Pub Date : 2024-11-08eCollection Date: 2024-01-01DOI: 10.3389/fncom.2024.1514220
Noemi Montobbio, Roberto Maffulli, Anees Abrol, Pablo Martínez-Cañada
{"title":"Editorial: Computational modeling and machine learning methods in neurodevelopment and neurodegeneration: from basic research to clinical applications.","authors":"Noemi Montobbio, Roberto Maffulli, Anees Abrol, Pablo Martínez-Cañada","doi":"10.3389/fncom.2024.1514220","DOIUrl":"https://doi.org/10.3389/fncom.2024.1514220","url":null,"abstract":"","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"18 ","pages":"1514220"},"PeriodicalIF":2.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11581899/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142709341","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}
Pub Date : 2024-11-06eCollection Date: 2024-01-01DOI: 10.3389/fncom.2024.1466364
Eric Chalmers, Santina Duarte, Xena Al-Hejji, Daniel Devoe, Aaron Gruber, Robert J McDonald
Deep Reinforcement Learning is a branch of artificial intelligence that uses artificial neural networks to model reward-based learning as it occurs in biological agents. Here we modify a Deep Reinforcement Learning approach by imposing a suppressive effect on the connections between neurons in the artificial network-simulating the effect of dendritic spine loss as observed in major depressive disorder (MDD). Surprisingly, this simulated spine loss is sufficient to induce a variety of MDD-like behaviors in the artificially intelligent agent, including anhedonia, increased temporal discounting, avoidance, and an altered exploration/exploitation balance. Furthermore, simulating alternative and longstanding reward-processing-centric conceptions of MDD (dysfunction of the dopamine system, altered reward discounting, context-dependent learning rates, increased exploration) does not produce the same range of MDD-like behaviors. These results support a conceptual model of MDD as a reduction of brain connectivity (and thus information-processing capacity) rather than an imbalance in monoamines-though the computational model suggests a possible explanation for the dysfunction of dopamine systems in MDD. Reversing the spine-loss effect in our computational MDD model can lead to rescue of rewarding behavior under some conditions. This supports the search for treatments that increase plasticity and synaptogenesis, and the model suggests some implications for their effective administration.
{"title":"Simulated synapse loss induces depression-like behaviors in deep reinforcement learning.","authors":"Eric Chalmers, Santina Duarte, Xena Al-Hejji, Daniel Devoe, Aaron Gruber, Robert J McDonald","doi":"10.3389/fncom.2024.1466364","DOIUrl":"10.3389/fncom.2024.1466364","url":null,"abstract":"<p><p>Deep Reinforcement Learning is a branch of artificial intelligence that uses artificial neural networks to model reward-based learning as it occurs in biological agents. Here we modify a Deep Reinforcement Learning approach by imposing a suppressive effect on the connections between neurons in the artificial network-simulating the effect of dendritic spine loss as observed in major depressive disorder (MDD). Surprisingly, this simulated spine loss is sufficient to induce a variety of MDD-like behaviors in the artificially intelligent agent, including anhedonia, increased temporal discounting, avoidance, and an altered exploration/exploitation balance. Furthermore, simulating alternative and longstanding reward-processing-centric conceptions of MDD (dysfunction of the dopamine system, altered reward discounting, context-dependent learning rates, increased exploration) does not produce the same range of MDD-like behaviors. These results support a conceptual model of MDD as a reduction of brain connectivity (and thus information-processing capacity) rather than an imbalance in monoamines-though the computational model suggests a possible explanation for the dysfunction of dopamine systems in MDD. Reversing the spine-loss effect in our computational MDD model can lead to rescue of rewarding behavior under some conditions. This supports the search for treatments that increase plasticity and synaptogenesis, and the model suggests some implications for their effective administration.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"18 ","pages":"1466364"},"PeriodicalIF":2.1,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11576168/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142681336","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}
Pub Date : 2024-10-31eCollection Date: 2024-01-01DOI: 10.3389/fncom.2024.1475530
