No abstract

Human visual perception is able to recognize a wide range of targets under challenging conditions, but has limited throughput. Machine vision and automatic content analytics can process images at a high speed, but suffers from inadequate recognition accuracy for general target classes. In this paper, we propose a new paradigm to explore and combine the strengths of both systems. A single trial EEG-based brain machine interface (BCI) subsystem is used to detect objects of interest of arbitrary classes from an initial subset of images. The EEG detection outcomes are used as input to a graph-based pattern mining subsystem to identify, refine, and propagate the labels to retrieve relevant images from a much larger pool. The combined strategy is unique in its generality, robustness, and high throughput. It has great potential for advancing the state of the art in media retrieval applications. We have evaluated and demonstrated significant performance gains of the proposed system with multiple and diverse image classes over several data sets, including those from Internet (Caltech 101) and remote sensing images. In this paper, we will also present insights learned from the experiments and discuss future research directions.

The error-related negativity (ERN) is a negative deflection in the event-related potential following a mistake that is a putative biomarker of anxiety. The study assessed the ERN as a diagnostic biomarker using receiver operating characteristic (ROC) analyses in 96 cases with anxiety disorders (AD) and 96 matched healthy controls (HC) ages 8 to 18 years. Forty-one cases had generalized anxiety disorder (GAD); 55 cases had other anxiety disorders (OAD) without GAD. ERN amplitude was significantly increased in AD cases compared to HC. The area under the curve (AUC) in the ROC analysis was .64, indicating the ERN is an inadequate diagnostic test for AD altogether. The ERN was significantly increased in cases with either GAD or OAD compared to HC. The AUC in ROC analyses with GAD and OAD was .75 and .56, respectively, suggesting the ERN provides an adequate diagnostic test for GAD but not for OAD.

Objective The study examined the comorbidity of obsessive-compulsive disorder (OCD) with major depressive disorder (MDD) in a family study of OCD with pediatric probands. Method The study examined the lifetime prevalence of MDD in 133 first- and 459 second-degree relatives of pediatric probands with OCD and normal controls, and identified clinical variables associated with MDD in case first-degree relatives (FDR). All available FDR were directly interviewed blind to proband status; parents were also interviewed to assess the family psychiatric history of FDR and second-degree relatives (SDR). Best-estimate diagnoses were made using all sources of information. Data were analyzed with logistic regression and robust Cox regression models. Results Lifetime MDD prevalence was higher in case than control FDR (30.4% vs. 15.4%). Lifetime MDD prevalence was higher in FDR of case probands with MDD than in either FDR of case probands without MDD (46.3% vs. 19.7%) or control FDR (46.3% vs. 15.4%). MDD in case FDR was associated with MDD in case probands and with age and OCD in those relatives. Lifetime MDD prevalence was similar in case and control SDR. However, lifetime MDD prevalence was higher in SDR of case probands with MDD than in either SDR of case probands without MDD (31.9% vs. 16.8%) or control SDR (31.9% vs. 15.4%). Conclusions The results provide further evidence of the heterogeneity of early-onset OCD and suggest that early-onset OCD comorbid with MDD is a complex familial syndrome.

The pathophysiology of attention-deficit/hyperactivity disorder (ADHD) involves deficits in performance monitoring and adaptive adjustments. Yet, the developmental trajectory and underlying neural correlates of performance monitoring deficits in youth with ADHD remain poorly understood. To address the gap, this study recruited 77 children and adolescents with ADHD and 77 age- and gender-matched healthy controls (HC), ages 8–18 years, who performed an arrow flanker task during electroencephalogram recording. Compared to HC, participants with ADHD responded more slowly and showed larger reaction time variability (RTV) and reduced post-error slowing; they also exhibited reduced error-related negativity (ERN) and error positivity effects, and reduced N2 and P3 congruency effects. Age effects were observed across groups: with increasing age, participants responded faster, with less variability, and with increased post-error slowing. They also exhibited increased ERN effects and increased N2 and P3 congruency effects. Increased RTV and reduced P3 amplitude in incongruent trials were associated with increased ADHD Problems Scale scores on the Child Behavior Checklist across groups. The altered behavioral and ERP responses in ADHD are consistent with the pattern associated with younger age across groups. Further research with a longitudinal design may determine specific aspects of developmental alteration and deficits in ADHD during performance monitoring.