Journal of Neuroscience Methods最新文献

{"title":"A novel open-access artificial-intelligence-driven platform for CNS drug discovery utilizing adult zebrafish","authors":"Danil A. Lukovikov ,&nbsp;Tatiana O. Kolesnikova ,&nbsp;Aleksey N. Ikrin ,&nbsp;Nikita O. Prokhorenko ,&nbsp;Anton D. Shevlyakov ,&nbsp;Andrei A. Korotaev ,&nbsp;Longen Yang ,&nbsp;Vea Bley ,&nbsp;Murilo S. de Abreu ,&nbsp;Allan V. Kalueff","doi":"10.1016/j.jneumeth.2024.110256","DOIUrl":"10.1016/j.jneumeth.2024.110256","url":null,"abstract":"<div><h3>Background</h3><p>Although zebrafish are increasingly utilized in biomedicine for CNS disease modelling and drug discovery, this generates big data necessitating objective, precise and reproducible analyses. The artificial intelligence (AI) applications have empowered automated image recognition and video-tracking to ensure more efficient behavioral testing.</p></div><div><h3>New method</h3><p>Capitalizing on several AI tools that most recently became available, here we present a novel open-access AI-driven platform to analyze tracks of adult zebrafish collected from <em>in vivo</em> neuropharmacological experiments. For this, we trained the AI system to distinguish zebrafish behavioral patterns following systemic treatment with several well-studied psychoactive drugs - nicotine, caffeine and ethanol.</p></div><div><h3>Results</h3><p>Experiment 1 showed the ability of the AI system to distinguish nicotine and caffeine with 75 % and ethanol with 88 % probability and high (81 %) accuracy following a post-training exposure to these drugs. Experiment 2 further validated our system with additional, previously unexposed compounds (cholinergic arecoline and varenicline, and serotonergic fluoxetine), used as positive and negative controls, respectively.</p></div><div><h3>Comparison with existing methods</h3><p>The present study introduces a novel open-access AI-driven approach to analyze locomotor activity of adult zebrafish.</p></div><div><h3>Conclusions</h3><p>Taken together, these findings support the value of custom-made AI tools for unlocking full potential of zebrafish CNS drug research by monitoring, processing and interpreting the results of <em>in vivo</em> experiments.</p></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"411 ","pages":"Article 110256"},"PeriodicalIF":2.7,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142055826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Non-invasive electroencephalography in awake cats: Feasibility and application to sensory processing in chronic pain","authors":"Aliénor Delsart ,&nbsp;Aude Castel ,&nbsp;Guillaume Dumas ,&nbsp;Colombe Otis ,&nbsp;Mathieu Lachance ,&nbsp;Maude Barbeau-Grégoire ,&nbsp;Bertrand Lussier ,&nbsp;Franck Péron ,&nbsp;Marc Hébert ,&nbsp;Nicolas Lapointe ,&nbsp;Maxim Moreau ,&nbsp;Johanne Martel-Pelletier ,&nbsp;Jean-Pierre Pelletier ,&nbsp;Eric Troncy","doi":"10.1016/j.jneumeth.2024.110254","DOIUrl":"10.1016/j.jneumeth.2024.110254","url":null,"abstract":"<div><h3>Background</h3><p>Feline osteoarthritis (OA) leads to chronic pain and somatosensory sensitisation. In humans, sensory exposure can modulate chronic pain. Recently, electroencephalography (EEG) revealed a specific brain signature to human OA. However, EEG pain characterisation or its modulation does not exist in OA cats, and all EEG were conducted in sedated cats, using intradermal electrodes, which could alter sensory (pain) perception.</p></div><div><h3>New method</h3><p>Cats (<em>n</em>=11) affected by OA were assessed using ten gold-plated surface electrodes. Sensory stimuli were presented in random orders: response to mechanical temporal summation, grapefruit scent and mono-chromatic wavelengths (500 nm-blue, 525 nm-green and 627 nm-red light). The recorded EEG was processed to identify event-related potentials (ERP) and to perform spectral analysis (z-score).</p></div><div><h3>Results</h3><p>The procedure was well-tolerated. The ERPs were reported for both mechanical (F3, C3, Cz, P3, Pz) and olfactory stimuli (Cz, Pz). The main limitation was motion artifacts. Spectral analysis revealed a significant interaction between the power of EEG frequency bands and light wavelengths (<em>p</em>&lt;0.001). All wavelengths considered, alpha band proportion was higher than that of delta and gamma bands (<em>p</em>&lt;0.044), while the latter was lower than the beta band (<em>p</em>&lt;0.016). Compared to green and red, exposure to blue light elicited distinct changes in EEG power over time (<em>p</em>&lt;0.001).