Mansoor S Raza, Mohsin Murtaza, Chi-Tsun Cheng, Muhana M A Muslam, Bader M Albahlal
The intricate interplay between driver cognitive dysfunction, mental workload (MWL), and heart rate variability (HRV) provides a captivating avenue for investigation within the domain of transportation safety studies. This article provides a systematic review and examines cognitive hindrance stemming from mental workload and heart rate variability. It scrutinizes the mental workload experienced by drivers by leveraging data gleaned from prior studies that employed heart rate monitoring systems and eye tracking technology, thereby illuminating the correlation between cognitive impairment, mental workload, and physiological indicators such as heart rate and ocular movements. The investigation is grounded in the premise that the mental workload of drivers can be assessed through physiological cues, such as heart rate and eye movements. The study discovered that HRV and infrared (IR) measurements played a crucial role in evaluating fatigue and workload for skilled drivers. However, the study overlooked potential factors contributing to cognitive impairment in drivers and could benefit from incorporating alternative indicators of cognitive workload for deeper insights. Furthermore, investigated driving simulators demonstrated that an eco-safe driving Human-Machine Interface (HMI) significantly promoted safe driving behaviors without imposing excessive mental and visual workload on drivers. Recommendations were made for future studies to consider additional indicators of cognitive workload, such as subjective assessments or task performance metrics, for a more comprehensive understanding.
{"title":"Systematic review of cognitive impairment in drivers through mental workload using physiological measures of heart rate variability.","authors":"Mansoor S Raza, Mohsin Murtaza, Chi-Tsun Cheng, Muhana M A Muslam, Bader M Albahlal","doi":"10.3389/fncom.2024.1475530","DOIUrl":"10.3389/fncom.2024.1475530","url":null,"abstract":"<p><p>The intricate interplay between driver cognitive dysfunction, mental workload (MWL), and heart rate variability (HRV) provides a captivating avenue for investigation within the domain of transportation safety studies. This article provides a systematic review and examines cognitive hindrance stemming from mental workload and heart rate variability. It scrutinizes the mental workload experienced by drivers by leveraging data gleaned from prior studies that employed heart rate monitoring systems and eye tracking technology, thereby illuminating the correlation between cognitive impairment, mental workload, and physiological indicators such as heart rate and ocular movements. The investigation is grounded in the premise that the mental workload of drivers can be assessed through physiological cues, such as heart rate and eye movements. The study discovered that HRV and infrared (IR) measurements played a crucial role in evaluating fatigue and workload for skilled drivers. However, the study overlooked potential factors contributing to cognitive impairment in drivers and could benefit from incorporating alternative indicators of cognitive workload for deeper insights. Furthermore, investigated driving simulators demonstrated that an eco-safe driving Human-Machine Interface (HMI) significantly promoted safe driving behaviors without imposing excessive mental and visual workload on drivers. Recommendations were made for future studies to consider additional indicators of cognitive workload, such as subjective assessments or task performance metrics, for a more comprehensive understanding.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"18 ","pages":"1475530"},"PeriodicalIF":2.1,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11560442/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142617217","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}
Pub Date : 2024-10-30eCollection Date: 2024-01-01DOI: 10.3389/fncom.2024.1435956
Shtwai Alsubai, Abdullah Alqahtani, Abed Alanazi, Mohemmed Sha, Abdu Gumaei
Introduction: Facial expressions have become a common way for interaction among humans. People cannot comprehend and predict the emotions or expressions of individuals through simple vision. Thus, in psychology, detecting facial expressions or emotion analysis demands an assessment and evaluation of decisions for identifying the emotions of a person or any group during communication. With the recent evolution of technology, AI (Artificial Intelligence) has gained significant usage, wherein DL (Deep Learning) based algorithms are employed for detecting facial expressions.
