal components have also been used as features
for machine learning, and reasonable classifications have been
accomplished using linear discriminant analysis (12) and support
vector machines (13).
In this study, we used the cortical pattern matching method
(14) to assess cortical gray matter abnormalities in patients with
recent-onset psychosis. We further applied the PyMVPA (Multi-
variate Pattern Analysis in Python, http://www.pymvpa.org)
machine-learning package (15,16) to gray matter density (GMD)
maps to determine whether group classification at the individual
level could be achieved in the early course of psychosis. Cortical
pattern matching is an advanced brain registration technique that
can achieve accurate anatomical correspondence between brain
surfaces. It has proved successful in detecting subtle cortical gray
matter changes in normal development and aging and pathologic
conditions (14). PyMVPA is a recently developed Python module
that integrates and implements multiple machine-learning algo-
rithms for pattern classification suitable for neuroimaging data
(15). We applied the sparse multinomial logistic regression
(SMLR) classifier (17). It has several advantages—computational
efficiency, good classification performance, and the intrinsic
feature selection process that makes a separate signal filtering
We hypothesized that cortical gray matter deficits would be
present in psychotic patients in the prefrontal, cingulate, and
superior temporal regions, on the basis of the convergence of
previous findings. Further, we expected that application of
multivariate classification based on cortical gray matter patterns
would be able to discriminate reliably between recent-onset
psychosis patients and healthy control subjects.
Methods and Materials
Participants were recruited from the Aftercare Research Pro-
gram and Adolescent Brain-Behavior Research Clinic (ABBRC) at
the University of California—Los Angeles. Criteria for identifica-
tion of subjects with recent-onset psychosis included onset of
first-episode psychosis within the past 2 years and a DSM-IV
diagnosis of a psychotic disorder. For patients, the baseline
clinical assessment interview included a structured diagnostic
interview (18) and a review of medical records and collateral
information available from family and care providers that con-
tributed to a consensus diagnosis of psychotic disorder. Detailed
information regarding reliability and consensus diagnosis proce-
dures are described elsewhere (19,20).
Healthy control subjects were recruited from the same com-
munities as the patients through local advertising. They did not
meet DSM-IV criteria for a psychiatric disorder, as determined by
direct Structured Clinical Interview for DSM interview, and did
not have a first-degree family history of a psychotic disorder or
meet criteria for a prodromal state, as determined by Structured
Interview for Prodromal Syndromes (SIPS) assessment with the
patients and (for minors) their parents or legal guardians.
Additional exclusion criteria for all participants included the
presence of a neurologic disorder, drug or alcohol abuse or
dependence within the past 6 months, insufficient English flu-
ency, and IQ below 70.
Clinical interviewers underwent a rigorous training protocol
to ensure reliability on clinical measures. Certification requires
that interviewers achieve “good” to “excellent” reliability (inter-
class correlations over .75 for all symptom ratings, and kappas of
at least .80 for prodromal syndrome diagnoses) on SIPS training
videotapes, compared with gold standard ratings developed at
Yale University (21,22). Diagnostic reliability on the SCID-I/P
(Patient Edition) requires independent rating of a minimum of six
SCID-I/P training videos, followed by four live supervised assess-
ments. Interrater reliability was calculated by comparing trainee
ratings with gold standard ratings, as described in Ventura et al.
(20); trainees are required to achieve a sensitivity kappa of .75 or
greater and a specificity kappa of at least .75 regarding SCID-I/P
symptoms, as well as 90% agreement on all diagnostic classifi-
cations across SCID-I/P assessments.
Thirty-six recent-onset psychosis patients (including four ul-
tra-high-risk individuals who converted to psychosis within 12
months from the scan time) and 36 sex- and age-matched healthy
control subjects were included in the analysis. Although most of
the patients in the sample had a diagnosis of schizophrenia
spectrum disorder (schizophrenia, schizophreniform, or schizo-
affective disorder), to maximize the sample size, we also in-
cluded a small number of patients with affective psychosis and
atypical psychosis. There were 13 females and 23 males in each
group, and the mean (? SD) ages were 19.0 ? 5.2 years and 19.0
years ? 4.8 years for patients and control subjects, respectively.
