Classification of major depressive disorder using an attention-guided unified deep convolutional neural network and individual structural covariance network.

Major depressive disorder (MDD) is the second leading cause of disability worldwide. Currently, the structural magnetic resonance imaging-based MDD diagnosis models mainly utilize local grayscale information or morphological characteristics in a single site with small samples. Emerging evidence has demonstrated that different brain structures in different circuits have distinct developmental timing, but mature coordinately within the same functional circuit. Thus, establishing an attention-guided unified classification framework with deep learning and individual structural covariance networks in a large multisite dataset could facilitate developing an accurate diagnosis strategy. Our results showed that attention-guided classification could improve the classification accuracy from primary 75.1% to ultimate 76.54%. Furthermore, the discriminative features of regional covariance connectivities and local structural characteristics were found to be mainly located in prefrontal cortex, insula, superior temporal cortex, and cingulate cortex, which have been widely reported to be closely associated with depression. Our study demonstrated that our attention-guided unified deep learning framework may be an effective tool for MDD diagnosis. The identified covariance connectivities and structural features may serve as biomarkers for MDD.

Neural signatures of default mode network in major depression disorder after electroconvulsive therapy.

Functional abnormalities of default mode network (DMN) have been well documented in major depressive disorder (MDD). However, the association of DMN functional reorganization with antidepressant treatment and gene expression is unclear. Moreover, whether the functional interactions of DMN could predict treatment efficacy is also unknown. Here, we investigated the link of treatment response with functional alterations of DMN and gene expression with a comparably large sample including 46 individuals with MDD before and after electroconvulsive therapy (ECT) and 46 age- and sex-matched healthy controls. Static and dynamic functional connectivity (dFC) analyses showed increased intrinsic/static but decreased dynamic functional couplings of inter- and intra-subsystems and between nodes of DMN. The changes of static functional connections of DMN were spatially correlated with brain gene expression profiles. Moreover, static and dFC of the DMN before treatment as features could predict depressive symptom improvement following ECT. Taken together, these results shed light on the underlying neural and genetic basis of antidepressant effect of ECT and the intrinsic functional connectivity of DMN have the potential to serve as prognostic biomarkers to guide accurate personalized treatment.

Molecular basis underlying changes of brain entropy and functional connectivity in major depressive disorders after electroconvulsive therapy.

INTRODUCTION: Electroconvulsive therapy (ECT) is widely used for treatment-resistant depression. However, it is unclear whether/how ECT can be targeted to affect brain regions and circuits in the brain to dynamically regulate mood and cognition. METHODS: This study used brain entropy (BEN) to measure the irregular levels of brain systems in 46 major depressive disorder (MDD) patients before and after ECT treatment. Functional connectivity (FC) was further adopted to reveal changes of functional couplings. Moreover, transcriptomic and neurotransmitter receptor data were used to reveal genetic and molecular basis of the changes of BEN and functional connectivities. RESULTS: Compared to pretreatment, the BEN in the posterior cerebellar lobe (PCL) significantly decreased and FC between the PCL and the right temporal pole (TP) significantly increased in MDD patients after treatment. Moreover, we found that these changes of BEN and FC were closely associated with genes' expression profiles involved in MAPK signaling pathway, GABAergic synapse, and dopaminergic synapse and were significantly correlated with the receptor/transporter density of 5-HT, norepinephrine, glutamate, etc. CONCLUSION: These findings suggest that loops in the cerebellum and TP are crucial for ECT regulation of mood and cognition, which provides new evidence for the antidepressant effects of ECT and the potential molecular mechanism leading to cognitive impairment.

Suppressing Thermal Negative Effect and Maintaining High-Temperature Steady Electrical Performance of Triboelectric Nanogenerators by Employing Phase Change Material.

Triboelectric nanogenerators (TENGs) are newly developed energy-harvesting mechanisms, which can efficiently transmute irregular mechanical energy into scarce electrical energy. However, the electrical performance of TENGs shows a decreasing tendency with the increase in temperature, and the negative effect caused by friction heat and operating environmental thermal stresses for the output performance, durability, and reliability are still a bottleneck, restricting the practical application of TENG electronic devices. Especially for wearable TENG devices, the heat-induced temperature rise evokes extreme discomfort and even hazards to human health. To effectively suppress the thermal negative effect and maintain the high-temperature steady electrical performance of TENGs, a novel thermo-regulating TENG (Tr-TENG) based on phase change materials (PCMs) is designed. The results state clearly that the Tr-TENG can maintain steady output performance without deterioration by the introduction of PCMs, during continuous heating and natural cooling, while the output performance of conventional TENG is decayed by 18.33%. More importantly, the Tr-TENG possesses high-efficiency thermal management ability, resulting in its improved durability, reliability, and thermal comfort. This study creates new possibilities for the development of advanced multifunctional TENGs with attractive characteristics and desirable performances and promotes the application of TENG electronic devices in harsh environments.