Methods: The study proposes a system design that detects facial expressions by extracting relevant features using a Modified ResNet model. The proposed system stacks building-blocks with residual connections and employs an advanced extraction method with quantum computing, which significantly reduces computation time compared to conventional methods. The backbone stem utilizes a quantum convolutional layer comprised of several parameterized quantum-filters. Additionally, the research integrates residual connections in the ResNet-18 model with the Modified up Sampled Bottle Neck Process (MuS-BNP), retaining computational efficacy while benefiting from residual connections.
Results: The proposed model demonstrates superior performance by overcoming the issue of maximum similarity within varied facial expressions. The system's ability to accurately detect and differentiate between expressions is measured using performance metrics such as accuracy, F1-score, recall, and precision.
Discussion: This performance analysis confirms the efficacy of the proposed system, highlighting the advantages of quantum computing in feature extraction and the integration of residual connections. The model achieves quantum superiority, providing faster and more accurate computations compared to existing methodologies. The results suggest that the proposed approach offers a promising solution for facial expression recognition tasks, significantly improving both speed and accuracy.
{"title":"Facial emotion recognition using deep quantum and advanced transfer learning mechanism.","authors":"Shtwai Alsubai, Abdullah Alqahtani, Abed Alanazi, Mohemmed Sha, Abdu Gumaei","doi":"10.3389/fncom.2024.1435956","DOIUrl":"10.3389/fncom.2024.1435956","url":null,"abstract":"<p><strong>Introduction: </strong>Facial expressions have become a common way for interaction among humans. People cannot comprehend and predict the emotions or expressions of individuals through simple vision. Thus, in psychology, detecting facial expressions or emotion analysis demands an assessment and evaluation of decisions for identifying the emotions of a person or any group during communication. With the recent evolution of technology, AI (Artificial Intelligence) has gained significant usage, wherein DL (Deep Learning) based algorithms are employed for detecting facial expressions.</p><p><strong>Methods: </strong>The study proposes a system design that detects facial expressions by extracting relevant features using a Modified ResNet model. The proposed system stacks building-blocks with residual connections and employs an advanced extraction method with quantum computing, which significantly reduces computation time compared to conventional methods. The backbone stem utilizes a quantum convolutional layer comprised of several parameterized quantum-filters. Additionally, the research integrates residual connections in the ResNet-18 model with the Modified up Sampled Bottle Neck Process (MuS-BNP), retaining computational efficacy while benefiting from residual connections.</p><p><strong>Results: </strong>The proposed model demonstrates superior performance by overcoming the issue of maximum similarity within varied facial expressions. The system's ability to accurately detect and differentiate between expressions is measured using performance metrics such as accuracy, F1-score, recall, and precision.</p><p><strong>Discussion: </strong>This performance analysis confirms the efficacy of the proposed system, highlighting the advantages of quantum computing in feature extraction and the integration of residual connections. The model achieves quantum superiority, providing faster and more accurate computations compared to existing methodologies. The results suggest that the proposed approach offers a promising solution for facial expression recognition tasks, significantly improving both speed and accuracy.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"18 ","pages":"1435956"},"PeriodicalIF":2.1,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11557492/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142617216","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}
Pub Date : 2024-10-24eCollection Date: 2024-01-01DOI: 10.3389/fncom.2024.1482994
Liao Xuanzhi, Abeer Hakeem, Linda Mohaisen, Muhammad Umer, Muhammad Attique Khan, Shrooq Alsenan, Shtwai Alsubai, Nisreen Innab
Brain stress monitoring has emerged as a critical research area for understanding and managing stress and neurological health issues. This burgeoning field aims to provide accurate information and prediction about individuals' stress levels by analyzing behavioral data and physiological signals. To address this emerging problem, this research study proposes an innovative approach that uses an attention mechanism-based XLNet model (called BrainNet) for continuous stress monitoring and stress level prediction. The proposed model analyzes streams of brain data, including behavioral and physiological signal patterns using Swell and WESAD datasets. Testing on the Swell multi-class dataset, the model achieves an impressive accuracy of 95.76%. Furthermore, when evaluated on the WESAD dataset, it demonstrates even higher accuracy, reaching 98.32%. When applied to the binary classification of stress and no stress using the Swell dataset, the model achieves an outstanding accuracy of 97.19%. Comparative analysis with other previously published research studies underscores the superior performance of the proposed approach. In addition, cross-validation confirms the significance, efficacy, and robustness of the model in brain stress level prediction and aligns with the goals of smart diagnostics for understanding neurological behaviors.