The IQ scores were 104.1 ? 17.1 and 109.2 ? 23.6, and years of
education were 11.2 ? 2.6 years and 11.8 years ? 3.0 years, for
patients and control subjects, respectively. One patient and three
control subjects were left-handed among all subjects. There were
no significant differences in age, sex, handedness, or years of
education (all ps ? .20). The diagnostic breakdown of psychotic
patients was schizophrenia (n ? 21), schizophreniform disorder
(6), schizoaffective disorder (5), bipolar disorder with psychotic
features (2), major depression with mood-incongruent psychotic
symptoms (1), and psychosis not otherwise specified (1). For 31
patients whose medication records were available, atypical anti-
psychotic medications had been taken by 16 cases, mood
stabilizers by 6 cases, and antidepressants by 9 cases, before MRI
scans. Four patients had taken none of these medications before
scans. The study was approved by Internal Review Board at the
University of California—Los Angeles. All subjects signed in-
formed consent/assent documents after the study procedures
were fully explained.
Image Processing and Analysis
All participants were scanned on a 1.5-T Siemens Sonata MRI
scanner. A three-dimensional (3D) magnetization prepared rapid
gradient echo (MPRAGE) sequence generated 160 contiguous,
1.0-mm sagittal slices. Imaging parameters were echo time/
repetition time ? 4.38 msec/1900 msec; flip angle ? 15°; field of
view ? 256 mm2; voxel dimension ? 1 mm3.
For each scan, a radio frequency bias field correction was
performed (23). The cerebrum was extracted from the remainder
of the head in the image and was divided into left and right
hemispheric images. These images were edited manually, keep-
ing cerebral voxels and removing nonbrain tissue voxels. Auto-
mated tissue segmentation was performed on each scan to
classify the image into gray matter, white matter, and cerebro-
spinal fluid (24). The gray matter image was retained for further
analysis. The hemispheric images were registered to a standard
3D stereotaxic space (25) with nine degree-of-freedom linear
transformations (26). Cortical pattern matching (14) was per-
formed in the standard space, as described below.
A cortical surface extraction was performed to generate both
hemispheric surface models for each brain (27). In this process,
a spherical mesh surface was continuously deformed to fit the
2 BIOL PSYCHIATRY 2009;xx:xxx
D. Sun et al.
ARTICLE IN PRESS
cortical surface that best differentiated brain tissue and cortical
cerebrospinal fluid, and a high-resolution surface model repre-
senting 65,536 brain surface points was created. On each hemi-
spheric surface, 29 anatomic landmark curves following major
sulci and seven control curves that delineate the lateral surface
and the medial surface were manually traced by image analysts
blind to subject demographics and diagnosis. The tracing
protocol is available on the Internet (http://www.loni.ucla.
edu/?esowell/edevel/MedialLinesProtocol.htm). The reliability of
tracing was tested on six standard brain surfaces, and the average
distance between the sulcal curves tracing by the analysts and the
standard sulcal curves was less than 2 mm in most regions.
The hemispheric surfaces and curves were then flattened to a
two-dimensional plane, and average curves were generated by
averaging the positions of the same curves across all subjects.
The hemispheric surfaces were elastically warped to each other
on the basis of matching individual curves to their corresponding
average curves, and the coordinate positions of each surface
point in their 3D space were preserved. The 3D surface models
were reconstructed in the standard space and were transformed
back to each individual scan’s native space for GMD sampling.
In each scan’s native space where the segmented gray matter
image resided, local GMD was calculated and assigned to each
point on the hemispheric surface models. This was done by
creating a sphere of 15-mm radius around each surface point and
calculating the proportion of gray matter volume within the
sphere. The obtained GMD maps were transformed to the
standard space for group comparison and classification.
