Fully automated classification of pulmonary nodules in positron emission tomography-computed tomography imaging using a two-stage multimodal learning approach.

Background: Lung cancer is a malignant tumor, for which pulmonary nodules are considered to be significant indicators. Early recognition and timely treatment of pulmonary nodules can contribute to improving the survival rate of patients with cancer. Positron emission tomography-computed tomography (PET/CT) is a noninvasive, fusion imaging technique that can obtain both functional and structural information of lung regions. However, studies of pulmonary nodules based on computer-aided diagnosis have primarily focused on the nodule level due to a reliance on the annotation of nodules, which is superficial and unable to contribute to the actual clinical diagnosis. The aim of this study was thus to develop a fully automated classification framework for a more comprehensive assessment of pulmonary nodules in PET/CT imaging data. Methods: We developed a two-stage multimodal learning framework for the diagnosis of pulmonary nodules in PET/CT imaging. In this framework, Stage I focuses on pulmonary parenchyma segmentation using a pretrained U-Net and PET/CT registration. Stage II aims to extract, integrate, and recognize image-level and feature-level features by employing the three-dimensional (3D) Inception-residual net (ResNet) convolutional block attention module architecture and a dense-voting fusion mechanism. Results: In the experiments, the proposed model's performance was comprehensively validated using a set of real clinical data, achieving mean scores of 89.98%, 89.21%, 84.75%, 93.38%, 86.83%, and 0.9227 for accuracy, precision, recall, specificity, F1 score, and area under curve values, respectively. Conclusions: This paper presents a two-stage multimodal learning approach for the automatic diagnosis of pulmonary nodules. The findings reveal that the main reason for limiting model performance is the nonsolitary property of nodules in pulmonary nodule diagnosis, providing direction for future research.

MPGAN: Multi Pareto Generative Adversarial Network for the denoising and quantitative analysis of low-dose PET images of human brain.

Positron emission tomography (PET) imaging is widely used in medical imaging for analyzing neurological disorders and related brain diseases. Usually, full-dose imaging for PET ensures image quality but raises concerns about potential health risks of radiation exposure. The contradiction between reducing radiation exposure and maintaining diagnostic performance can be effectively addressed by reconstructing low-dose PET (L-PET) images to the same high-quality as full-dose (F-PET). This paper introduces the Multi Pareto Generative Adversarial Network (MPGAN) to achieve 3D end-to-end denoising for the L-PET images of human brain. MPGAN consists of two key modules: the diffused multi-round cascade generator (GDmc) and the dynamic Pareto-efficient discriminator (DPed), both of which play a zero-sum game for n(n∈1,2,3) rounds to ensure the quality of synthesized F-PET images. The Pareto-efficient dynamic discrimination process is introduced in DPed to adaptively adjust the weights of sub-discriminators for improved discrimination output. We validated the performance of MPGAN using three datasets, including two independent datasets and one mixed dataset, and compared it with 12 recent competing models. Experimental results indicate that the proposed MPGAN provides an effective solution for 3D end-to-end denoising of L-PET images of the human brain, which meets clinical standards and achieves state-of-the-art performance on commonly used metrics.

Glucocorticoid alleviates hypothalamic nerve injury via remodeling HPA axis homeostasis in stressed rats.

Excessive stress can exceed the adjustment ability of body and cause injury and dysfunction, while elucidation of the mechanism and prevention measures of stress-related injury are still insufficient. The present study was to observe the effect of glucocorticoid (GC) on stress-induced hypothalamic nerve injury and elucidate the potential mechanism. The present study intended to establish a chronic restraint stress rat model for follow-up study. Open field test and elevated plus maze test were used to observe behavioral changes of stress rats; Enzyme-linked immunosorbent assay (ELISA) was used to detect changes in the levels of hypothalamus-pituitary-adrenal (HPA) axis-related hormones and inflammatory factors in hypothalamus; toluidine blue staining was used to observe pathological changes of hypothalamus. The results showed that stress rats showed obvious anxiety-like behaviors, the levels of HPA axis-related hormones and inflammatory factors showed abnormal fluctuations, and morphological results showed significant nerve injury in hypothalamus. Low-dose GC treatment significantly improved behavioral changes, alleviated hypothalamic nerve injury, and restored hypothalamic levels of inflammatory factors, serum levels of GC, corticotropin-releasing hormone (CRH), and adrenocorticotropic hormone (ACTH) and GC level in adrenal cortex of stressed rats, while GC receptor (GR) inhibitor, CRH receptor inhibitor, and adrenalectomy reversed the ameliorative effects of low-dose GC. Our study clarified that low-dose GC can restore stress coping ability by reshaping the homeostasis of the HPA axis, thus alleviating behavioral abnormalities and hypothalamic nerve injury in stressed rats.

