Identifying Brain Abnormalities with Schizophrenia Based on a Hybrid Feature Selection Technology

Decomposition-Based Correlation Learning for Multi-Modal MRI-Based Classification of Neuropsychiatric Disorders

Multi-modal magnetic resonance imaging (MRI) is widely used for diagnosing brain disease in clinical practice. However, the high-dimensionality of MRI images is challenging when training a convolution neural network. In addition, utilizing multiple MRI modalities jointly is even more challenging. We developed a method using decomposition-based correlation learning (DCL). To overcome the above challenges, we used a strategy to capture the complex relationship between structural MRI and functional MRI data. Under the guidance of matrix decomposition, DCL takes into account the spike magnitude of leading eigenvalues, the number of samples, and the dimensionality of the matrix. A canonical correlation analysis (CCA) was used to analyze the correlation and construct matrices. We evaluated DCL in the classification of multiple neuropsychiatric disorders listed in the Consortium for Neuropsychiatric Phenomics (CNP) dataset. In experiments, our method had a higher accuracy than several existing methods. Moreover, we found interesting feature connections from brain matrices based on DCL that can differentiate disease and normal cases and different subtypes of the disease. Furthermore, we extended experiments on a large sample size dataset and a small sample size dataset, compared with several other well-established methods that were designed for the multi neuropsychiatric disorder classification; our proposed method achieved state-of-the-art performance on all three datasets.

Impact of Psychosocial Occupational Therapy Combined with Anodal Transcranial Direct Current Stimulation to the Left Dorsolateral Prefrontal Cortex on the Cognitive Performance of Patients with Schizophrenia: A Randomized Controlled Trial

Background

The most common cognitive dysfunctions in patients with schizophrenia are information processing, memory, and learning. Based on the hypothesis of rehabilitation and brain stimulation in memory and learning, adding a form of neuromodulation to conventional rehabilitation might increase the effectiveness of treatments.

Aims

To explore the effects of psychosocial occupational therapy combined with anodal Transcranial Direct Current Stimulation (tDCS) on cognitive performance in patients with Schizophrenia.

Methods

Twenty-four patients diagnosed with schizophrenia were randomized into the experimental and control groups. We used The Cambridge Neuropsychological Test Automated Battery (CANTAB) and the Loewenstein Occupational Therapy Cognitive Assessment battery (LOTCA) to assess spatial recognition, attention, visual memory, learning abilities, and high-level cognitive functions like problem-solving. All participants received customized psychosocial occupational therapy activities. Furthermore, the experimental group received 12 sessions of active anodal tDCS for 20 minutes with 2 mA intensity on the left dorsolateral prefrontal cortex (DLPFC) while the patients in the sham group received sham tDCS.

Results

Combining tDCS to conventional psychosocial occupational therapy resulted in a significant increase in spatial memory, visual learning, and attention.

Conclusions

Anodal tDCS on the left DLPFC improved visual memory, attention, and learning abilities. Contrary to our expectations, we could not find any changes in complex and more demanding cognitive functions.

Machine Learning Analytics of Resting-State Functional Connectivity Predicts Survival Outcomes of Glioblastoma Multiforme Patients

Glioblastoma multiforme (GBM) is the most frequently occurring brain malignancy. Due to its poor prognosis with currently available treatments, there is a pressing need for easily accessible, non-invasive techniques to help inform pre-treatment planning, patient counseling, and improve outcomes. In this study we determined the feasibility of resting-state functional connectivity (rsFC) to classify GBM patients into short-term and long-term survival groups with respect to reported median survival (14.6 months). We used a support vector machine with rsFC between regions of interest as predictive features. We employed a novel hybrid feature selection method whereby features were first filtered using correlations between rsFC and OS, and then using the established method of recursive feature elimination (RFE) to select the optimal feature subset. Leave-one-subject-out cross-validation evaluated the performance of models. Classification between short- and long-term survival accuracy was 71.9%. Sensitivity and specificity were 77.1 and 65.5%, respectively. The area under the receiver operating characteristic curve was 0.752 (95% CI, 0.62–0.88). These findings suggest that highly specific features of rsFC may predict GBM survival. Taken together, the findings of this study support that resting-state fMRI and machine learning analytics could enable a radiomic biomarker for GBM, augmenting care and planning for individual patients.

