Neuroscience informatics最新文献

{"title":"Multiclass semantic segmentation mediated neuropathological readout in Parkinson's disease","authors":"Hosein Barzekar ,&nbsp;Hai Ngu ,&nbsp;Han Hui Lin ,&nbsp;Mohsen Hejrati ,&nbsp;Steven Ray Valdespino ,&nbsp;Sarah Chu ,&nbsp;Baris Bingol ,&nbsp;Somaye Hashemifar ,&nbsp;Soumitra Ghosh","doi":"10.1016/j.neuri.2023.100131","DOIUrl":"https://doi.org/10.1016/j.neuri.2023.100131","url":null,"abstract":"<div><p>Automated segmentation of anatomical sub-regions with high precision has become a necessity to enable the quantification and characterization of cells/ tissues in histology images. An automated model to do this task is currently unavailable. One area of the brain which requires precise sub-region segmentation and downstream analysis is Substantia Nigra (SN). The loss of dopaminergic (DA) neurons in SN is the primary endpoint for majority of Parkinson's disease (PD) preclinical studies. The scientists rely on manually segmenting anatomical sub-regions of the brain which is extremely time-consuming and prone to labeler-dependent bias. In this study, we employed a UNet-based architecture to segment two sub-regions of SN-dorsal tier of substantia nigra pars compacta (SNCD) and reticulata (SNr). We compared model performance with various combinations of encoders, image sizes and sample selection techniques. The model is trained on approximately one thousand annotated 2D brain images stained with Nissl/ Haematoxylin and Tyrosine Hydroxylase enzyme (TH, indicator of dopaminergic neuron viability). The framework's output are: segmentation of SNr and SNCD irrespective of the tissue staining, quantitative readout for TH intensity indicating DA health status in the segmented regions. With the availability of training data, this model can be expanded to other 2D sub-region segmentation tasks. The shorter turnaround time, high accuracy and unbiased data output of this model will fulfill the ever increasing demands of data analysis in PD preclinical research.</p></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"3 2","pages":"Article 100131"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49700294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gene set enrichment analysis indicates convergence in the mTOR signalling pathway between syndromic and non-syndromic autism","authors":"Victor Gustavo Oliveira Evangelho ,&nbsp;Murilo Lamim Bello ,&nbsp;Helena Carla Castro ,&nbsp;Marcia Rodrigues Amorim","doi":"10.1016/j.neuri.2023.100119","DOIUrl":"10.1016/j.neuri.2023.100119","url":null,"abstract":"<div><p>Autism is a developmental disorder that affects around 62.1 million people globally. Estimates of its prevalence have been on the rise. Recent research suggests that in the United States alone, the cost of caring for individuals with autism could reach $461 billion by 2025, including medical expenses. Autism results from a combination of genetic and environmental factors, and molecular diagnosis can often be challenging. Therefore, there is a need for more reliable biomarkers to assist in clinical evaluation. Here, we employed a bioinformatics technique, Gene Set Enrichment Analysis (GSEA), that allows for the evaluation of whether specific genes associated with autism are related to common biological pathways and particular molecular processes using data extracted from genetic biobanks. Thus, it was possible to validate 910 genes related to autism by means of GSEA. The generated data indicated genetic convergence in a molecular pathway, suggesting that the disordered activation of the RAS-MAPK and PI3K-AKT signaling cascades converges in the mTOR pathway. Cell typification in silico indicated high expression in striated neurons, type D1 (p=5,947e-04) and type D2 (p=1,292e-05). In conclusion, our molecular pathway data can be used to assess, using computer modeling, whether new drug candidates for treating autism interact with proteins involved in the mTOR pathway, thus optimizing the screening of new drugs. In addition, with the evidence of such biomarkers and the development of easily accessible laboratory tests, in the future, the early clinical diagnosis of autism could be significantly improved.