An Attention-Based Hemispheric Relation Inference Network for Perinatal Brain Age Prediction.

Brain anatomical age is an effective feature to assess the status of the brain, such as atypical development and aging. Although some deep learning models have been developed for estimating infant brain age, the performance of these models was unsatisfactory because few of them considered the developmental characteristics of brain anatomy during the perinatal period-the most rapid and complex developmental stage across the lifespan. The present study proposed an attention-based hemispheric relation inference network (HRINet) that takes advantage of the nature of brain structural lateralization during early development. This model captures the inter-hemispheric relationship using a graph attention mechanism and transmits lateralization information as features to describe the interactive development between bilateral hemispheres. The HRINet was used to estimate the brain age of 531 preterm and full-term neonates from the Developing Human Connectome Project (dHCP) database based on two metrics (mean curvature and sulcal depth) characterizing the folding morphology of the cortex. Our results showed that the HRINet outperformed other benchmark models in fitting the perinatal brain age, with mean absolute error of 0.53 and determination coefficient of 0.89. We also verified the generalizability of the HRINet on an extra independent dataset collected from the Gansu Provincial Maternity and Child-care Hospital. Furthermore, by applying the best-performing model to an independent dataset consisting of 47 scans of preterm infants at term-equivalent age, we showed that the predicted age was significantly lower than the chronological age, suggesting a delayed development of premature brains. Our results demonstrate the effectiveness and generalizability of the HRINet in estimating infant brain age, providing promising clinical applications for assessing neonatal brain maturity.

Disrupted dynamic brain functional connectivity in male cocaine use disorder: Hyperconnectivity, strongly-connected state tendency, and links to impulsivity and borderline traits.

Cocaine use is a major public health problem with serious negative consequences at both the individual and societal levels. Cocaine use disorder (CUD) is associated with cognitive and emotional impairments, often manifesting as alterations in brain functional connectivity (FC). This study employed resting-state functional magnetic resonance imaging (rs-fMRI) to examine dynamic FC in 38 male participants with CUD and 31 matched healthy controls. Using group spatial independent component analysis (group ICA) combined with sliding window approach, we identified two recurring distinct connectivity states: the strongly-connected state (state 1) and weakly-connected state (state 2). CUD patients exhibited significant increased mean dwell and fraction time in state 1, and increased transitions from state 2 to state 1, demonstrated significant strongly-connected state tendency. Our analysis revealed abnormal FC patterns that are state-dependent and state-shared in CUD patients. This study observed hyperconnectivity within the default mode network (DMN) and between DMN and other networks, which varied depending on the state. Furthermore, after adjustment for multiple comparisons, we found significant correlations between these altered dynamic FCs and clinical measures of impulsivity and borderline personality disorder. The disrupted FC and repetitive effects of precuneus and angular gyrus across correlations suggested that they might be the important hub of neural circuits related behaviorally and mentally in CUD. In summary, our study highlighted the potential of these disrupted FC as neuroimaging biomarkers and therapeutic targets, and provided new insights into the understanding of the neurophysiologic mechanisms of CUD.

Liver fibrosis automatic diagnosis utilizing dense-fusion attention contrastive learning network.

