Investigating brain structural patterns in first episode psychosis and schizophrenia using MRI and a machine learning approach (original) (raw)
Related papers
Progress in Neuro-Psychopharmacology and Biological Psychiatry, 2010
Background: Brain morphometric measures from magnetic resonance imaging (MRI) have not been used to discriminate between first-episode patients with schizophrenia and healthy subjects. Methods: Magnetic resonance images were acquired from 34 (17 males, 17 females) first-episode schizophrenia patients and 48 (24 males, 24 females) age-and parental socio-economic status-matched healthy subjects. Twenty-nine regions of interest (ROI) were measured on 1-mm-thick coronal slices from the prefrontal and central parts of the brain. Linear discriminant function analysis was conducted using standardized z scores of the volumes of each ROI. Results: Discriminant function analysis with cross-validation procedures revealed that brain anatomical variables correctly classified 75.6% of male subjects and 82.9% of female subjects, respectively. The results of the volumetric comparisons of each ROI between patients and controls were generally consistent with those of the previous literature. Conclusions: To our knowledge, this study provides the first evidence of MRI-based successful classification between first-episode patients with schizophrenia and healthy controls. The potential of these methods for early detection of schizophrenia should be further explored.
2014
Although structural magnetic resonance imaging (MRI) has revealed partly non-overlapping brain abnormalities in schizophrenia and bipolar disorder, it is unknown whether structural MRI scans can be used to separate individuals with schizophrenia from those with bipolar disorder. An algorithm capable of discriminating between these two disorders could become a diagnostic aid for psychiatrists. Here, we scanned 66 schizophrenia patients, 66 patients with bipolar disorder and 66 healthy subjects on a 1.5 T MRI scanner. Three support vector machines were trained to separate patients with schizophrenia from healthy subjects, patients with schizophrenia from those with bipolar disorder, and patients with bipolar disorder from healthy subjects, respectively, based on their gray matter density images. The predictive power of the models was tested using cross-validation and in an independent validation set of 46 schizophrenia patients, 47 patients with bipolar disorder and 43 healthy subjects scanned on a 3 T MRI scanner. Schizophrenia patients could be separated from healthy subjects with an average accuracy of 90%. Additionally, schizophrenia patients and patients with bipolar disorder could be distinguished with an average accuracy of 88%.The model delineating bipolar patients from healthy subjects was less accurate, correctly classifying 67% of the healthy subjects and only 53% of the patients with bipolar disorder. In the latter group, lithium and antipsychotics use had no influence on the classification results. Application of the 1.5 T models on the 3 T validation set yielded average classification accuracies of 76% (healthy vs schizophrenia), 66% (bipolar vs schizophrenia) and 61% (healthy vs bipolar). In conclusion, the accurate separation of schizophrenia from bipolar patients on the basis of structural MRI scans, as demonstrated here, could be of added value in the differential diagnosis of these two disorders. The results also suggest that gray matter pathology in schizophrenia and bipolar disorder differs to such an extent that they can be reliably differentiated using machine learning paradigms.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention, 2007
This paper presents a discriminative model of multivariate pattern classification, based on functional magnetic resonance imaging (fMRI) and anatomical template. As a measure of brain function, Regional homogeneity (ReHo) is calculated voxel by voxel, and then a widely used anatomical template is applied on ReHo map to parcelate it into 116 brain regions. The mean and standard deviation of ReHo values in each region are extracted as features. Pseudo-Fisher Linear Discriminant Analysis (PFLDA) is performed for training samples to generate discriminative model. Classification experiments have been carried out in 48 schizophrenia patients and 35 normal controls. Under a full leave-one-out (LOO) cross-validation, correct prediction rate of 80% is achieved. Anatomical parcellation process is proved useful to improve classification rate by a control experiment. The discriminative model shows its ability to reveal abnormal brain functional activities and identify people with schizophrenia.
NeuroImage, 2007
Currently available laboratory procedures might provide additional information to psychiatric diagnostic systems for more valid classifications of mental disorders. To identify the correlative pattern of gray matter distribution that best discriminates schizophrenia patients from healthy subjects, we applied discriminant function analysis techniques using the multivariate linear model and the voxel-based morphometry. The first analysis was conducted to obtain a statistical model that classified 30 male healthy subjects and 30 male schizophrenia patients diagnosed according to current operational criteria. The second analysis was performed to prospectively validate the statistical model by successfully classifying a new cohort that consisted of 16 male healthy subjects and 16 male schizophrenia patients. Inferences about the structural relevance of the gray matter distribution could be made if the individual profile of pattern expression could be linked to the specific diagnosis of each subject. The result was that 90% of the subjects were correctly classified by the eigenimage, and the Jackknife approach revealed well above chance accuracy. The pattern of the eigenimage was characterized by positive loadings indicating gray matter decline in the patients in the lateral and medial prefrontal regions, insula, lateral temporal regions, medial temporal structures, and thalamus as well as the negative loadings reflecting gray matter increase in the patients in the putamen and cerebellum. When the eigenimage derived from the original cohort was applied to classify data from the second cohort, it correctly assigned more than 80% of the healthy subjects and schizophrenia patients. These findings suggest that the characteristic distribution of gray matter changes may be of diagnostic value for schizophrenia.
Regional Structural Characterization of the Brain of Schizophrenia Patients1
Academic Radiology, 2005
Abnormal neuro-development and brain structure may play a role in the pathophysiology of schizophrenia. To study morphology and age-related changes in this disease, we started with a set of cranial MRI's of 46 schizophrenia patients and age/gender matched healthy controls. First, we deformed a template brain image to our set of subject images. The Jacobian fields of these deformations were then reduced to sets of 52 normalized region volumes for each subject using a neuro-anatomical atlas. The normalized regional volumes of the control and patient groups were compared using Student's t-test. In addition, the age correlation of each region volume was calculated for the two groups. All results were corrected for multiple comparisons using permutation testing. Finally, we used a classifier based on support vector machines and a feature selection method in order to determine our ability to discriminate brains of controls from those of patients. RESULTS: Analysis of the region-integrated Jacobians showed an enlargement of the third ventricle in patients. The age-correlation study demonstrated significant positive correlation in the third ventricle and right thalamus of controls, but not patients. Using an average of 6.5 features, our classifier was able to correctly identify 72% of patients and 70% of controls. CONCLUSIONS: In addition to enlargement of the third ventricle, the brains of schizophrenia patients demonstrate a different pattern of age-related changes.
2012
tion, and the third component represented the hemispheric reciprocity in activity. The first and second components were similar to those of the control group; however, the third component in control subjects showed activation of the center versus anterior and posterior regions. This result is consistent with the notion of abnormalities in hemispheric asymmetries during the processing of sensory information in schizophrenia. In conclusion, this ERP study demonstrated that P100 amplitudes have information that can successfully classify patients and controls.
Schizophrenia classification using regions of interest in brain mri
Proceedings of Intelligent Data Analysis in Biomedicine and Pharmacology, IDAMAP, 2009
Is it possible to identify human schizophrenic patients just by analyzing their brain images? This is the fundamental question of magnetic resonance imaging (MRI) based studies of human brains for people affected by schizophrenia and other mental illnesses traditionally diagnosed by self-reports and behavioral observations. The appeal of this approach is at least two-fold: to provide a non-invasive diagnostic tool for mass analyses and early diagnoses, and to characterize mental illnesses with specific and detectable ...