{"title":"BrainNet: an automated approach for brain stress prediction utilizing electrodermal activity signal with XLNet model.","authors":"Liao Xuanzhi, Abeer Hakeem, Linda Mohaisen, Muhammad Umer, Muhammad Attique Khan, Shrooq Alsenan, Shtwai Alsubai, Nisreen Innab","doi":"10.3389/fncom.2024.1482994","DOIUrl":"https://doi.org/10.3389/fncom.2024.1482994","url":null,"abstract":"<p><p>Brain stress monitoring has emerged as a critical research area for understanding and managing stress and neurological health issues. This burgeoning field aims to provide accurate information and prediction about individuals' stress levels by analyzing behavioral data and physiological signals. To address this emerging problem, this research study proposes an innovative approach that uses an attention mechanism-based XLNet model (called BrainNet) for continuous stress monitoring and stress level prediction. The proposed model analyzes streams of brain data, including behavioral and physiological signal patterns using Swell and WESAD datasets. Testing on the Swell multi-class dataset, the model achieves an impressive accuracy of 95.76%. Furthermore, when evaluated on the WESAD dataset, it demonstrates even higher accuracy, reaching 98.32%. When applied to the binary classification of stress and no stress using the Swell dataset, the model achieves an outstanding accuracy of 97.19%. Comparative analysis with other previously published research studies underscores the superior performance of the proposed approach. In addition, cross-validation confirms the significance, efficacy, and robustness of the model in brain stress level prediction and aligns with the goals of smart diagnostics for understanding neurological behaviors.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"18 ","pages":"1482994"},"PeriodicalIF":2.1,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11540660/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142603906","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}
Pub Date : 2024-10-23eCollection Date: 2024-01-01DOI: 10.3389/fncom.2024.1445621
Audrey Sederberg, Aurélie Pala, Garrett B Stanley
Introduction: As emerging technologies enable measurement of precise details of the activity within microcircuits at ever-increasing scales, there is a growing need to identify the salient features and patterns within the neural populations that represent physiologically and behaviorally relevant aspects of the network. Accumulating evidence from recordings of large neural populations suggests that neural population activity frequently exhibits relatively low-dimensional structure, with a small number of variables explaining a substantial fraction of the structure of the activity. While such structure has been observed across the brain, it is not known how reduced-dimension representations of neural population activity relate to classical metrics of "brain state," typically described in terms of fluctuations in the local field potential (LFP), single-cell activity, and behavioral metrics.
Methods: Hidden state models were fit to spontaneous spiking activity of populations of neurons, recorded in the whisker area of primary somatosensory cortex of awake mice. Classic measures of cortical state in S1, including the LFP and whisking activity, were compared to the dynamics of states inferred from spiking activity.
Results: A hidden Markov model fit the population spiking data well with a relatively small number of states, and putative inhibitory neurons played an outsize role in determining the latent state dynamics. Spiking states inferred from the model were more informative of the cortical state than a direct readout of the spiking activity of single neurons or of the population. Further, the spiking states predicted both the trial-by-trial variability in sensory responses and one aspect of behavior, whisking activity.
Discussion: Our results show how classical measurements of brain state relate to neural population spiking dynamics at the scale of the microcircuit and provide an approach for quantitative mapping of brain state dynamics across brain areas.