BACKGROUND: Liver fibrosis poses a significant public health challenge given its elevated incidence and associated mortality rates. Diffusion-Weighted Imaging (DWI) serves as a non-invasive diagnostic tool for supporting the identification of liver fibrosis. Deep learning, as a computer-aided diagnostic technology, can assist in recognizing the stage of liver fibrosis by extracting abstract features from DWI images. However, gathering samples is often challenging, posing a common dilemma in previous research. Moreover, previous studies frequently overlooked the cross-comparison information and latent connections among different DWI parameters. Thus, it is becoming a challenge to identify effective DWI parameters and dig potential features from multiple categories in a dataset with limited samples. PURPOSE: A self-defined Multi-view Contrastive Learning Network is developed to automatically classify multi-parameter DWI images and explore synergies between different DWI parameters. METHODS: A Dense-fusion Attention Contrastive Learning Network (DACLN) is designed and used to recognize DWI images. Concretely, a multi-view contrastive learning framework is constructed to train and extract features from raw multi-parameter DWI. Besides, a Dense-fusion module is designed to integrate feature and output predicted labels. RESULTS: We evaluated the performance of the proposed model on a set of real clinical data and analyzed the interpretability by Grad-CAM and annotation analysis, achieving average scores of 0.8825, 0.8702, 0.8933, 0.8727, and 0.8779 for accuracy, precision, recall, specificity and F-1 score. Of note, the experimental results revealed that IVIM-f, CTRW-ß, and MONO-ADC exhibited significant recognition ability and complementarity. CONCLUSION: Our method achieves competitive accuracy in liver fibrosis diagnosis using the limited multi-parameter DWI dataset and finds three types of DWI parameters with high sensitivity for diagnosing liver fibrosis, which suggests potential directions for future research.

Stimulator of interferon genes mediated immune senescence reveals the immune microenvironment and prognostic characteristics of bladder cancer.

Background: Studies have shown that the stimulator of interferon genes (STING) is critical in tumorigenesis, and development. This study aimed to investigate the immune profile and prognostic significance of STING-mediated immune senescence in bladder cancer (BLCA). Methods: We identified differential genes between tumor and normal tissue based on the Cancer Genome Atlas database, and used consensus clustering to identify BLCA subtypes. The genes most associated with overall survival were screened by further analysis and used to construct risk models. Then, comparing the immune microenvironment, tumor mutational load (TMB), and microsatellite instability (MSI) scores between different risk groups. Eventually, a nomogram was constructed based on clinical information and risk scores. The model was validated using receiver operating curves (ROC) and calibration plots. Results: We identified 160 differential genes, including 13 genes most associated with prognosis. Three subtypes of bladder cancer with different clinical and immunological features were identified. Immunotherapy was more likely to benefit the low-risk group, which had higher TMB and MSI scores. The nomogram was found to be highly predictive based on ROC analysis and calibration plots. Conclusion: The risk model and nomogram not only predict the prognosis of BLCA patients but also can guide the treatment.

A study of macroinvertebrate community structure and diversity in response to land use type in the Yiluo River Basin.