Student’s t tests were performed to compute differences in
mean GMD between patients and control subjects at each brain
surface point, and uncorrected P-maps were generated for
visualization. Following this, standard permutation tests were
conducted to confirm the significance of the overall pattern of
differences. We conducted 100,000 randomized permutations
(randomly assigning subjects to either patient or control groups,
while keeping the total number of subjects per group the same)
for the whole hemispheric surfaces. In each permutation, the
number of suprathreshold surface voxels for which p ? .01 was
computed, and the null distribution of this statistic was deter-
mined from all permutations. Between-group differences were
considered significant if less than 5% (p ? .05) of the results from
all random permutations exceeded the actual result. This ap-
proach has been used in many prior studies and is comparable to
an approach called set-level inference in functional brain imag-
ing (28). In other words, the fraction of the surface that exceeds
a predefined fixed threshold is estimated both on real data and in
random simulations, and the fraction of the random simulations that
beat the real effect is considered the p value or likelihood that the
observed pattern of suprathreshold effects occurred by chance.
PyMVPA was applied to GMD maps for group classification
(15). Basically, all coregistered GMD maps were converted to
one-dimensional arrays and were combined to form a two-
dimensional (GMD ? subject) array. Binary group labels (0 for
control subjects, and one for patients) were assigned to each
subject. The SMLR classifier (17) was applied to the data set, with
the lambda penalty set to the default value (lm ? .1). We used
the leave-one-out cross-validation method to determine the
accuracy of classification. All subjects except one were chosen as
the training data set, and a decision surface that best separated
the two groups was computed by the SMLR algorithm. The
decision surface was then applied to the left-out subject (test data
set) to predict into which group he or she fell. Iteratively, the
leave-one-out process was applied to each subject, and the
accuracy of all predictions was calculated.
To evaluate the significance of the acquired accuracy value
from the described cross-validation, 1000 permutations of leave-
one-out cross-validations were conducted. In each permutation,
the group labels (36 as “0,” and 36 as “1”) were randomly
assigned to all subjects, and a leave-one-out process was per-
formed to determine the prediction accuracy for this randomly
permuted experimental data set. The accuracy values obtained
from all permutations formed a null distribution, and the test was
considered significant if less than 5% (p ? .05) of the results from
all permutations exceeded the actual result. Using this null
distribution, it is possible to tell how likely it is to observe a
certain classification accuracy purely by chance, and conversely
it is possible to assign a significance level to the classification
accuracy. This would not be possible without knowing the
variance in the classification accuracy under the null hypothesis,
which the randomization process simulates.
Sparse Multinomial Logistic Regression Classifier
Briefly, the SMLR classifier belongs to a set of machine-
learning approaches that build a classification function from a
weighted combination of basis functions, in which the weights
are tuned during the learning phase to produce an optimal
classification of the training data (17). Sparse means that the
weight estimates are encouraged during the learning process to
be either high or exactly zero, to make the model more parsi-
monious, efficient to run, to avoid overfitting, and to improve
generalization capacity. To do this, a regularization or penalty
function is included during the learning process to promote a
sparse model. Multinomial logistic regression is one approach to
the multiclass classification problem, in which the features in the
images are used as predictor variables, and the output is a
categorization (here there are two classes). Basically, for each
category, a multiple regression is run to predict the odds ratio
that the image falls into that category. The odds ratios are then
converted into probabilities, and the most likely class is chosen.
the logarithm of the odds ratio of an image belonging to a specific
class. Then, the odds ratio is converted into a probability using a
nonlinear transfer function (sum of exponentials), which ensures
that all the classification probabilities sum to one across all classes.
To see this, we can assume that the training set consists of n
examples of data falling into k categories with p explanatory
variables. Then, we let ?jbe the multinomial probability of an
observation falling into the jth category. Then, we run a multiple
regression on the p features to predict the log of the odds ratio that
the training example belongs to the jth versus the kth category (29):
??0j??1jx1i??2jx2i? · · · ??pjxpi;
j?1,2, . . .,(k?1),
i?1,2, . . .,n.