</p></div><div><h3>Comparison with existing method</h3><p>This is the first demonstration of EEG feasibility in conscious cats with surface electrodes recording brain activity while exposing them to sensory stimulations.</p></div><div><h3>Conclusion</h3><p>The identification of ERPs and spectral patterns opens new avenues for investigating feline chronic pain and its potential modulation through sensory interventions.</p></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"411 ","pages":"Article 110254"},"PeriodicalIF":2.7,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0165027024001997/pdfft?md5=b73c807f316fab76fffaa8a7d0dacdb2&pid=1-s2.0-S0165027024001997-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142036053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A minimalistic approach to classifying Alzheimer’s disease using simple and extremely small convolutional neural networks","authors":"Edvard O.S. Grødem ,&nbsp;Esten Leonardsen ,&nbsp;Bradley J. MacIntosh ,&nbsp;Atle Bjørnerud ,&nbsp;Till Schellhorn ,&nbsp;Øystein Sørensen ,&nbsp;Inge Amlien ,&nbsp;Anders M. Fjell ,&nbsp;Alzheimer’s Disease Neuroimaging Initiative","doi":"10.1016/j.jneumeth.2024.110253","DOIUrl":"10.1016/j.jneumeth.2024.110253","url":null,"abstract":"<div><h3>Background:</h3><p>There is a broad interest in deploying deep learning-based classification algorithms to identify individuals with Alzheimer’s disease (AD) from healthy controls (HC) based on neuroimaging data, such as T1-weighted Magnetic Resonance Imaging (MRI). The goal of the current study is to investigate whether modern, flexible architectures such as EfficientNet provide any performance boost over more standard architectures.</p></div><div><h3>Methods:</h3><p>MRI data was sourced from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and processed with a minimal preprocessing pipeline. Among the various architectures tested, the minimal 3D convolutional neural network SFCN stood out, composed solely of 3x3x3 convolution, batch normalization, ReLU, and max-pooling. We also examined the influence of scale on performance, testing SFCN versions with trainable parameters ranging from 720 up to 2.9 million.</p></div><div><h3>Results:</h3><p>SFCN achieves a test ROC AUC of 96.0% while EfficientNet got an ROC AUC of 94.9 %. SFCN retained high performance down to 720 trainable parameters, achieving an ROC AUC of 91.4%.</p></div><div><h3>Comparison with existing methods:</h3><p>The SFCN is compared to DenseNet and EfficientNet as well as the results of other publications in the field.</p></div><div><h3>Conclusions:</h3><p>The results indicate that using the minimal 3D convolutional neural network SFCN with a minimal preprocessing pipeline can achieve competitive performance in AD classification, challenging the necessity of employing more complex architectures with a larger number of parameters. This finding supports the efficiency of simpler deep learning models for neuroimaging-based AD diagnosis, potentially aiding in better understanding and diagnosing Alzheimer’s disease.</p></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"411 ","pages":"Article 110253"},"PeriodicalIF":2.7,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0165027024001985/pdfft?md5=a67a2cd29e6051ebf7457b24f1b2b10f&pid=1-s2.0-S0165027024001985-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142017742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comparative study between a power and a connectivity sEEG biomarker for seizure-onset zone identification in temporal lobe epilepsy","authors":"Manel Vila-Vidal ,&nbsp;Ferran Craven-Bartle Corominas ,&nbsp;Matthieu Gilson ,&nbsp;Riccardo Zucca ,&nbsp;Alessandro Principe ,&nbsp;Rodrigo Rocamora ,&nbsp;Gustavo Deco ,&nbsp;Adrià Tauste Campo","doi":"10.1016/j.jneumeth.2024.110238","DOIUrl":"10.1016/j.jneumeth.2024.110238","url":null,"abstract":"<div><h3>Background:</h3><p>Ictal stereo-encephalography (sEEG) biomarkers for seizure onset zone (SOZ) localization can be classified depending on whether they target abnormalities in signal power or functional connectivity between signals, and they may depend on the frequency band and time window at which they are estimated.