Land use types have a significant impact on river ecosystems. The Yiluo River is the largest tributary below Xiaolangdi Reservoir in the middle reaches of the Yellow River, and is one of the important water conservation areas in the Yellow River Basin. Studying the ecological status of the Yiluo River under varied land use types in this basin is crucial for both ecological protection and the high-quality development of the Yellow River Basin. This study investigated the impacts of land use types on the macroinvertebrate community and functional structure in the Yiluo River Basin and introduced the concept of the land use health index (LUI). During the survey period, a total of 11,894 macroinvertebrates were collected, and 143 species were identified, belonging to 4 phyla, 7 orders, 22 families, and 75 families. The results showed that LUI had the most significant impact on macroinvertebrate community structure, with substrate type, dry plant weight, total phosphorus, turbidity, and attached algae biomass also playing significant roles in affecting macroinvertebrate communities. The species richness, the Shannon-Wiener index, and the Margalef richness index exhibited a nonlinear positive correlation with LUI of the sampling site, increasing as LUI enhancing and eventually reaching a plateau. Functional richness showed a linear and positive correlation with LUI, increasing with its enhancement, while functional evenness and functional divergence exhibited a nonlinear correlation with LUI. Functional evenness initially increased and then decreased with the enhancement of LUI, while functional divergence decreased with LUI enhancement. This study can provide a scientific reference for river ecological management under various land use scenarios.The Yiluo River is the largest tributary below Xiaolangdi Reservoir in the middle reaches of the Yellow River, and is one of the important water conservation areas in the Yellow River Basin. Studying the ecological status of the Yiluo River under varied land use types in this basin is crucial for both ecological protection and the high-quality development of the Yellow River Basin. This study investigated the impacts of land use types on the macroinvertebrate community and functional structure in the Yiluo River Basin and introduced the concept of the land use health index (LUI). During the survey period, a total of 11,894 macroinvertebrates were collected, and 143 species were identified, belonging to 4 phyla, 7 orders, 22 families, and 75 families. The results showed that LUI had the most significant impact on macroinvertebrate community structure, with substrate type, dry plant weight, total phosphorus, turbidity, and attached algae biomass also playing significant roles in affecting macroinvertebrate communities. The species richness, the Shannon-Wiener index, and the Margalef richness index exhibited a nonlinear positive correlation with LUI of the sampling site, increasing as LUI enhancing and eventually reaching a plateau. Functional richness showed a linear and positive correlation with LUI, increasing with its enhancement, while functional evenness and functional divergence exhibited a nonlinear correlation with LUI. Functional evenness initially increased and then decreased with the enhancement of LUI, while functional divergence decreased with LUI enhancement. This study can provide a scientific reference for river ecological management under various land use scenarios.

Monocyte-Derived Macrophages Aggravate Cardiac Dysfunction After Ischemic Stroke in Mice.

BACKGROUND: Cardiac damage induced by ischemic stroke, such as arrhythmia, cardiac dysfunction, and even cardiac arrest, is referred to as cerebral-cardiac syndrome (CCS). Cardiac macrophages are reported to be closely associated with stroke-induced cardiac damage. However, the role of macrophage subsets in CCS is still unclear due to their heterogeneity. Sympathetic nerves play a significant role in regulating macrophages in cardiovascular disease. However, the role of macrophage subsets and sympathetic nerves in CCS is still unclear. METHODS AND RESULTS: In this study, a middle cerebral artery occlusion mouse model was used to simulate ischemic stroke. ECG and echocardiography were used to assess cardiac function. We used Cx3cr1GFPCcr2RFP mice and NLRP3-deficient mice in combination with Smart-seq2 RNA sequencing to confirm the role of macrophage subsets in CCS. We demonstrated that ischemic stroke-induced cardiac damage is characterized by severe cardiac dysfunction and robust infiltration of monocyte-derived macrophages into the heart. Subsequently, we identified that cardiac monocyte-derived macrophages displayed a proinflammatory profile. We also observed that cardiac dysfunction was rescued in ischemic stroke mice by blocking macrophage infiltration using a CCR2 antagonist and NLRP3-deficient mice. In addition, a cardiac sympathetic nerve retrograde tracer and a sympathectomy method were used to explore the relationship between sympathetic nerves and cardiac macrophages. We found that cardiac sympathetic nerves are significantly activated after ischemic stroke, which contributes to the infiltration of monocyte-derived macrophages and subsequent cardiac dysfunction. CONCLUSIONS: Our findings suggest a potential pathogenesis of CCS involving the cardiac sympathetic nerve-monocyte-derived macrophage axis.

Decreased connexin 40 expression of the sinoatrial node mediates ischemic stroke-induced arrhythmia in mice.