</p></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"3 2","pages":"Article 100119"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48647349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of breathing pathway and musical features on the processing of music induced emotions","authors":"Mohammad Javad Mollakazemi,&nbsp;Dibyajyoti Biswal,&nbsp;Brooke Place,&nbsp;Abhijit Patwardhan","doi":"10.1016/j.neuri.2023.100117","DOIUrl":"10.1016/j.neuri.2023.100117","url":null,"abstract":"<div><p>The effects of the breathing pathway (nasal vs. oral) on the processing of emotions are not yet well-understood although there is evidence of respiratory entrainment of local field potential activity in human limbic networks and the importance of nasal airflow in shaping this entrainment. In this study, we compared the degree of various emotions triggered by different pieces of music during oral breathing (OB) and nasal breathing (NB). In addition, correlation of different musical features with emotions was investigated. Our results showed that during NB, subjects found songs more relaxing (p = 0.00013) and happier (p = 0.069), and they felt more arousal states from songs (p = 0.036) when compared to the same songs during OB, while during OB subjects' average rating for more negative emotions was higher when compared to NB (NS). During both OB and NB, we observed that the consonance degree of songs had significantly high positive correlations with positive emotions (valence: p &lt; 0.01, happy: p &lt; 0.05, relaxed: NB: p &lt; 0.05, OB: NS) and significantly high negative correlations with negative emotions (angry: p &lt; 0.001, fear: p &lt; 0.05, frustrated: NB: p &lt; 0.001, OB: NS), while the higher complexity rate of songs had a positive correlation with negative emotions (fear: p &lt; 0.01, sad &lt; 0.05, frustrated: p &lt; 0.05, angry: OB: p &lt; 0.05, NB: NS) and negative correlations with positive emotions (happy: p &lt; 0.05, relaxed: p &lt; 0.05, valence: p &lt; 0.05).</p></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"3 1","pages":"Article 100117"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48598181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transvenous embolization of dural arteriovenous fistula of the cavernous sinus by identifying the orifice of the occluded inferior petrosal sinus through the angle of the microguidewire","authors":"Huachen Zhang,&nbsp;Shikai Liang,&nbsp;Xianli Lv","doi":"10.1016/j.neuri.2023.100120","DOIUrl":"10.1016/j.neuri.2023.100120","url":null,"abstract":"<div><h3>Objective</h3><p>To describe that the angle of the microguidwire on lateral projection under fluoroscopic image is a prediction of cannulation of the occluded inferior petrosal sinus in the transvenous embolization of cavernous sinus dural fistulas.</p></div><div><h3>Methods</h3><p>From January 2018 through January 2021, 12 cavernous sinus dural fistulas with ipsilateral inferior petrosal sinus occlusion identified in 12 consecutive patients were cured by cannulation of the occluded ipsilateral inferior petrosal sinus. Clinical, radiologic and procedure data of the 12 patients were retrospectively reviewed. The angle of microguidewire between on lateral projection under fluoroscopic image between the inferior petrosal sinus and the internal jugular vein was measured.</p></div><div><h3>Results</h3><p>In the 12 patients, access via the occluded ipsilateral inferior petrosal sinus was primarily attempted as the transvenous approach. During the procedure, the angle of microguidwire on lateral projection under fluoroscopic image between the inferior petrosal sinus and the internal jugular vein was 117°±7°, which is very useful to confirm the cannulation of the occluded inferior petrosal sinus. Complete occlusion was achieved in all fistulas, with no procedure-related morbidity or mortality. Postprocedural symptom was improved in all patients.</p></div><div><h3>Conclusion</h3><p>Cannulation of an occluded inferior petrosal sinus is possible and reasonable as an initial access attempt for cavernous sinus dural fistulas. The angle of microguidwire on the lateral projection under fluoroscopic image can help to confirm the orifice of the occluded inferior petrosal sinus.</p></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"3 1","pages":"Article 100120"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47473602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and implementation of auto encoder based bio medical signal transmission to optimize power using convolution neural network","authors":"K.N. Sunil Kumar ,&nbsp;G.B. Arjun Kumar ,&nbsp;Ravi Gatti ,&nbsp;S. Santosh Kumar ,&nbsp;Darshan A. Bhyratae ,&nbsp;Satyasrikanth Palle","doi":"10.1016/j.neuri.2023.100121","DOIUrl":"10.1016/j.neuri.2023.100121","url":null,"abstract":"<div><p>Real-time biomedical signal transmission requires IoTs and cloud infrastructure. In this work, we investigate feasible lossy compression approaches that leverage the temporal and spatial dynamics of the signal along with current algorithms based on Compressive Sensing (CS) that use signal correlation in space and time. These techniques are altered so they may be applied efficiently to a distributed WSN. To achieve this, we proposed Convolution Neural Network (CNN) based Optimized Bio-Signals Compression using Auto-Encoder (BCAE), which integrates auto-encoder and feature selection. Instead of using the entire signal as an input, we encode the main part of the signal and send it to the desired location. Reconstruction decrypts without signal loss. Realistic aggregation and data collection procedures can improve data reconstruction accuracy. We compare various techniques' reconstruction error vs. energy requirements. The simulation results reveal that packet loss is 40% and data reconstruction error is 5%. Data forwarding time is lowered by 16.36%, while network energy usage is cut by 23.59%. The proposed method outperforms with existing techniques and the results are validated using MATLAB.