</p></div><div><h3>New method:</h3><p>This work aimed to compare and optimize the performance of a power and a connectivity-based biomarker to identify SOZ contacts from ictal sEEG recordings. To do so, we used a previously introduced power-based measure, the normalized mean activation (nMA), which quantifies the ictal average power activation. Similarly, we defined the normalized mean strength (nMS), to quantify the ictal mean functional connectivity of every contact with the rest. The optimal frequency bands and time windows were selected based on optimizing AUC and F2-score.</p></div><div><h3>Results:</h3><p>The analysis was performed on a dataset of 67 seizures from 10 patients with pharmacoresistant temporal lobe epilepsy. Our results suggest that the power-based biomarker generally performs better for the detection of SOZ than the connectivity-based one. However, an equivalent performance level can be achieved when both biomarkers are independently optimized. Optimal performance was achieved in the beta and lower-gamma range for the power biomarker and in the lower- and higher-gamma range for connectivity, both using a 20 or 30 s period after seizure onset.</p></div><div><h3>Conclusions:</h3><p>The results of this study highlight the importance of this optimization step over frequency and time windows when comparing different SOZ discrimination biomarkers. This information should be considered when training SOZ classifiers on retrospective patients’ data for clinical applications.</p></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"411 ","pages":"Article 110238"},"PeriodicalIF":2.7,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0165027024001833/pdfft?md5=59b47d5ea699b11845a3aae3c327c32f&pid=1-s2.0-S0165027024001833-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142017741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"White matter and latency of visual evoked potentials during maturation: A miniature pig model of adolescent development","authors":"Peter Kochunov ,&nbsp;L. Elliot Hong ,&nbsp;Ann Summerfelt ,&nbsp;Si Gao ,&nbsp;P. Leon Brown ,&nbsp;Matthew Terzi ,&nbsp;Ashley Acheson ,&nbsp;Marty G. Woldorff ,&nbsp;Els Fieremans ,&nbsp;Ali Abdollahzadeh ,&nbsp;Korrapati V. Sathyasaikumar ,&nbsp;Sarah M. Clark ,&nbsp;Robert Schwarcz ,&nbsp;Paul D. Shepard ,&nbsp;Greg I. Elmer","doi":"10.1016/j.jneumeth.2024.110252","DOIUrl":"10.1016/j.jneumeth.2024.110252","url":null,"abstract":"<div><h3>Background</h3><p>Continuous myelination of cerebral white matter (WM) during adolescence overlaps with the formation of higher cognitive skills and the onset of many neuropsychiatric disorders. We developed a miniature-pig model of adolescent brain development for neuroimaging and neurophysiological assessment during this critical period. Minipigs have gyroencephalic brains with a large cerebral WM compartment and a well-defined adolescence period.</p></div><div><h3>Methods</h3><p>Eight Sinclair™ minipigs (<em>Sus scrofa domestica</em>) were evaluated four times during weeks 14–28 (40, 28 and 28 days apart) of adolescence using monocular visual stimulation (1 Hz)-evoked potentials and diffusion MRI (dMRI) of WM. The latency for the pre-positive 30 ms (PP30), positive 30 ms (P30) and negative 50 ms (N50) components of the flash visual evoked potentials (fVEPs) and their interhemispheric latency (IL) were recorded in the frontal, central and occipital areas during ten 60-second stimulations for each eye. The dMRI imaging protocol consisted of fifteen b-shells (b = 0–3500 s/mm²) with 32 directions/shell, providing measurements that included fractional anisotropy (FA), radial kurtosis, kurtosis anisotropy (KA), axonal water fraction (AWF), and the permeability-diffusivity index (PDI).</p></div><div><h3>Results</h3><p>Significant reductions (p &lt; 0.05) in the latency and IL of fVEP measurements paralleled significant rises in FA, KA, AWF and PDI over the same period. The longitudinal latency changes in fVEPs were primarily associated with whole-brain changes in diffusion parameters, while fVEP IL changes were related to maturation of the corpus callosum.