BACKGROUND: Arrhythmia is the most common cardiac complication after ischemic stroke. Connexin 40 is the staple component of gap junctions, which influences the propagation of cardiac electrical signals in the sinoatrial node. However, the role of connexin 40 in post-stroke arrhythmia remains unclear. METHODS: In this study, a permanent middle cerebral artery occlusion model was used to simulate the occurrence of an ischemic stroke. Subsequently, an electrocardiogram was utilized to record and assess variations in electrocardiogram measures. In addition, optical tissue clearing and whole-mount immunofluorescence staining were used to confirm the anatomical localization of the sinoatrial node, and the sinoatrial node tissue was collected for RNA sequencing to screen for potential pathological mechanisms. Lastly, the rAAV9-Gja5 virus was injected with ultrasound guidance into the heart to increase Cx40 expression in the sinoatrial node. RESULTS: We demonstrated that the mice suffering from a permanent middle cerebral artery occlusion displayed significant arrhythmia, including atrial fibrillation, premature ventricular contractions, atrioventricular block, and abnormal electrocardiogram parameters. Of note, we observed a decrease in connexin 40 expression within the sinoatrial node after the ischemic stroke via RNA sequencing and western blot. Furthermore, rAAV9-Gja5 treatment ameliorated the occurrence of arrhythmia following stroke. CONCLUSIONS: In conclusion, decreased connexin 40 expression in the sinoatrial node contributed to the ischemic stroke-induced cardiac arrhythmia. Therefore, enhancing connexin 40 expression holds promise as a potential therapeutic approach for ischemic stroke-induced arrhythmia.

Decreased structural pathways mediating functional connectivity in obstructive sleep apnea.

BACKGROUND: Obstructive sleep apnea (OSA) is a common sleep breathing disorder that is often accompanied by changes in structural connectivity (SC) and functional connectivity (FC). However, the current understanding of the interaction between SC and FC in OSA is still limited. METHODS: The aim of this study is to integrate complementary neuroimaging modalities into a unified framework using multi-layer network analysis methods and to reveal their complex interrelationships. We introduce a new graph metric called SC-FC bandwidth, which measures the throughput of SC mediating FC in a multi-layer network. The bandwidth differences between two groups are evaluated using the network-based statistics (NBS) method. Additionally, we traced and analyzed the SC pathways corresponding to the abnormal bandwidth. RESULTS: In both the healthy control and patients with OSA, the majority offunctionally synchronized nodes were connected via SC paths of length 2. With the NBS method, we observed significantly lower bandwidth between the right Posterior cingulate gyrus and right Cuneus, bilateral Middle frontal gyrus, bilateral Gyrus rectus in OSA patients. By tracing the high-proportion SC pathways, it was found that OSA patients typically exhibit a decrease in direct SC-FC, SC-FC triangles, and SC-FC quads intra- and inter-networks. CONCLUSION: Complex interrelationship changes have been observed between the SC and FC in patients with OSA, which might leads to abnormal information transmission and communication in the brain network.

Automated Diagnosis of Major Depressive Disorder With Multi-Modal MRIs Based on Contrastive Learning: A Few-Shot Study.

Depression ranks among the most prevalent mood-related psychiatric disorders. Existing clinical diagnostic approaches relying on scale interviews are susceptible to individual and environmental variations. In contrast, the integration of neuroimaging techniques and computer science has provided compelling evidence for the quantitative assessment of major depressive disorder (MDD). However, one of the major challenges in computer-aided diagnosis of MDD is to automatically and effectively mine the complementary cross-modal information from limited datasets. In this study, we proposed a few-shot learning framework that integrates multi-modal MRI data based on contrastive learning. In the upstream task, it is designed to extract knowledge from heterogeneous data. Subsequently, the downstream task is dedicated to transferring the acquired knowledge to the target dataset, where a hierarchical fusion paradigm is also designed to integrate features across inter- and intra-modalities. Lastly, the proposed model was evaluated on a set of multi-modal clinical data, achieving average scores of 73.52% and 73.09% for accuracy and AUC, respectively. Our findings also reveal that the brain regions within the default mode network and cerebellum play a crucial role in the diagnosis, which provides further direction in exploring reproducible biomarkers for MDD diagnosis.

Effects of second language acquisition on brain functional networks at different developmental stages.