</p></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"3 1","pages":"Article 100121"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46361474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantitative EEG features and machine learning classifiers for eye-blink artifact detection: A comparative study","authors":"Maliha Rashida,&nbsp;Mohammad Ashfak Habib","doi":"10.1016/j.neuri.2022.100115","DOIUrl":"10.1016/j.neuri.2022.100115","url":null,"abstract":"<div><p>Ocular artifact, namely eye-blink artifact, is an inevitable and one of the most destructive noises of EEG signals. Many solutions of detecting the eye-blink artifact were proposed. Different subsets of EEG features and Machine Learning (ML) classifiers were used for this purpose. But no comprehensive comparison of these features and ML classifiers was presented. This paper presents the comparison of twelve EEG features and five ML classifiers, commonly used in existing studies for the detection of eye-blink artifacts. An EEG dataset, containing 2958 epochs of eye-blink, non-eye-blink, and eye-blink-like (non-eye-blink) EEG activities, is used in this study. The performance of each feature and classifier has been measured using accuracy, precision, recall, and f1-score. Experimental results reveal that scalp topography is the most potential among the selected features in detecting eye-blink artifacts. The best performing classifier is Artificial Neural Network (ANN) among the five classifiers. The combination of scalp topography and ANN classifier performed as the most powerful feature-classifier combination. However, it is expected that the findings of this study will help the future researchers to select appropriate features and classifiers in building eye-blink artifact detection models.</p></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"3 1","pages":"Article 100115"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45786077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predictive value of clot imaging in acute ischemic stroke: A systematic review of artificial intelligence and conventional studies","authors":"Daniela Dumitriu LaGrange ,&nbsp;Jeremy Hofmeister ,&nbsp;Andrea Rosi ,&nbsp;Maria Isabel Vargas ,&nbsp;Isabel Wanke ,&nbsp;Paolo Machi ,&nbsp;Karl-Olof Lövblad","doi":"10.1016/j.neuri.2022.100114","DOIUrl":"10.1016/j.neuri.2022.100114","url":null,"abstract":"<div><p>The neuroimaging signs of the clot in acute ischemic stroke are relevant for clot biology and its response to treatment. The diagnostic and predictive value of clot imaging is confirmed by conventional studies and emerges as a topic of interest for artificial intelligence (AI) developments. We performed a systematic review to evaluate the state of the art of AI in clot imaging, how far AI is from becoming clinically beneficial, and what are the perspectives to consider for further developments. In parallel, the review is examining the evidence brought by conventional studies concerning the relevance of clot imaging, from 2019 to August 2022. The automatic detection and segmentation of the clot are the most important advances towards AI implementation in the clinic. Predictive radiomics models require further exploration and methods optimization. Future AI approaches could consider conventional clot imaging characteristics and patient specific vascular features as variables for model development.</p></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"3 1","pages":"Article 100114"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48498180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A connectome-based deep learning approach for Early MCI and MCI detection using structural brain networks","authors":"Shayan Kolahkaj,&nbsp;Hoda Zare","doi":"10.1016/j.neuri.2023.100118","DOIUrl":"10.1016/j.neuri.2023.100118","url":null,"abstract":"<div><p>Precise detection of Alzheimer's disease (AD), especially at the early stages, i.e., early mild cognitive impairment (EMCI) and MCI, allows the physicians to promptly intervene to prevent the progression to advanced stages. However, identification of such stages using non-invasive brain imaging techniques like DWI, remains one of the most challenging tasks due to the subtle and mild changes in the brain structures of the subjects. Findings