Since all the ?’s add to unity, this reduce to
exp(?0j??1jx1i??2jx2i? · · · ??pjxpi)
k ?1exp(?0j??1jx1i??2jx2i? · · · ??pjxpi)
D. Sun et al.
BIOL PSYCHIATRY 2009;xx:xxx 3
ARTICLE IN PRESS
Recent-onset psychosis patients showed significantly lower
cortical GMD compared with sex- and age-matched healthy
control subjects (p ? .0002 in 100,000 permutations). As
shown in Figure 1, differences were most pronounced in the
lateral surface of the prefrontal and temporal lobes, limbic
regions along the cingulate sulci, and areas along the parieto-
occipital fissures. The primary sensorimotor cortex was rela-
tively spared, as well as the primary visual cortex on the
The PyMVPA classification analysis, using leave-one-out
cross-validation, accurately classified 86.1% of the patients and
control subjects. That is, in both groups, 31 of 36 subjects were
correctly assigned to their actual groups, when applying the
learned patterns from all other subjects to each individual
subject, which gave an accuracy of 86.1% for both groups.
Among 1000 permutations of leave-one-out cross-validations,
none gave accuracy values higher than 86.1%, ensuring that the
classification was statistically significant (p ? .001). The accuracy
of classification was 84.4% when the four ultra-high-risk con-
verter subjects and four sex- and age-matched control cases were
excluded from the analysis (78.1% for patients, and 90.6% for
control subjects). When patients with affective psychosis and
psychosis not otherwise specified (n ? 4) and four sex- and
age-matched control subjects were excluded, the accuracy of
classification was 87.5% (90.6% for patients and 84.4% for control
One hundred twenty-nine feature surface voxels were se-
lected by the SMLR process and were linearly combined for the
classification (30). The 25% with the highest weights, which
constituted 18 clusters and accounted for 59.9% of the total
weights, were plotted on the 3D surface to identify the regions
that contributed the most to the classification (Figure 2). The
regions containing surface points with highest weights included
the frontal pole, superior and middle temporal regions on the left
hemisphere, and the superior temporal, somatomotor, and sub-
genual regions on the right hemisphere.
Permutation tests by keeping the original sex ratios for both
groups did not change the result for either between-group
comparison or classification.
Here we applied a unique combination of imaging analysis
methods to a sample of recent-onset psychosis patients and
well-matched healthy subjects, revealing significant local gray
matter deficits that were most pronounced in prefrontal, cingu-
late, and lateral temporal regions in patients. Using a machine-
learning algorithm (PyMVPA), we achieved highly accurate
(86.1%) brain-image-based group classification.
Cortical pattern matching, a surface-based registration method
using reliable, manually selected anatomic landmarks and a
sophisticated warping technique, ensured that interindividual
brain anatomic variability was accounted for as far as possible.
SMLR, a novel classifier provided by the PyMVPA package, was
Figure 1. Maps of average gray matter density (GMD) and
P-maps of recent-onset psychosis patients versus healthy
control subjects comparison. Patients showed significantly
and temporal lobes, limbic regions along the cingulate sulci,
and areas along the parieto-occipital fissures. The primary
sensorimotor cortex and primary visual cortex on the medial
surface was relatively spared.
were plotted, forming 18 separate clusters. The regions containing surface
points with highest weights for group classification included the frontal
4 BIOL PSYCHIATRY 2009;xx:xxx
D. Sun et al.
ARTICLE IN PRESS
used to assign individuals into patient or control groups. Because
the SMLR algorithm has feature selection as an intrinsic process,
the whole gray matter density maps can be used as the input
data, making feature reduction such as principal component
analysis or analysis of variance–based filtering unnecessary and
avoiding the loss of potentially relevant information.
The prefrontal, cingulate, and lateral temporal regions
showed significant gray matter differences between patients and
control subjects, consistent with previous findings on schizo-
phrenia/psychosis (4,5). These cortical regions play important
roles in working memory, executive function, and auditory
sensation and language processing, all of which are impaired in
schizophrenic and psychotic patients. These gray matter deficits
may therefore underlie such functional abnormalities. The pri-
mary sensorimotor cortices and primary visual cortex were
relatively spared, probably indicating that these primary cortices
are less severely involved in the underlying pathophysiology of
psychosis compared with higher order association cortices.