</p></div><div><h3>Conclusions</h3><p>Good agreement between reduction in the latency of fVEPs and maturation of cerebral WM was interpreted as evidence for ongoing myelination and confirmation of the minipig as a viable research platform. Adolescent development in minipigs can be studied using human neuroimaging and neurophysiological protocols and followed up with more invasive assays to investigate key neurodevelopmental hypotheses in psychiatry.</p></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"411 ","pages":"Article 110252"},"PeriodicalIF":2.7,"publicationDate":"2024-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142004482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low concentration dimethyl sulfoxide (DMSO) modulates epileptiform synchronization in the 4-aminopyridine in vitro model","authors":"Fei Ran Li ,&nbsp;Mia Gemayel ,&nbsp;Maxime Lévesque ,&nbsp;Siyan Wang ,&nbsp;Camila Franco Suarez ,&nbsp;Massimo Avoli","doi":"10.1016/j.jneumeth.2024.110255","DOIUrl":"10.1016/j.jneumeth.2024.110255","url":null,"abstract":"<div><p>Dimethyl sulfoxide (DMSO) is commonly used to dissolve water-insoluble drugs due to its dipolar and aprotic properties. It also serves as a vehicle in many pharmacological studies. However, it has been reported that DMSO can induce seizures in human patients, lower seizure threshold <em>in vivo</em>, and modulate ion receptors activities <em>in vitro</em>. Therefore, we investigated here the effect of 0.03 % and 0.06 % DMSO, which are 10–50 times lower than what usually employed in previous studies, in the 4-aminopyridine (4AP) model of epileptiform synchronization in male mouse brain slices. We found that 0.03 % and 0.06 % DMSO increase 4AP-induced ictal discharge rate, while 0.06 % DMSO decreases ictal discharge duration. Our results suggest that the effects of DMSO on neuronal excitability deserve further analysis and that investigators need to be aware of its confounding effect as a solvent, even at very low concentrations.</p></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"411 ","pages":"Article 110255"},"PeriodicalIF":2.7,"publicationDate":"2024-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142004481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Attention-based CNN-BiLSTM for sleep state classification of spatiotemporal wide-field calcium imaging data","authors":"Xiaohui Zhang ,&nbsp;Eric C. Landsness ,&nbsp;Hanyang Miao ,&nbsp;Wei Chen ,&nbsp;Michelle J. Tang ,&nbsp;Lindsey M. Brier ,&nbsp;Joseph P. Culver ,&nbsp;Jin-Moo Lee ,&nbsp;Mark A. Anastasio","doi":"10.1016/j.jneumeth.2024.110250","DOIUrl":"10.1016/j.jneumeth.2024.110250","url":null,"abstract":"<div><h3>Background</h3><p>Wide-field calcium imaging (WFCI) with genetically encoded calcium indicators allows for spatiotemporal recordings of neuronal activity in mice. When applied to the study of sleep, WFCI data are manually scored into the sleep states of wakefulness, non-REM (NREM) and REM by use of adjunct EEG and EMG recordings. However, this process is time-consuming, invasive and often suffers from low inter- and intra-rater reliability. Therefore, an automated sleep state classification method that operates on spatiotemporal WFCI data is desired.</p></div><div><h3>New method</h3><p>A hybrid network architecture consisting of a convolutional neural network (CNN) to extract spatial features of image frames and a bidirectional long short-term memory network (BiLSTM) with attention mechanism to identify temporal dependencies among different time points was proposed to classify WFCI data into states of wakefulness, NREM and REM sleep.</p></div><div><h3>Results</h3><p>Sleep states were classified with an accuracy of 84 % and Cohen’s <em>κ</em> of 0.64. Gradient-weighted class activation maps revealed that the frontal region of the cortex carries more importance when classifying WFCI data into NREM sleep while posterior area contributes most to the identification of wakefulness. The attention scores indicated that the proposed network focuses on short- and long-range temporal dependency in a state-specific manner.</p></div><div><h3>Comparison with existing method</h3><p>On a held out, repeated 3-hour WFCI recording, the CNN-BiLSTM achieved a <em>κ</em> of 0.67, comparable to a <em>κ</em> of 0.65 corresponding to the human EEG/EMG-based scoring.