Previous studies have shown that language acquisition influences both the structure and function of the brain. However, whether the acquisition of a second language at different periods of life alters functional network organization in different ways remains unclear. Here, functional magnetic resonance imaging data from 27 English-speaking monolingual controls and 52 Spanish-English bilingual individuals, including 22 early bilinguals who began learning a second language before the age of ten and 30 late bilinguals who started learning a second language at age fourteen or later, were collected from the OpenNeuro database. Topological metrics of resting-state functional networks, including small-world attributes, network efficiency, and rich- and diverse-club regions, that characterize functional integration and segregation of the networks were computed via a graph theoretical approach. The results showed obvious increases in network efficiency in early bilinguals and late bilinguals relative to the monolingual controls; for example, the global efficiency of late bilinguals and early bilinguals was improved relative to that of monolingual controls, and the local efficiency of early bilinguals occupied an intermediate position between that of late bilinguals and monolingual controls. Obvious increases in rich-club and diverse-club functional connectivity were observed in the bilinguals relative to the monolingual controls. Three network metrics were positively correlated with Spanish proficiency test scores. These findings demonstrated that early and late acquisition of a second language had different impacts on the functional networks of the brain.

Rich Club Reorganization in Nurses Before and After the Onset of Occupational Burnout: A Longitudinal MRI Study.

BACKGROUND: Studies on potential disruptions in rich club structure in nursing staff with occupational burnout are lacking. Moreover, existing studies on nurses with burnout are limited by their cross-sectional design. PURPOSE: To investigate rich club reorganization in nursing staff before and after the onset of burnout and the underlying impact of anatomical distance on such reconfiguration. STUDY TYPE: Prospective, longitudinal. POPULATION: Thirty-nine hospital nurses ( 23.67 ± 1.03 $$ 23.67\pm 1.03 $$ years old at baseline, 24.67 ± 1.03 $$ 24.67\pm 1.03 $$ years old at a follow-up within 1.5 years, 38 female). FIELD STRENGTH/SEQUENCE: Magnetization-prepared rapid gradient-echo and gradient-echo echo-planar imaging sequences at 3.0 T. ASSESSMENT: The Maslach Burnout Inventory and Symptom Check-List 90 testing were acquired at each MRI scan. Rich club structure was assessed at baseline and follow-up to determine whether longitudinal changes were related to burnout and to changes in connectivities with different anatomical distances (short-, mid-, and long range). STATISTICAL TESTS: Chi-square, paired-samples t, two-sample t, Mann-Whitney U tests, network-based statistic, Spearman correlation analysis, and partial least squares regression analysis. Significance level: Bonferroni-corrected P < 0.05 $$ P<0.05 $$ . RESULTS: In nurses who developed burnout: 1) Strengths of rich club, feeder, local, short-, mid-, and long-range connectivities were significantly decreased at follow-up compared with baseline. 2) At follow-up, strengths of above connectivities and that between A5m.R and dlPu.L were significantly correlated with emotional exhaustion (r ranges from -0.57 to -0.73) and anxiety scores (r = -0.56), respectively. 3) Longitudinal change (follow-up minus baseline) in connectivity strength between A5m.R and dlPu.L reflected change in emotional exhaustion score (r = 0.87). Longitudinal changes in strength of connectivities mainly involving parietal lobe were significantly decreased in nurses who developed burnout compared with those who did not. DATA CONCLUSION: In nurses after the onset of burnout, rich club reorganization corresponded to significant reductions in strength of connectivities with different anatomical distances. LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY: Stage 2.

Aberrant dynamic functional connectivity of thalamocortical circuitry in major depressive disorder. / é‡åº¦æŠ‘éƒéšœç¢æ‚£è€ ä¸˜è„‘çš®å±‚çŽ¯è·¯çš„åŠ¨æ€åŠŸèƒ½è¿žæŽ¥å¼‚å¸¸.

