Cerebral arterial blood flow,attention,and executive and cognitive functions in depressed patients after acute hypertensive cerebral hemorrhage

BACKGROUND Intracerebral hemorrhage mainly occurs in middle-aged and elderly patients with hypertension,and surgery is currently the main treatment for hypertensive cerebral hemorrhage,but the bleeding caused by surgery will cause damage to the patient's nerve cells,resulting in cognitive and motor dysfunction,resulting in a decline in the patient's quality of life.AIM To investigate associations between cerebral arterial blood flow and executive and cognitive functions in depressed patients after acute hypertensive cerebral hemorrhage.METHODS Eighty-nine patients with depression after acute hypertensive cerebral hemorrhage who were admitted to our hospital between January 2019 and July 2021 were selected as the observation group,while 100 patients without depression who had acute hypertensive cerebral hemorrhage were selected as the control group.The attention span of the patients was assessed using the Paddle Pin Test while executive function was assessed using the Wisconsin Card Sorting Test(WCST)and cognitive function was assessed using the Montreal Cognitive Assessment Scale(MoCA).The Hamilton Depression Rating Scale(HAMD-24)was used to evaluate the severity of depression of involved patients.Cerebral arterial blood flow was measured in both groups.RESULTS The MoCA score,net scores I,II,III,IV,and the total net score of the scratch test in the observation group were significantly lower than those in the control group(P<0.05).Concurrently,the total number of responses,number of incorrect responses,number of persistent errors,and number of completed responses of the first classification in the WCST test were significantly higher in the observation group than those in the control group(P<0.05).Blood flow in the basilar artery,left middle cerebral artery,right middle cerebral artery,left anterior cerebral artery,and right anterior cerebral artery was significantly lower in the observation group than in the control group(P<0.05).The basilar artery,left middle cerebral artery,right middle cerebral artery,left anterior cerebral artery,and right anterior cerebral artery were positively correlated with the net and total net scores of each part of the Paddle Pin test and the MoCA score(P<0.05),and negatively correlated with each part of the WCST test(P<0.05).In the observation group,the post-treatment improvement was more prominent in the Paddle Pin test,WCST test,HAMD-24 score,and MoCA score compared with those in the pre-treatment period(P<0.05).Blood flow in the basilar artery,left middle cerebral artery,right middle cerebral artery,left anterior cerebral artery,and right anterior cerebral artery significantly improved in the observation group after treatment(P<0.05).CONCLUSION Impaired attention,and executive and cognitive functions are correlated with cerebral artery blood flow in patients with depression after acute hypertensive cerebral hemorrhage and warrant further study.

An Improved Solov2 Based on Attention Mechanism and Weighted Loss Function for Electrical Equipment Instance Segmentation

The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment,this paper uses the bottleneck attention module(BAM)attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation mode.Firstly,the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels,thereby improving the expression ability of the feature map;secondly,the weighted sum of CrossEntropy Loss and Dice loss is designed as the mask loss to improve the segmentation accuracy and robustness of the model;finally,the non-maximal suppression(NMS)algorithm to better handle the overlap problem in instance segmentation.Experimental results show that the proposed method achieves an average segmentation accuracy of mAP of 80.4% on three types of electrical equipment datasets,including transformers,insulators and voltage transformers,which improve the detection accuracy by more than 5.7% compared with the original Solov2 model.The segmentation model proposed can provide a focusing technical means for the intelligent management of power systems.

基于Coordinate Attention和空洞卷积的异物识别

在我国工厂的工业化生产中,带式运输机占有重要的地位,但是在其运输物料的过程中,常有木板、金属管、大型金属片等混入物料中,从而对带式运输机的传送带造成损毁,引起巨大的经济损失.为了检测出传送带上的不规则异物,设计了一种新的异物检测方法.针对传统异物检测方法中存在的对于图像特征提取能力不足以及网络感受野相对较小的问题,我们提出了一种基于coordinate attention和空洞卷积的单阶段异物识别方法.首先,网络利用coordinate attention机制,使网络更加关注图像的空间信息,并对图像中的重要特征进行了增强,增强了网络的性能;其次,在网络提取多尺度特征的部分,将原网络的静态卷积变为空洞卷积,有效减少了常规卷积造成的信息损失;除此之外,我们还使用了新的损失函数,进一步提高了网络的性能.实验结果证明,我们提出的网络能有效识别出传送带上的异物,较好地完成异物检测任务.