{"title":"Latent dynamics of primary sensory cortical population activity structured by fluctuations in the local field potential.","authors":"Audrey Sederberg, Aurélie Pala, Garrett B Stanley","doi":"10.3389/fncom.2024.1445621","DOIUrl":"10.3389/fncom.2024.1445621","url":null,"abstract":"<p><strong>Introduction: </strong>As emerging technologies enable measurement of precise details of the activity within microcircuits at ever-increasing scales, there is a growing need to identify the salient features and patterns within the neural populations that represent physiologically and behaviorally relevant aspects of the network. Accumulating evidence from recordings of large neural populations suggests that neural population activity frequently exhibits relatively low-dimensional structure, with a small number of variables explaining a substantial fraction of the structure of the activity. While such structure has been observed across the brain, it is not known how reduced-dimension representations of neural population activity relate to classical metrics of \"brain state,\" typically described in terms of fluctuations in the local field potential (LFP), single-cell activity, and behavioral metrics.</p><p><strong>Methods: </strong>Hidden state models were fit to spontaneous spiking activity of populations of neurons, recorded in the whisker area of primary somatosensory cortex of awake mice. Classic measures of cortical state in S1, including the LFP and whisking activity, were compared to the dynamics of states inferred from spiking activity.</p><p><strong>Results: </strong>A hidden Markov model fit the population spiking data well with a relatively small number of states, and putative inhibitory neurons played an outsize role in determining the latent state dynamics. Spiking states inferred from the model were more informative of the cortical state than a direct readout of the spiking activity of single neurons or of the population. Further, the spiking states predicted both the trial-by-trial variability in sensory responses and one aspect of behavior, whisking activity.</p><p><strong>Discussion: </strong>Our results show how classical measurements of brain state relate to neural population spiking dynamics at the scale of the microcircuit and provide an approach for quantitative mapping of brain state dynamics across brain areas.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"18 ","pages":"1445621"},"PeriodicalIF":2.1,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11537859/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590127","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}
Pub Date : 2024-10-22eCollection Date: 2024-01-01DOI: 10.3389/fncom.2024.1487877
Kauê T N Duarte, Abhijot S Sidhu, Murilo C Barros, David G Gobbi, Cheryl R McCreary, Feryal Saad, Richard Camicioli, Eric E Smith, Mariana P Bento, Richard Frayne
Introduction: White matter hyperintensities (WMHs) are frequently observed on magnetic resonance (MR) images in older adults, commonly appearing as areas of high signal intensity on fluid-attenuated inversion recovery (FLAIR) MR scans. Elevated WMH volumes are associated with a greater risk of dementia and stroke, even after accounting for vascular risk factors. Manual segmentation, while considered the ground truth, is both labor-intensive and time-consuming, limiting the generation of annotated WMH datasets. Un-annotated data are relatively available; however, the requirement of annotated data poses a challenge for developing supervised machine learning models.
Methods: To address this challenge, we implemented a multi-stage semi-supervised learning (M3SL) approach that first uses un-annotated data segmented by traditional processing methods ("bronze" and "silver" quality data) and then uses a smaller number of "gold"-standard annotations for model refinement. The M3SL approach enabled fine-tuning of the model weights with the gold-standard annotations. This approach was integrated into the training of a U-Net model for WMH segmentation. We used data from three scanner vendors (over more than five scanners) and from both cognitively normal (CN) adult and patients cohorts [with mild cognitive impairment and Alzheimer's disease (AD)].
Results: An analysis of WMH segmentation performance across both scanner and clinical stage (CN, MCI, AD) factors was conducted. We compared our results to both conventional and transfer-learning deep learning methods and observed better generalization with M3SL across different datasets. We evaluated several metrics (F-measure, IoU, and Hausdorff distance) and found significant improvements with our method compared to conventional (p < 0.001) and transfer-learning (p < 0.001).
Discussion: These findings suggest that automated, non-machine learning, tools have a role in a multi-stage learning framework and can reduce the impact of limited annotated data and, thus, enhance model performance.