Thalamocortical circuitry has a substantial impact on emotion and cognition. Previous studies have demonstrated alterations in thalamocortical functional connectivity (FC), characterized by region-dependent hypo- or hyper-connectivity, among individuals with major depressive disorder (MDD). However, the dynamical reconfiguration of the thalamocortical system over time and potential abnormalities in dynamic thalamocortical connectivity associated with MDD remain unclear. Hence, we analyzed dynamic FC (dFC) between ten thalamic subregions and seven cortical subnetworks from resting-state functional magnetic resonance images of 48 patients with MDD and 57 healthy controls (HCs) to investigate time-varying changes in thalamocortical FC in patients with MDD. Moreover, dynamic laterality analysis was conducted to examine the changes in functional lateralization of the thalamocortical system over time. Correlations between the dynamic measures of thalamocortical FC and clinical assessment were also calculated. We identified four dynamic states of thalamocortical circuitry wherein patients with MDD exhibited decreased fractional time and reduced transitions within a negative connectivity state that showed strong correlations with primary cortical networks, compared with the HCs. In addition, MDD patients also exhibited increased fluctuations in functional laterality in the thalamocortical system across the scan duration. The thalamo-subnetwork analysis unveiled abnormal dFC variability involving higher-order cortical networks in the MDD cohort. Significant correlations were found between increased dFC variability with dorsal attention and default mode networks and the severity of symptoms. Our study comprehensively investigated the pattern of alteration of the thalamocortical dFC in MDD patients. The heterogeneous alterations of dFC between the thalamus and both primary and higher-order cortical networks may help characterize the deficits of sensory and cognitive processing in MDD.

Improving brain age prediction with anatomical feature attention-enhanced 3D-CNN.

Currently, significant progress has been made in predicting brain age from structural Magnetic Resonance Imaging (sMRI) data using deep learning techniques. However, despite the valuable structural information they contain, the traditional engineering features known as anatomical features have been largely overlooked in this context. To address this issue, we propose an attention-based network design that integrates anatomical and deep convolutional features, leveraging an anatomical feature attention (AFA) module to effectively capture salient anatomical features. In addition, we introduce a fully convolutional network, which simplifies the extraction of deep convolutional features and overcomes the high computational memory requirements associated with deep learning. Our approach outperforms several widely-used models on eight publicly available datasets (n = 2501), with a mean absolute error (MAE) of 2.20 years in predicting brain age. Comparisons with deep learning models lacking the AFA module demonstrate that our fusion model effectively improves overall performance. These findings provide a promising approach for combining anatomical and deep convolutional features from sMRI data to predict brain age, with potential applications in clinical diagnosis and treatment, particularly for populations with age-related cognitive decline or neurological disorders.

Preliminary study on the role of the CSMD2 gene in bladder cancer.

Background: CSMD2 has been reported as a potential prognostic factor in several cancers. However, whether CSMD2 affects bladder cancer (BC) remains unclear. Methods: Public data were obtained from the TCGA (https://cancergenome.nih.gov) databases. CSMD2expression and its prognostic value were analyzed using bioinformatics methods. CSMD2 mRNA level in patients with BC and BC cell lines was evaluated via quantitative reverse transcriptase polymerase chain reaction. CSMD2 protein level in patients with BC was evaluated via immunohistochemistry. BC cell lines T24 and UMUC-3 were selected for loss-of-function assays targeting CSMD2. Cell viability was determined by CCK8 and clone formation experiments. Cell migration and invasion were evaluated using Transwell assays. Furthermore, the transcriptome of UMUC-3 with CSMD2 knockdown was sequenced to analyze potential signaling network pathways. Finally, the TIMER2.0 database was employed to identify the correlation between CSMD2 and immune cells in the tumor microenvironment. Results: CSMD2 expression was up-regulated in BC tissues compared to adjacent tissues. High CSMD2 expression was associated with poor survival and could serve as an independent predictor for survival in patients with BC. Furthermore, down-regulation of CSMD2 notably restrained the viability, migration, and invasion abilities of T24 and UMUC-3 cells. Moreover, transcriptomic sequencing after CSMD2 knockdown in UMUC-3 cells revealed its involvement in the regulation of the malignant phenotype in BC. Finally, public databases suggest a connection between CSMD2 and immune cell infiltration in BC. Conclusions: These findings suggest that CSMD2 may promote proliferation and tumorigenicity, and could represent a potential target for improving the prognosis of BC.

Fine-grained features characterize hippocampal and amygdaloid change pattern in Parkinson's disease and discriminate cognitive-deficit subtype.