基于频空融合与3D-CNN-Attention的抑郁症识别

提出了一种基于频谱信息的三维特征构建方法,根据电极位置将每个通道的功率值排列成二维特征向量。将不同频段特征排列成三维积分特征张量,提取频域信息,同时,为了减少容积导体效应影响,利用功能连接将时序脑电(EEG)数据映射到空间脑功能网络,提取空间信息。通过对特征与目标类之间关系的分析,提出一种3D-CNN-Attention网络模型,在3D-CNN网络中加入Attention机制,以增强EEG特征学习能力。在公开数据集上的系列对比实验,结果表明基于3D-CNN-Attention网络框架的抑郁症检测性能优于其他方法,获得了最高为96.32%的准确率。本文方法能够为抑郁症检测提供一种有效的解决方案。

Two Stages Segmentation Algorithm of Breast Tumor in DCE-MRI Based on Multi-Scale Feature and Boundary Attention Mechanism

Nuclearmagnetic resonance imaging of breasts often presents complex backgrounds.Breast tumors exhibit varying sizes,uneven intensity,and indistinct boundaries.These characteristics can lead to challenges such as low accuracy and incorrect segmentation during tumor segmentation.Thus,we propose a two-stage breast tumor segmentation method leveraging multi-scale features and boundary attention mechanisms.Initially,the breast region of interest is extracted to isolate the breast area from surrounding tissues and organs.Subsequently,we devise a fusion network incorporatingmulti-scale features and boundary attentionmechanisms for breast tumor segmentation.We incorporate multi-scale parallel dilated convolution modules into the network,enhancing its capability to segment tumors of various sizes through multi-scale convolution and novel fusion techniques.Additionally,attention and boundary detection modules are included to augment the network’s capacity to locate tumors by capturing nonlocal dependencies in both spatial and channel domains.Furthermore,a hybrid loss function with boundary weight is employed to address sample class imbalance issues and enhance the network’s boundary maintenance capability through additional loss.Themethod was evaluated using breast data from 207 patients at RuijinHospital,resulting in a 6.64%increase in Dice similarity coefficient compared to the benchmarkU-Net.Experimental results demonstrate the superiority of the method over other segmentation techniques,with fewer model parameters.

Enhancement of Visual Attention by Color Revealed Using Electroencephalography

Attention constitutes a fundamental psychological feature guiding our mental effort toward specific objects, concurrent with processes such as memory, reasoning, and imagination. Visual attention, crucial for selecting surrounding information, often decreases in older adults and patients with cerebrovascular disorders. Effective methods to enhance attention are scarce. Here, we investigated whether color information influences visual attention and brain activity during task performance, utilizing EEG. We examined 13 healthy young adults (seven women and six men;mean age: 21.2 ± 0.58 years) using 19-electrode electroencephalograms to assess the impact of color information on visual attention. The Clinical Assessment for Attention cancellation test was conducted under the black, red, and blue color conditions. Wilcoxon’s signed-rank test was used to assess differences in task performance (task time and error) between conditions. Spearman’s rank correlation was utilized to examine the correlation in power levels between task performance and color conditions. Significant variations in total task errors were observed among color conditions. The black condition exhibited the highest error frequency (0.7 ± 0.9 times), followed by the red condition (0.5 ± 0.8 times), with the lowest error frequency occurring in the blue (0.2 ± 0.4 times) condition (black vs. red: P = 0.03;black vs. blue: P = 0.00;red vs. blue: P = 0.032). No time difference was observed. The black condition showed negative delta and high-gamma correlations in the central electrodes. The red condition revealed positive alpha and low-gamma correlations in the frontal and occipital areas. Although no correlations were observed in the blue condition, it enhanced attentional performance. Positive alpha and low-gamma waves might be crucial for spotting attentional errors in key areas. Our findings provide insights into the effects of color information on visual attention and potential neural correlates associated with attentional processes. In conclusion, our study implies a connection between color information and attentional task performance, with blue font associated with the most accurate performance.