</p></div><div><h3>Conclusions</h3><p>The CNN-BiLSTM effectively classifies sleep states from spatiotemporal WFCI data and will enable broader application of WFCI in sleep research.</p></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"411 ","pages":"Article 110250"},"PeriodicalIF":2.7,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S016502702400195X/pdfft?md5=28a84841e7c1b572d74d7ed45dcf27d4&pid=1-s2.0-S016502702400195X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141995872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Primate eye tracking with carbon-nanotube-paper-composite based capacitive sensors and machine learning algorithms","authors":"Tianyi Li ,&nbsp;Vigneshwar Sakthivelpathi ,&nbsp;Zhongjie Qian ,&nbsp;Robijanto Soetedjo ,&nbsp;Jae-Hyun Chung","doi":"10.1016/j.jneumeth.2024.110249","DOIUrl":"10.1016/j.jneumeth.2024.110249","url":null,"abstract":"<div><h3>Background</h3><p>Accurate real-time eye tracking is crucial in oculomotor system research. While the scleral search coil system is the gold standard, its implantation procedure and bulkiness pose challenges. Camera-based systems are affected by ambient lighting and require high computational and electric power.</p></div><div><h3>New Method</h3><p>This study presents a novel eye tracker using proximity capacitive sensors made of carbon-nanotube-paper-composite (CPC). These sensors detect femtofarad-level capacitance changes caused by primate corneal movement during horizontal and vertical eye rotations. Data processing and machine learning algorithms are evaluated to enhance the accuracy of gaze angle prediction.</p></div><div><h3>Results</h3><p>The system performance is benchmarked against the scleral coil during smooth pursuits, saccades tracking, and fixations. The eye tracker demonstrates up to 0.97 correlation with the coil in eye tracking and is capable of estimating gaze angle with a median absolute error as low as 0.30°.</p></div><div><h3>Comparison</h3><p>The capacitive eye tracker demonstrates good consistency and accuracy in comparison to the gold-standard scleral search coil method.</p></div><div><h3>Conclusions</h3><p>This lightweight, non-invasive capacitive eye tracker offers potential as an alternative to traditional coil and camera-based systems in oculomotor research and vision science.</p></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"410 ","pages":"Article 110249"},"PeriodicalIF":2.7,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141990522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decoding micro-electrocorticographic signals by using explainable 3D convolutional neural network to predict finger movements","authors":"Chao-Hung Kuo ,&nbsp;Guan-Tze Liu ,&nbsp;Chi-En Lee ,&nbsp;Jing Wu ,&nbsp;Kaitlyn Casimo ,&nbsp;Kurt E. Weaver ,&nbsp;Yu-Chun Lo ,&nbsp;You-Yin Chen ,&nbsp;Wen-Cheng Huang ,&nbsp;Jeffrey G. Ojemann","doi":"10.1016/j.jneumeth.2024.110251","DOIUrl":"10.1016/j.jneumeth.2024.110251","url":null,"abstract":"<div><h3>Background</h3><p>Electroencephalography (EEG) and electrocorticography (ECoG) recordings have been used to decode finger movements by analyzing brain activity. Traditional methods focused on single bandpass power changes for movement decoding, utilizing machine learning models requiring manual feature extraction.</p></div><div><h3>New method</h3><p>This study introduces a 3D convolutional neural network (3D-CNN) model to decode finger movements using ECoG data. The model employs adaptive, explainable AI (xAI) techniques to interpret the physiological relevance of brain signals. ECoG signals from epilepsy patients during awake craniotomy were processed to extract power spectral density across multiple frequency bands. These data formed a 3D matrix used to train the 3D-CNN to predict finger trajectories.</p></div><div><h3>Results</h3><p>The 3D-CNN model showed significant accuracy in predicting finger movements, with root-mean-square error (RMSE) values of 0.26–0.38 for single finger movements and 0.20–0.24 for combined movements. Explainable AI techniques, Grad-CAM and SHAP, identified the high gamma (HG) band as crucial for movement prediction, showing specific cortical regions involved in different finger movements. These findings highlighted the physiological significance of the HG band in motor control.