AIMS: To extract vertex-wise features of the hippocampus and amygdala in Parkinson's disease (PD) with mild cognitive impairment (MCI) and normal cognition (NC) and further evaluate their discriminatory efficacy. METHODS: High-resolution 3D-T1 data were collected from 68 PD-MCI, 211 PD-NC, and 100 matched healthy controls (HC). Surface geometric features were captured using surface conformal representation, and surfaces were registered to a common template using fluid registration. The statistical tests were performed to detect differences between groups. The disease-discriminatory ability of features was also tested in the ensemble classifiers. RESULTS: The amygdala, not the hippocampus, showed significant overall differences among the groups. Compared with PD-NC, the right amygdala in MCI patients showed expansion (anterior cortical, anterior amygdaloid, and accessory basal areas) and atrophy (basolateral ventromedial area) subregions. There was notable atrophy in the right CA1 and hippocampal subiculum of PD-MCI. The accuracy of classifiers with multivariate morphometry statistics as features exceeded 85%. CONCLUSION: PD-MCI is associated with multiscale morphological changes in the amygdala, as well as subtle atrophy in the hippocampus. These novel metrics demonstrated the potential to serve as biomarkers for PD-MCI diagnosis. Overall, these findings from this study help understand the role of subcortical structures in the neuropathological mechanisms of PD cognitive impairment.

Automatic Diagnosis of Major Depressive Disorder Using a High- and Low-Frequency Feature Fusion Framework.

Major Depressive Disorder (MDD) is a common mental illness resulting in immune disorders and even thoughts of suicidal behavior. Neuroimaging techniques serve as a quantitative tool for the assessment of MDD diagnosis. In the domain of computer-aided magnetic resonance imaging diagnosis, current research predominantly focuses on isolated local or global information, often neglecting the synergistic integration of multiple data sources, thus potentially overlooking valuable details. To address this issue, we proposed a diagnostic model for MDD that integrates high-frequency and low-frequency information using data from diffusion tensor imaging (DTI), structural magnetic resonance imaging (sMRI), and functional magnetic resonance imaging (fMRI). First, we designed a meta-low-frequency encoder (MLFE) and a meta-high-frequency encoder (MHFE) to extract the low-frequency and high-frequency feature information from DTI and sMRI, respectively. Then, we utilized a multilayer perceptron (MLP) to extract features from fMRI data. Following the feature cross-fusion, we designed the ensemble learning threshold voting method to determine the ultimate diagnosis for MDD. The model achieved accuracy, precision, specificity, F1-score, MCC, and AUC values of 0.724, 0.750, 0.882, 0.600, 0.421, and 0.667, respectively. This approach provides new research ideas for the diagnosis of MDD.

The α1 adrenoceptor antagonist prazosin potentiates morphine induced conditioned place preference in rats.

The norepinephrine (NE) system is involved in pathways that regulate morphine addiction. Here, we investigated the role of α1 adrenoceptor in the ventrolateral orbital cortex (VLO) of rats with repeated morphine treatment and underlying molecular mechanisms. The rewarding properties of morphine were assessed by the conditioned place preference (CPP) paradigm. Prazosin, an α1 adrenoceptor antagonist, was microinjected into the VLO. The expression of α1 adrenoceptor, p-CaMKII/CaMKII, CRTC1, BDNF and PSD95 in the VLO were determined by immunohistochemistry or western blotting. Neurotransmitter NE in the VLO and inflammatory factors in serum were detected separately through high-performance liquid chromatography and enzyme-linked immunosorbent assay. Our experimental results showed that repeated morphine administration induced stable CPP and prazosin promoted the morphine-induced CPP. Microinjection of prazosin in the VLO not only blocked the activity of α1 adrenoceptor, decreased CaMKII phosphorylation and CRTC1, which eventually resulted in a regression of synaptic plasticity-related proteins, but also was accompanied by significantly decreasing of NE in the VLO and increasing of inflammatory cytokines in peripheral blood. These findings suggested that prazosin potentiates the addictive effects of morphine. The effect of increased CPP through reducing α1 adrenoceptor and NE was associated with the CaMKII-CRTC1 pathway and synaptic plasticity-related proteins in the VLO and inflammatory cytokines in the peripheral blood. The NE system may therefore be an underlying therapeutic target in morphine addiction. Additionally, we believe that the clinical use of prazosin in hypertensive patients with morphine abuse may be a potential risk because of its reinforcing effect on addiction.