Effect of non-pharmacological treatment on the full recovery of social functioning in patients with attention deficit hyperactivity disorder

BACKGROUND Long-term treatment of attention deficit/hyperactivity disorder(ADHD)is associated with adverse events,such as nausea and vomiting,dizziness,and sleep disturbances,and poor maintenance of late ADHD medication compromises treatment outcomes and prolongs the recovery of patients’social functioning.AIM To evaluate the effect of non-pharmacological treatment on the full recovery of social functioning in patients with ADHD.METHODS A total of 90 patients diagnosed with ADHD between May 2019 and August 2020 were included in the study and randomly assigned to either the pharmacological group(methylphenidate hydrochloride and tomoxetine hydrochloride)or the non-pharmacological group(parental training,behavior modification,sensory integration therapy,and sand tray therapy),with 45 cases in each group.Outcome measures included treatment compliance,Swanson,Nolan,and Pelham,Version IV(SNAP-IV)scores,Conners Parent Symptom Questionnaire(PSQ)scores,and Weiss Functional Impairment Rating Scale(WFIRS)scores.RESULTS The non-pharmacological interventions resulted in significantly higher compliance in patients(95.56%)compared with medication(71.11%)(P<0.05).However,no significant differences in SNAP-IV and PSQ scores,in addition to the learning/school,social activities,and adventure activities of the WFIRS scores were observed between the two groups(P>0.05).Patients with non-pharmacological interventions showed higher WFIRS scores for family,daily life skills,and self-concept than those in the pharmacological group(P<0.05).CONCLUSION Non-pharmacological interventions,in contrast to the potential risks of adverse events after longterm medication,improve patient treatment compliance,alleviate patients’behavioral symptoms of attention,impulsivity,and hyperactivity,and improve their cognitive ability,thereby improving family relationships and patient self-evaluation.

基于Attention机制的CNN-LSTM概率预测模型的股指预测

鉴于证券市场波动大预测难度高,文章基于encoder-decoder结构将Attention机制融入CNN-LSTM模型,利用Attention机制来捕捉不同时间点之间的数据依赖模式,提取长序列信息,并且在此基础上给出概率密度函数进行抽样预测,最终得出股票价格的点预测和区间预测。实验结果表明,融入Attention机制的CNN-LSTM概率预测模型从综合性能来看优于其他基准模型,能够对上证指数收盘价进行较高精度的多步预测。

Liver Tumor Segmentation Based on Multi-Scale and Self-Attention Mechanism

Liver cancer has the second highest incidence rate among all types of malignant tumors,and currently,its diagnosis heavily depends on doctors’manual labeling of CT scan images,a process that is time-consuming and susceptible to subjective errors.To address the aforementioned issues,we propose an automatic segmentation model for liver and tumors called Res2Swin Unet,which is based on the Unet architecture.The model combines Attention-Res2 and Swin Transformer modules for liver and tumor segmentation,respectively.Attention-Res2 merges multiple feature map parts with an Attention gate via skip connections,while Swin Transformer captures long-range dependencies and models the input globally.And the model uses deep supervision and a hybrid loss function for faster convergence.On the LiTS2017 dataset,it achieves better segmentation performance than other models,with an average Dice coefficient of 97.0%for liver segmentation and 81.2%for tumor segmentation.

Connectivity differences between adult male and female patients with attention deficit hyperactivity disorder according to resting-state functional MRI

Attention deficit hyperactivity disorder（ADHD） is a pervasive psychiatric disorder that affects both children and adults. Adult male and female patients with ADHD are differentially affected, but few studies have explored the differences. The purpose of this study was to quantify differences between adult male and female patients with ADHD based on neuroimaging and connectivity analysis. Resting-state functional magnetic resonance imaging scans were obtained and preprocessed in 82 patients. Group-wise differences between male and female patients were quantified using degree centrality for different brain regions. The medial-, middle-, and inferior-frontal gyrus, superior parietal lobule, precuneus, supramarginal gyrus, superior- and middle-temporal gyrus, middle occipital gyrus, and cuneus were identified as regions with significant group-wise differences. The identified regions were correlated with clinical scores reflecting depression and anxiety and significant correlations were found. Adult ADHD patients exhibit different levels of depression and anxiety depending on sex, and our study provides insight into how changes in brain circuitry might differentially impact male and female ADHD patients.