</p></div><div><h3>Comparison with existing methods</h3><p>The 3D-CNN model outperformed traditional machine learning approaches by effectively capturing spatial and temporal patterns in ECoG data. The use of xAI techniques provided clearer insights into the model's decision-making process, unlike the \"black box\" nature of standard deep learning models.</p></div><div><h3>Conclusions</h3><p>The proposed 3D-CNN model, combined with xAI methods, enhances the decoding accuracy of finger movements from ECoG data. This approach offers a more efficient and interpretable solution for brain-computer interface (BCI) applications, emphasizing the HG band's role in motor control.</p></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"411 ","pages":"Article 110251"},"PeriodicalIF":2.7,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141995871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neuro-XAI: Explainable deep learning framework based on deeplabV3+ and bayesian optimization for segmentation and classification of brain tumor in MRI scans","authors":"Tallha Saeed ,&nbsp;Muhammad Attique Khan ,&nbsp;Ameer Hamza ,&nbsp;Mohammad Shabaz ,&nbsp;Wazir Zada Khan ,&nbsp;Fatimah Alhayan ,&nbsp;Leila Jamel ,&nbsp;Jamel Baili","doi":"10.1016/j.jneumeth.2024.110247","DOIUrl":"10.1016/j.jneumeth.2024.110247","url":null,"abstract":"<div><p>The prevalence of brain tumor disorders is currently a global issue. In general, radiography, which includes a large number of images, is an efficient method for diagnosing these life-threatening disorders. The biggest issue in this area is that it takes a radiologist a long time and is physically strenuous to look at all the images. As a result, research into developing systems based on machine learning to assist radiologists in diagnosis continues to rise daily. Convolutional neural networks (CNNs), one type of deep learning approach, have been pivotal in achieving state-of-the-art results in several medical imaging applications, including the identification of brain tumors. CNN hyperparameters are typically set manually for segmentation and classification, which might take a while and increase the chance of using suboptimal hyperparameters for both tasks. Bayesian optimization is a useful method for updating the deep CNN's optimal hyperparameters. The CNN network, however, can be considered a \"black box\" model because of how difficult it is to comprehend the information it stores because of its complexity. Therefore, this problem can be solved by using Explainable Artificial Intelligence (XAI) tools, which provide doctors with a realistic explanation of CNN's assessments. Implementation of deep learning-based systems in real-time diagnosis is still rare. One of the causes could be that these methods don't quantify the Uncertainty in the predictions, which could undermine trust in the AI-based diagnosis of diseases. To be used in real-time medical diagnosis, CNN-based models must be realistic and appealing, and uncertainty needs to be evaluated. So, a novel three-phase strategy is proposed for segmenting and classifying brain tumors. Segmentation of brain tumors using the DeeplabV3+ model is first performed with tuning of hyperparameters using Bayesian optimization. For classification, features from state-of-the-art deep learning models Darknet53 and mobilenetv2 are extracted and fed to SVM for classification, and hyperparameters of SVM are also optimized using a Bayesian approach. The second step is to understand whatever portion of the images CNN uses for feature extraction using XAI algorithms. Using confusion entropy, the Uncertainty of the Bayesian optimized classifier is finally quantified. Based on a Bayesian-optimized deep learning framework, the experimental findings demonstrate that the proposed method outperforms earlier techniques, achieving a 97 % classification accuracy and a 0.98 global accuracy.</p></div>","PeriodicalId":16415,"journal":{"name":"Journal of Neuroscience Methods","volume":"410 ","pages":"Article 110247"},"PeriodicalIF":2.7,"publicationDate":"2024-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141916979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}