{"title":"Multi-stage semi-supervised learning enhances white matter hyperintensity segmentation.","authors":"Kauê T N Duarte, Abhijot S Sidhu, Murilo C Barros, David G Gobbi, Cheryl R McCreary, Feryal Saad, Richard Camicioli, Eric E Smith, Mariana P Bento, Richard Frayne","doi":"10.3389/fncom.2024.1487877","DOIUrl":"10.3389/fncom.2024.1487877","url":null,"abstract":"<p><strong>Introduction: </strong>White matter hyperintensities (WMHs) are frequently observed on magnetic resonance (MR) images in older adults, commonly appearing as areas of high signal intensity on fluid-attenuated inversion recovery (FLAIR) MR scans. Elevated WMH volumes are associated with a greater risk of dementia and stroke, even after accounting for vascular risk factors. Manual segmentation, while considered the ground truth, is both labor-intensive and time-consuming, limiting the generation of annotated WMH datasets. Un-annotated data are relatively available; however, the requirement of annotated data poses a challenge for developing supervised machine learning models.</p><p><strong>Methods: </strong>To address this challenge, we implemented a multi-stage semi-supervised learning (M3SL) approach that first uses un-annotated data segmented by traditional processing methods (\"bronze\" and \"silver\" quality data) and then uses a smaller number of \"gold\"-standard annotations for model refinement. The M3SL approach enabled fine-tuning of the model weights with the gold-standard annotations. This approach was integrated into the training of a U-Net model for WMH segmentation. We used data from three scanner vendors (over more than five scanners) and from both cognitively normal (CN) adult and patients cohorts [with mild cognitive impairment and Alzheimer's disease (AD)].</p><p><strong>Results: </strong>An analysis of WMH segmentation performance across both scanner and clinical stage (CN, MCI, AD) factors was conducted. We compared our results to both conventional and transfer-learning deep learning methods and observed better generalization with M3SL across different datasets. We evaluated several metrics (<i>F</i>-measure, <i>IoU</i>, and Hausdorff distance) and found significant improvements with our method compared to conventional (<i>p</i> < 0.001) and transfer-learning (<i>p</i> < 0.001).</p><p><strong>Discussion: </strong>These findings suggest that automated, non-machine learning, tools have a role in a multi-stage learning framework and can reduce the impact of limited annotated data and, thus, enhance model performance.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"18 ","pages":"1487877"},"PeriodicalIF":2.1,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11534601/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142582212","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}
Pub Date : 2024-10-21eCollection Date: 2024-01-01DOI: 10.3389/fncom.2024.1489463
Asma Aldrees, Stephen Ojo, James Wanliss, Muhammad Umer, Muhammad Attique Khan, Bayan Alabdullah, Shtwai Alsubai, Nisreen Innab
Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by notable challenges in cognitive function, understanding language, recognizing objects, interacting with others, and communicating effectively. Its origins are mainly genetic, and identifying it early and intervening promptly can reduce the necessity for extensive medical treatments and lengthy diagnostic procedures for those impacted by ASD. This research is designed with two types of experimentation for ASD analysis. In the first set of experiments, authors utilized three feature engineering techniques (Chi-square, backward feature elimination, and PCA) with multiple machine learning models for autism presence prediction in toddlers. The proposed XGBoost 2.0 obtained 99% accuracy, F1 score, and recall with 98% precision with chi-square significant features. In the second scenario, main focus shifts to identifying tailored educational methods for children with ASD through the assessment of their behavioral, verbal, and physical responses. Again, the proposed approach performs well with 99% accuracy, F1 score, recall, and precision. In this research, cross-validation technique is also implemented to check the stability of the proposed model along with the comparison of previously published research works to show the significance of the proposed model. This study aims to develop personalized educational strategies for individuals with ASD using machine learning techniques to meet their specific needs better.