Age-related connectivity differences between attention deficit and hyperactivity disorder patients and typically developing subjects：a resting-state functional MRI study

Attention deficit and hyperactivity disorder（ADHD） is a disorder characterized by behavioral symptoms including hyperactivity/impulsivity among children,adolescents,and adults.These ADHD related symptoms are influenced by the complex interaction of brain networks which were under explored.We explored age-related brain network differences between ADHD patients and typically developing（TD） subjects using resting state f MRI（rs-f MRI） for three age groups of children,adolescents,and adults.We collected rs-f MRI data from 184 individuals（27 ADHD children and 31 TD children;32 ADHD adolescents and 32 TD adolescents;and 31 ADHD adults and 31 TD adults）.The Brainnetome Atlas was used to define nodes in the network analysis.We compared three age groups of ADHD and TD subjects to identify the distinct regions that could explain age-related brain network differences based on degree centrality,a well-known measure of nodal centrality.The left middle temporal gyrus showed significant interaction effects between disease status（i.e.,ADHD or TD） and age（i.e.,child,adolescent,or adult）（P 0.001）.Additional regions were identified at a relaxed threshold（P 0.05）.Many of the identified regions（the left inferior frontal gyrus,the left middle temporal gyrus,and the left insular gyrus） were related to cognitive function.The results of our study suggest that aberrant development in cognitive brain regions might be associated with age-related brain network changes in ADHD patients.These findings contribute to better understand how brain function influences the symptoms of ADHD.

Attention-Deficit/Hyperactivity Disorder in Adults with High-Functioning Pervasive Developmental Disorders in Japan

Aims: This study was designed to verify the proportion of Japanese adults with pervasive developmental disorder (PDD) who met the diagnostic criteria (other than E) for attention-deficit/hyperactivity disorder (ADHD) in the Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition, Text Revision (DSM-IV-TR). Furthermore, we examined to what extent adults with PDD think that they exhibit ADHD symptoms. Methods: We developed an original Japanese self-report questionnaire to determine the presence or absence of 18 symptoms from the diagnostic criteria for ADHD in the DSM-IV-TR. We administered the questionnaire to 64 adults with high-functioning PDD (45 men and 19 women) and 21 adults with ADHD (10 men and 11 women), aged 18 to 59 years, with a full-scale intelligence quotient ≥75. Target patients were evaluated for ADHD by their psychiatrists. Results: Twenty-nine (45.3%) adults with PDD also had ADHD. The percentage of these adults who had over six perceived inattention symptoms from the DSM-IV-TR was 96.6%. The percentage of these adults who had over six perceived hyperactivity-impulsivity symptoms was 65.5%. Thirty-five (55.6%) adults with PDD responded that they were aware of having ADHD symptoms at the level of the relevant diagnostic criteria. Conclusions: The present study is the first to examine the frequency of objective and perceived ADHD symptoms in adults with PDD in Japan. Our results show that both objective and perceived ADHD symptoms frequently appear in a large number of adults with PDD. This suggests that it is necessary to attend to concomitant ADHD symptoms in the medical care of adults with PDD.

基于CNN-Attention-BP的降水发生预测研究

在综合分析降水统计预测模型特点的基础上,提出一种基于Attention机制、卷积神经网络(CNN)和BP神经网络的CNN-Attention-BP组合模型,并对1961—2020年不同气候类型的长春站、白城站、延吉站夏季降水进行实证分析.首先,运用卷积神经网络对6—8月20—次日20时降水量、平均气压、平均风速、平均气温和平均相对湿度进行特征学习,利用Attention机制来确定气象影响因素对降水预测的权重;然后,使用BP神经网络进行降水发生预测,选用准确率、交叉熵损失函数和F1-score来综合评价CNN-Attention-BP组合模型的性能.最后,将单一的支持向量机、多层感知机和卷积神经网络模型与组合模型进行比较分析.结果表明,CNN-Attention-BP组合模型具有自主学习和关注更重要信息的特征,能够有效提高吉林省夏季降水发生模型的预测能力,在样本越均衡、降水频率越接近于0.5的站点,预测精度越高,准确率最高可达88.4%.CNN-Attention-BP组合模型的准确率相较于其他单一模型最高可以提高近17个百分点.