The 86.1% classification accuracy is comparable to the best-
performing classifications in prior studies of schizophrenia. This
result suggests that even at the early stage of illness, psychotic
patients demonstrate some distinct patterns of cortical gray
matter differences that distinguish them from healthy individuals.
Each individual feature only accounts for a small portion of the
classification, and not all selected feature surface points were
within the regions of significant difference. The latter pattern is
consistent with previous reports (10) and indicates that some
discriminative signals could be missed if only features showing
significant between-group differences were searched. It is also
widely acknowledged in the machine-learning literature that
“weak learners,” or classifiers whose performance alone is only
slightly better than chance, can be combined to produce a
powerful classifier (9). The functional implications of and the
interplay among these “discriminative” regions can be the targets
of further investigations.
It is interesting to consider how cortical pattern matching
deals with sulcal variability and, more specifically, whether
greater sulcal variability among patients could contribute to the
classification results. It has been noted before that patients may
have slightly higher geometric variation in their sulcal landmarks,
when data from multiple subjects are mapped to a standard
stereotaxic space. This may be true in schizophrenia and psy-
chosis, although the evidence for greater cortical pattern varia-
tion in disease is stronger in other disorders such as Alzheimer’s
If patients are more variable in cortical structure than control
subjects, and if a standard registration approach were used
without modeling the cortex, then the cross-subject registration
errors in cortical anatomy can seriously reduce the power to
detect group differences and disease effects. To alleviate this loss
of power due to data misregistration across subjects at the cortex,
cortical pattern matching matches as far as possible major sulcal
landmarks traced by trained image analysts. This process also
matches the entire surface model of the cortex across subjects
and also performs a higher order matching of intervening surface
areas between the major sulci, using advanced mathematical
models based on covariant partial differential equations and
continuum mechanics. Because cortical anatomic regions are
generally defined by these major sulci, the cortical regions are
therefore accurately matched. It may be worth noting that
volume-based nonlinear registration algorithms cannot achieve
highly accurate brain surface matching, as suggested by a recent
large-scale comparison study (33).
In situations in which cortical patterns between brains are
topologically different, a one-to-one match may not exist at the
gross anatomic level. A well-studied example is that the parac-
ingulate sulcus is less frequently present in schizophrenic pa-
tients. In such cases, the best conceivable solution is to match
accurately what can be matched, and treat that which cannot be
matched as unmodeled residual variation. The lack of a sulcus
would be likely to be associated with fewer gray matter in that
area, which can be perfectly detected by cortical pattern match-
ing using the GMD measure.
In terms of classification, greater sulcal variability, if not
controlled for by cortical pattern matching, would reduce the
power of a classifier. The reason for this is that the unmodeled
cortical variance would tend to reduce the anatomic homology of
the gray matter features fed into the classifier as training data,
making classification more difficult. Cortical matching was per-
formed explicitly to reduce this source of error.