{"title":"Data-centric automated approach to predict autism spectrum disorder based on selective features and explainable artificial intelligence.","authors":"Asma Aldrees, Stephen Ojo, James Wanliss, Muhammad Umer, Muhammad Attique Khan, Bayan Alabdullah, Shtwai Alsubai, Nisreen Innab","doi":"10.3389/fncom.2024.1489463","DOIUrl":"10.3389/fncom.2024.1489463","url":null,"abstract":"<p><p>Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by notable challenges in cognitive function, understanding language, recognizing objects, interacting with others, and communicating effectively. Its origins are mainly genetic, and identifying it early and intervening promptly can reduce the necessity for extensive medical treatments and lengthy diagnostic procedures for those impacted by ASD. This research is designed with two types of experimentation for ASD analysis. In the first set of experiments, authors utilized three feature engineering techniques (Chi-square, backward feature elimination, and PCA) with multiple machine learning models for autism presence prediction in toddlers. The proposed XGBoost 2.0 obtained 99% accuracy, F1 score, and recall with 98% precision with chi-square significant features. In the second scenario, main focus shifts to identifying tailored educational methods for children with ASD through the assessment of their behavioral, verbal, and physical responses. Again, the proposed approach performs well with 99% accuracy, F1 score, recall, and precision. In this research, cross-validation technique is also implemented to check the stability of the proposed model along with the comparison of previously published research works to show the significance of the proposed model. This study aims to develop personalized educational strategies for individuals with ASD using machine learning techniques to meet their specific needs better.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"18 ","pages":"1489463"},"PeriodicalIF":2.1,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11532156/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142575728","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}
Pub Date : 2024-10-17eCollection Date: 2024-01-01DOI: 10.3389/fncom.2024.1444019
Houmem Slimi, Ala Balti, Sabeur Abid, Mounir Sayadi
Introduction: Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline, memory loss, and impaired daily functioning. Despite significant research, AD remains incurable, highlighting the critical need for early diagnosis and intervention to improve patient outcomes. Timely detection plays a crucial role in managing the disease more effectively. Pretrained convolutional neural networks (CNNs) trained on large-scale datasets, such as ImageNet, have been employed for AD classification, providing a head start for developing more accurate models.
Methods: This paper proposes a novel hybrid deep learning approach that combines the strengths of two specific pretrained architectures. The proposed model enhances the representation of AD-related patterns by leveraging the feature extraction capabilities of both networks. We validated this model using a large dataset of MRI images from AD patients. Performance was evaluated in terms of classification accuracy and robustness against noise, and the results were compared to several commonly used models in AD detection.
Results: The proposed hybrid model demonstrated significant performance improvements over individual models, achieving an accuracy classification rate of 99.85%. Comparative analysis with other models further revealed the superiority of the new architecture, particularly in terms of classification rate and resistance to noise interference.
Discussion: The high accuracy and robustness of the proposed hybrid model suggest its potential utility in early AD detection. By improving feature representation through the combination of two pretrained networks, this model could provide clinicians with a more reliable tool for early diagnosis and monitoring of AD progression. This approach holds promise for aiding in timely diagnoses and treatment decisions, contributing to better management of Alzheimer's disease.