PINPOINT SOURCE LOCALIZATION FOR OCULAR NONSELECTIVE ATTENTION WITH COMBINATION OF ERP AND fNIRI MEASUREMENTS

Compared with event-related potential(ERP)which is widely used in psychology research,functional near-infrared imaging(fNIRI)is a new technique providing hemodynamic information related to brain activity,except for electrophysiological signals.Here,we use both these techniques to study ocular attention.We conducted a series of experiments with a classic paradigm of ocular nonselective attention,and monitored responses with fNIRI and ERP respectively.The results showed that fNIRI measured brain activations in the left prefrontal lobe,while ERPs showed activation in frontal lobe.More importantly,only with the combination measurements of fNIRI and ERP,we were then able to find the pinpoint source of ocular nonselective attention,which is in the left and upper corner in Brodmann area 10.These results demonstrated that fNIRI is a reliable technique in psychology,and the combination of fNIRI and ERP can be promising to reveal more information in the research of brain mechanism.

Sustained attention in psychosis:Neuroimaging findings

To provide a systematic review of scientific literatureon functional magnetic resonance imaging(fMRI) stud-ies on sustained attention in psychosis. We searchedPubMed to identify fMRI studies pertaining sustainedattention in both affective and non-affective psycho-sis. Only studies conducted on adult patients using asustained attention task during fMRI scanning wereincluded in the final review. The search was conductedon September 10 th, 2013. 15 fMRI studies met our in-clusion criteria: 12 studies were focused on Schizophre-nia and 3 on Bipolar Disorder Type Ⅰ(BDI). Only halfof the Schizophrenia studies and two of the BDI stud-ies reported behavioral abnormalities, but all of themevidenced significant functional differences in brain re-gions related to the sustained attention system. Alteredfunctioning of the insula was found in both Schizophre-nia and BDI, and therefore proposed as a candidate trait marker for psychosis in general. On the other hand, other brain regions were differently impaired in affective and non-affective psychosis: alterations of cingulate cortex and thalamus seemed to be more common in Schizophrenia and amygdala dysfunctions in BDI. Neural correlates of sustained attention seem to be of great interest in the study of psychosis, highlight-ing differences and similarities between Schizophrenia and BDI.

Multi-Scale Attention-Based Deep Neural Network for Brain Disease Diagnosis

Whole brain functional connectivity(FC)patterns obtained from resting-state functional magnetic resonance imaging(rs-fMRI)have been widely used in the diagnosis of brain disorders such as autism spectrum disorder(ASD).Recently,an increasing number of studies have focused on employing deep learning techniques to analyze FC patterns for brain disease classification.However,the high dimensionality of the FC features and the interpretation of deep learning results are issues that need to be addressed in the FC-based brain disease classification.In this paper,we proposed a multi-scale attention-based deep neural network(MSA-DNN)model to classify FC patterns for the ASD diagnosis.The model was implemented by adding a flexible multi-scale attention(MSA)module to the auto-encoder based backbone DNN,which can extract multi-scale features of the FC patterns and change the level of attention for different FCs by continuous learning.Our model will reinforce the weights of important FC features while suppress the unimportant FCs to ensure the sparsity of the model weights and enhance the model interpretability.We performed systematic experiments on the large multi-sites ASD dataset with both ten-fold and leaveone-site-out cross-validations.Results showed that our model outperformed classical methods in brain disease classification and revealed robust intersite prediction performance.We also localized important FC features and brain regions associated with ASD classification.Overall,our study further promotes the biomarker detection and computer-aided classification for ASD diagnosis,and the proposed MSA module is flexible and easy to implement in other classification networks.