The limitations of this study include a relatively modest
sample size and the heterogeneous psychotic disorder diagnoses
in the patient group. Images were visually inspected for artifacts,
and those with observable artifacts were excluded from the
analyses. We cannot fully exclude the possibility that greater
motion in the patient group not resulting in observable artifacts
may have resulted in artifactual appearance of thinner cortex
(34), but in simulations in which potential motion-related cortical
thinning was assumed to be global, we showed that classification
accuracies were not severely affected (Supplement 1). The
accuracy value was derived using a leave-one-out cross-valida-
tion, thereby avoiding inflated accuracy due to data overfitting,
but a new data set might be preferable in some respects as a test
data set. Antipsychotics and other medications had been admin-
istered to most patients before MRI scans, and therefore we
cannot rule out the possibility that medication effects may
contribute to the observed differences. It can be speculated,
however, that the medication effect is less of a confounding
factor for the purposes of classification, because the types varied
considerably across patients, and there is unlikely to be a
common brain change pattern related to such a diversity of
Although we focused on cortical gray matter here, classifica-
tion analysis is not restricted to this particular measure. Measures
from other brain structures, other imaging modalities including
diffusion tensor imaging and functional MRI, electrophysiology
measures, and cognitive and clinical variables can all be inte-
grated into a classification analysis, and improved accuracy could
potentially be achieved. Classifiers other than SMLR or combina-
tions of different classifiers can be used to improve classification
accuracy as well. Boosting in particular offers one such ap-
proach, because it combines many features whose classification
performance on their own is only marginally better than chance
(i.e., weak learners). Even so, the advantage of boosting is
greatest when all the available features are weak, and not much
improvement is achieved if strong classifier is already available
(35). At the same time, the current methods can be applied in
future studies to individuals at ultra-high risk for developing
psychosis or schizophrenia. Patterns derived from recent-onset
psychotic patients can be applied to ultra-high-risk cases for
outcome prediction, and ultimately, patterns from individuals
who later converted to psychosis can be used to predict conver-
sion for future cases. An image-based tool is promising for
diagnostic use in standard clinical settings and for prediction of
outcome among clinically at risk individuals.
D. Sun et al.
BIOL PSYCHIATRY 2009;xx:xxx 5
ARTICLE IN PRESS
This research was supported by the following grants: National
Institute of Mental Health (NIMH) Grant No. MH65079 (to TDC)
and NIMH Grant No. P50 MH066286 (to KN), NIMH Grant No.
MH037705 (to KN), National Alliance for Research on Schizophre-
nia and Depression Young Investigator Award (to CEB), Grant
No. K23MH079028 (to MD), Grant No. EB008432 (to PMT), Grant
No. EB007813 (to PMT), Grant No. EB008281 (to PMT), Grant No.
HD050735 (to PMT), Grant No. AG020098 (to PMT), National
Institutes of Health (NIH)/National Center for Research Resources
Grant No. P-41 (to AWT), and NIH Grant No. U54 RR021813
(UCLA Center for Computational Biology), as well as by donations
from the Rutherford Charitable Foundation and Staglin Music
Festival for Mental Health to the University of California-Los Angeles
The authors report no biomedical financial interests or po-
tential conflicts of interest.
Supplementary material cited in this article is available
1. Caprihan A, Pearlson GD, Calhoun VD (2008): Application of principal
component analysis to distinguish patients with schizophrenia from
healthy controls based on fractional anisotropy measurements. Neuro-
2. Davatzikos C, Shen D, Gur RC, Wu X, Liu D, Fan Y, et al. (2005): Whole-
brain morphometric study of schizophrenia revealing a spatially com-
plex set of focal abnormalities. Arch Gen Psychiatry 62:1218–1227.
3. Michael AM, Calhoun VD, Andreasen NC, Baum SA (2008): A method to
classify schizophrenia using inter-task spatial correlations of functional
findings in schizophrenia. Schizophr Res 49:1–52.
Structural brain imaging evidence for multiple pathological processes
6. Friston KJ, Ashburner J (2004): Generative and recognition models for
neuroanatomy. Neuroimage 23:21–24.
7. Haxby JV, Gobbini MI, Furey ML, Ishai A, Schouten JL, Pietrini P (2001):
Distributed and overlapping representations of faces and objects in
ventral temporal cortex. Science 293:2425–2430.
8. Kay KN, Naselaris T, Prenger RJ, Gallant JL (2008): Identifying natural
images from human brain activity. Nature 452:352–355.