Multi-modal biomarkers of low back pain: A machine learning approach

•

Widespread differences in cortical thickness (CT) were observed in patients with low back pain.

•

Changes in CT correlated with self-reported clinical scores of pain and emotion.

•

Changes in resting state fMRI metrics of functional networks.

•

Support vector machines separated low back pain patients from controls with a high performance.

•

Multi-modal biomarkers can be useful when identifying personalized treatments for low back pain.

Chronic low back pain (LBP) is a very common health problem worldwide and a major cause of disability. Yet, the lack of quantifiable metrics on which to base clinical decisions leads to imprecise treatments, unnecessary surgery and reduced patient outcomes. Although, the focus of LBP has largely focused on the spine, the literature demonstrates a robust reorganization of the human brain in the setting of LBP. Brain neuroimaging holds promise for the discovery of biomarkers that will improve the treatment of chronic LBP. In this study, we report on morphological changes in cerebral cortical thickness (CT) and resting-state functional connectivity (rsFC) measures as potential brain biomarkers for LBP. Structural MRI scans, resting state functional MRI scans and self-reported clinical scores were collected from 24 LBP patients and 27 age-matched healthy controls (HC). The results suggest widespread differences in CT in LBP patients relative to HC. These differences in CT are correlated with self-reported clinical summary scores, the Physical Component Summary and Mental Component Summary scores. The primary visual, secondary visual and default mode networks showed significant age-corrected increases in connectivity with multiple networks in LBP patients. Cortical regions classified as hubs based on their eigenvector centrality (EC) showed differences in their topology within motor and visual processing regions. Finally, a support vector machine trained using CT to classify LBP subjects from HC achieved an average classification accuracy of 74.51%, AUC = 0.787 (95% CI: 0.66–0.91). The findings from this study suggest widespread changes in CT and rsFC in patients with LBP while a machine learning algorithm trained using CT can predict patient group. Taken together, these findings suggest that CT and rsFC may act as potential biomarkers for LBP to guide therapy.

Two-Step Feature Selection for Identifying Developmental Differences in Resting fMRI Intrinsic Connectivity Networks

Functional connectivity derived from functional magnetic resonance imaging (fMRI) is used as an effective way to assess brain architecture. There has been a growing interest in its application to the study of intrinsic connectivity networks (ICNs) during different brain development stages. fMRI data are of high dimension but small sample size, and it is crucial to perform dimension reduction before pattern analysis of ICNs. Feature selection is thus used to reduce redundancy, lower the complexity of learning, and enhance the interpretability. To study the varying patterns of ICNs in different brain development stages, we propose a two-step feature selection method. First, an improved support vector machine based recursive feature elimination method is utilized to study the differences of connectivity during development. To further reduce the highly correlated features, a combination of F-score and correlation score is applied. This method was then applied to analysis of the Philadelphia Neurodevelopmental Cohort (PNC) data. The two-step feature selection was randomly performed 20 times, and those features that showed up consistently in the experiments were chosen as the essential ICN differences between different brain ages. Our results indicate that ICN differences exist in brain development, and they are related to task control, cognition, information processing, attention, and other brain functions. In particular, compared with children, young adults exhibit increasing functional connectivity in the sensory/somatomotor network, cingulo-opercular task control network, visual network, and some other subnetworks. In addition, the connectivity in young adults decreases between the default mode network and other subnetworks such as the fronto-parietal task control network. The results are coincident with the fact that the connectivity within the brain alters from segregation to integration as an individual grows.