基于CNN-Attention算法的精神分裂症分类

人体复杂的生理活动是由大脑各区域间相互配合共同完成的,且脑区间的这种联系是随时间不断变化的,利用脑区之间动态功能连接和静态功能连接进行分类有助于提升分类模型的分类精度,同时揭示脑疾病的致病原因。文中使用静态与动态功能连接两种特征作为分类模型的输入,采用加入卷积神经网络和注意力机制的深度学习模型(CNN-Attention)对精神分裂症患者和健康被试进行分类。结果表明,相较于单独使用静态功能连接或动态功能连接,二者结合使用可以有效提高深度学习模型的分类精度,且所提出的深度学习模型拥有较高的分类精度(79.11%)。同时,找出了静态和动态功能连接中最具鉴别力的特征,为精神分裂症患者的临床诊断提供生物学依据。

A Preliminary Near-Infrared Spectroscopy Study in Adolescent and Adult Patients with Attention-Deficit/Hyperactivity Disorder Symptoms

Prefrontal dysfunction in patients with attention-deficit/hyperactivity disorder (AD/HD) has been repeatedly detected on a behavioral level, and various brain-imaging studies have elucidated the pathophysiology of AD/HD. Recent advances in near-infrared spectroscopy (NIRS) have enabled noninvasive investigations of brain function in various mental disorders, especially major depression, schizophrenia, and bipolar disorder. The objective of this preliminary study was to use NIRS to evaluate changes in frontal lobe blood flow in post childhood or adult patients with AD/HD symptoms. The subjects included five patients with a range of mental disorders and AD/HD symptoms, and a matched (age, sex, and dominant hand) control group of five healthy subjects. We compared the changes in cerebral blood flow during verbal fluency tasks between the two groups. The duration of the elevated oxygenated hemoglobin was notably shorter in the AD/HD group than that in the healthy control group. We suggest that the shorter elevation durations of oxygenated hemoglobin concentrations might be a biological indicator for post childhood or adult AD/HD or of impaired executive functioning.

改进YOLOv5模型在自然环境下柑橘识别的应用

在复杂的自然环境中绿色柑橘生长形态各异,颜色与背景色相近,为有效识别绿色柑橘,提出一种基于混合注意力机制并改进YOLOv5模型的柑橘识别方法。首先,改进YOLOv5的网络结构,在主干网络中添加混合注意力机制,即在主干网络中的第2层嵌入SE(squeeze and excitation)注意力,第11层嵌入CA(coordinate attention)注意力;其次,改进网络模型特征融合结构,将YOLOv5模型Concat特征融合操作的下层分支放在模型C3模块之前,再与另一条上层分支进行特征融合;最后,改进模型分类损失函数,将YOLOv5模型的分类损失函数改成Varifocal Loss函数,加强绿色柑橘特征信息的提取,提高绿色柑橘检测精度。根据自然环境和柑橘自身的特点,对自建数据集进行分类,设计3组不同分类场景下柑橘的对比试验以验证其有效性。试验结果表明,改进后的YOLOv5-SC模型准确率为91.74%,平均精度为95.09%,F1为89.56%,在自然环境下对绿色柑橘的识别具有更高的准确率和更好的鲁棒性,为绿色水果智能采摘提供技术支持。

复杂战场环境下改进YOLOv5军事目标识别算法研究

复杂战场环境下军事目标识别技术是提升战场情报获取能力的基础和关键。针对当前军事目标识别技术在复杂战场环境下漏检误检率高、实时性差等问题,提出一种基于改进YOLOv5模型的PB-YOLO军事目标识别算法。将改进的目标识别算法对于陆战场军事单元的识别锚框进行重新聚类,以提升模型对于目标大小适应度,加速模型收敛;采用通道-空间并行注意力机制,增加模型对复杂战场环境下目标特征信息与位置信息关注度;在特征融合网络部分使用BiFPN以提升模型对于特征的融合能力与速度;采用Alpha_IoU损失函数加速模型收敛,解决当真实框与预测框重合时IoU计算退化问题。实验结果表明,在自建军事目标数据集下,改进算法与主流目标识别算法相比,在保证模型空间复杂度的同时,mAP值达到了90.17%。消融实验对比结果表明,改进后网络较原模型精度提升11.57%,具有较好的识别性能,能够为战场情报获取提供有效的技术支撑。