9. Morra JH, Tu Z, Apostolova LG, Green AE, Toga AW, Thompson PM
(2008): Automatic subcortical segmentation using a contextual
model. Med Image Comput Comput Assist Interv Int Conference 11:
10. Fan Y, Resnick SM, Wu X, Davatzikos C (2008): Structural and functional
biomarkers of prodromal Alzheimer’s disease: A high-dimensional pat-
tern classification study. Neuroimage 41:277–285.
family members and schizophrenia patients share brain structure pat-
terns: A high-dimensional pattern classification study. Biol Psychiatry
12. Kawasaki Y, Suzuki M, Kherif F, Takahashi T, Zhou SY, Nakamura K, et al.
(2007): Multivariate voxel-based morphometry successfully differenti-
13. Yoon U, Lee JM, Im K, Shin YW, Cho BH, Kim IY, et al. (2007): Pattern
classification using principal components of cortical thickness and
its discriminative pattern in schizophrenia. Neuroimage 34:1405–
et al. (2004): Mapping cortical change in Alzheimer’s disease, brain
development, and schizophrenia. Neuroimage 23(suppl 1):S2–18.
15. Hanke M, Halchenko YO, Sederberg PB, Olivetti E, Frund I, Rieger JW, et
al. (2009): PyMVPA: A unifying approach to the analysis of neuroscien-
tific data. Front. Neuroinformatics 3:3.
16. Hanke M, Halchenko YO, Sederberg PB, Hanson SJ, Haxby JV, Pollmann
fMRI data. Neuroinformatics 7:37–53.
17. Krishnapuram B, Carin L, Figueiredo MA, Hartemink AJ (2005): Sparse
Multinomial Logistic Regression: Fast Algorithms and Generalization
18. First MB, Spitzer RL, Gibbon M, Williams JB (1997): Structured Clinical
Interview for DSM-IV Axis I Disorders. Washington, DC: American Psychi-
19. Meyer SE, Bearden CE, Lux SR, Gordon JL, Johnson JK, O’Brien MP, et al.
quality assurance with the structured clinical interview for DSM-IV
(SCID-I/P). Psychiatry Res 79:163–173.
21. McGlashan TH, Miller TJ, Woods SW (2001): Pre-onset detection and
intervention research in schizophrenia psychoses: Current estimates of
benefit and risk. Schizophr Bull 27:563–570.
(2002): Prospective diagnosis of the initial prodrome for schizophrenia
based on the structured interview for prodromal syndromes: Prelimi-
nary evidence of interrater reliability and predictive validity. Am J Psy-
23. Sled JG, Zijdenbos AP, Evans AC (1998): A nonparametric method for
automatic correction of intensity nonuniformity in MRI data. IEEE Trans
24. Zhang Y, Brady M, Smith S (2001): Segmentation of brain MR images
through a hidden markov random field model and the expectation
International Consortium for Brain Mapping (ICBM). Neuroimage 2:89–
27. MacDonald JD, Kabani N, Avis D, Evans AC (2000): Automated 3-D ex-
traction of inner and outer surfaces of cerebral cortex from MRI. Neuro-
28. Friston KJ, Holmes A, Poline JB, Price CJ, Frith CD (1996): Detecting
29. Chatterjee S, Hadi AS (2006): Regression Analysis by Example, 4th ed.
Hoboken, NJ: Wiley, 317–340.
30. Ferrarini L, Palm WM, Olofsen H, van der Landen R, van Buchem MA,
Reiber JH, et al. (2008): Ventricular shape biomarkers for Alzheimer’s
disease in clinical MR images. Magn Reson Med 59:260–267.
31. Narr K, Thompson P, Sharma T, Moussai J, Zoumalan C, Rayman J, et al.
(2001): Three-dimensional mapping of gyral shape and cortical surface
al. (1998): Cortical variability and asymmetry in normal aging and Alz-
heimer’s disease. Cereb Cortex 8:492–509.
33. Klein A, Andersson J, Ardekani BA, Ashburner J, Avants B, Chiang
MC, et al. (2009): Evaluation of 14 nonlinear deformation algorithms
applied to human brain MRI registration. Neuroimage 46:786–
35. Martinez-Ramon M, Koltchinskii V, Heileman GL, Posse S (2006): fMRI
pattern classification using neuroanatomically constrained boosting.
6 BIOL PSYCHIATRY 2009;xx:xxx
D. Sun et al.
ARTICLE IN PRESS