from previous studies suggested that topological organization alterations occur in the DTI-derived structural connectomes in MCI patients. Therefore, for improving diagnosis performance, we presented a connectome-based deep learning architecture based on BrainNet Convolutional neural network (CNN) model. The proposed model automatically extracts hidden topological features from structural networks using specially-designed convolutional filters. Experiments on 360 subjects, including 120 subjects with EMCI, 120 subjects with MCI and, 120 normal controls (NCs), with both T1-weighted MRI and DWI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI), provided the highest binary classification accuracies of 0.96, 0.98, and 0.95 for NC/EMCI, NC/MCI and EMCI/MCI respectively.</p><p>In addition, we also investigated the effect of different atlas sizes and fiber descriptors as edge weights on the discriminative ability of the classification performance. Experimental results indicate that our approach exhibited superior performance to previous methods and performed effectively without any prior complex feature engineering and regardless the variability of imaging acquisition protocols and medical scanners.</p><p>Finally, we observed that DTI-based graph representation of brain regions connections preserve important but hidden connectivity pattern information to discriminate between clinical profiles, and our proposed approach could be easily extended to other neurodegenerative and neuropsychiatric diseases.</p></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"3 1","pages":"Article 100118"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44499546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reporting of angiographic studies in patients diagnosed with a cerebral Arteriovenous Malformation: a systematic review","authors":"Suparna Das, P. Kasher, M. Waqar, Adrian arry-Jones, H. Patel","doi":"10.1016/j.neuri.2023.100125","DOIUrl":"https://doi.org/10.1016/j.neuri.2023.100125","url":null,"abstract":"","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44740786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gradient boosting decision-tree-based algorithm with neuroimaging for personalized treatment in depression","authors":"Farzana Z. Ali ,&nbsp;Kenneth Wengler ,&nbsp;Xiang He ,&nbsp;Minh Hoai Nguyen ,&nbsp;Ramin V. Parsey ,&nbsp;Christine DeLorenzo","doi":"10.1016/j.neuri.2022.100110","DOIUrl":"10.1016/j.neuri.2022.100110","url":null,"abstract":"<div><h3>Introduction</h3><p>Pretreatment positron emission tomography (PET) with 2-deoxy-2-[¹⁸F]fluoro-D-glucose (FDG) and magnetic resonance spectroscopy (MRS) may identify biomarkers for predicting remission (absence of depression). Yet, no such image-based biomarkers have achieved clinical validity. The purpose of this study was to identify biomarkers of remission using machine learning (ML) with pretreatment FDG-PET/MRS neuroimaging, to reduce patient suffering and economic burden from ineffective trials.</p></div><div><h3>Methods</h3><p>This study used simultaneous PET/MRS neuroimaging from a double-blind, placebo-controlled, randomized antidepressant trial on 60 participants with major depressive disorder (MDD) before initiating treatment. After eight weeks of treatment, those with ≤7 on 17-item Hamilton Depression Rating Scale were designated <em>a priori</em> as remitters (free of depression, 37%). Metabolic rate of glucose uptake (metabolism) from 22 brain regions were acquired from PET. Concentrations (mM) of glutamine and glutamate and gamma-aminobutyric acid (GABA) in anterior cingulate cortex were quantified from MRS. The data were randomly split into 67% train and cross-validation (<span><math><mi>n</mi><mo>=</mo><mn>40</mn></math></span>), and 33% test (<span><math><mi>n</mi><mo>=</mo><mn>20</mn></math></span>) sets. The imaging features, along with age, sex, handedness, and treatment assignment (selective serotonin reuptake inhibitor or SSRI vs. placebo) were entered into the eXtreme Gradient Boosting (XGBoost) classifier for training.</p></div><div><h3>Results</h3><p>In test data, the model showed 62% sensitivity, 92% specificity, and 77% weighted accuracy. Pretreatment metabolism of left hippocampus from PET was the most predictive of remission.</p></div><div><h3>Conclusions</h3><p>The pretreatment neuroimaging takes around 60 minutes but has potential to prevent weeks of failed treatment trials. This study effectively addresses common issues for neuroimaging analysis, such as small sample size, high dimensionality, and class imbalance.</p></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"2 4","pages":"Article 100110"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9873411/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9730566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}