前言阿尔茨海默病(AD)是一种进行性神经退行性疾病,以认知能力下降、记忆力减退和日常功能受损为特征。尽管开展了大量研究,但阿尔茨海默病仍无法治愈,这突出表明了早期诊断和干预以改善患者预后的迫切需要。及时发现对更有效地控制疾病起着至关重要的作用。在大规模数据集(如 ImageNet)上训练的预训练卷积神经网络(CNN)已被用于 AD 分类,为开发更精确的模型提供了一个良好的开端:本文提出了一种新型混合深度学习方法,它结合了两种特定预训练架构的优势。通过利用这两种网络的特征提取能力,所提出的模型增强了对注意力缺失症相关模式的表示。我们使用来自 AD 患者的大型 MRI 图像数据集对该模型进行了验证。我们从分类准确性和对噪声的鲁棒性两个方面对其性能进行了评估,并将结果与一些常用的注意力缺失症检测模型进行了比较:结果:与单个模型相比,所提出的混合模型的性能有了显著提高,分类准确率达到 99.85%。与其他模型的对比分析进一步显示了新架构的优越性,尤其是在分类率和抗噪声干扰能力方面:讨论:所提出的混合模型的高准确率和鲁棒性表明,它在早期注意力缺失症检测中具有潜在的实用性。通过结合两个预训练网络来改进特征表示,该模型可以为临床医生提供更可靠的工具,用于早期诊断和监测注意力缺失症的进展。这种方法有望帮助及时做出诊断和治疗决定,为更好地管理阿尔茨海默病做出贡献。
{"title":"A combinatorial deep learning method for Alzheimer's disease classification-based merging pretrained networks.","authors":"Houmem Slimi, Ala Balti, Sabeur Abid, Mounir Sayadi","doi":"10.3389/fncom.2024.1444019","DOIUrl":"10.3389/fncom.2024.1444019","url":null,"abstract":"<p><strong>Introduction: </strong>Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline, memory loss, and impaired daily functioning. Despite significant research, AD remains incurable, highlighting the critical need for early diagnosis and intervention to improve patient outcomes. Timely detection plays a crucial role in managing the disease more effectively. Pretrained convolutional neural networks (CNNs) trained on large-scale datasets, such as ImageNet, have been employed for AD classification, providing a head start for developing more accurate models.</p><p><strong>Methods: </strong>This paper proposes a novel hybrid deep learning approach that combines the strengths of two specific pretrained architectures. The proposed model enhances the representation of AD-related patterns by leveraging the feature extraction capabilities of both networks. We validated this model using a large dataset of MRI images from AD patients. Performance was evaluated in terms of classification accuracy and robustness against noise, and the results were compared to several commonly used models in AD detection.</p><p><strong>Results: </strong>The proposed hybrid model demonstrated significant performance improvements over individual models, achieving an accuracy classification rate of 99.85%. Comparative analysis with other models further revealed the superiority of the new architecture, particularly in terms of classification rate and resistance to noise interference.</p><p><strong>Discussion: </strong>The high accuracy and robustness of the proposed hybrid model suggest its potential utility in early AD detection. By improving feature representation through the combination of two pretrained networks, this model could provide clinicians with a more reliable tool for early diagnosis and monitoring of AD progression. This approach holds promise for aiding in timely diagnoses and treatment decisions, contributing to better management of Alzheimer's disease.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"18 ","pages":"1444019"},"PeriodicalIF":2.1,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11525984/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142557513","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}
Pub Date : 2024-10-15eCollection Date: 2024-01-01DOI: 10.3389/fncom.2024.1478193
Di Gao, Guanghao Yang, Jiarun Shen, Fang Wu, Chao Ji
Introduction: Adolescence is a fundamental period of transformation, encompassing extensive physical, psychological, and behavioral changes. Effective health risk assessment during this stage is crucial for timely intervention, yet traditional methodologies often fail to accurately predict mental and behavioral health risks due to the intricacy of neural dynamics and the scarcity of quality-annotated fMRI datasets.
Methods: This study introduces an innovative deep learning-based framework for health risk assessment in adolescents by employing a combination of a two-dimensional convolutional autoencoder (2DCNN-AE) with multi-sequence learning and multi-scale asynchronous correlation information extraction techniques. This approach facilitates the intricate analysis of spatial and temporal features within fMRI data, aiming to enhance the accuracy of the risk assessment process.
Results: Upon examination using the Adolescent Risk Behavior (AHRB) dataset, which includes fMRI scans from 174 individuals aged 17-22, the proposed methodology exhibited a significant improvement over conventional models. It attained a precision of 83.116%, a recall of 84.784%, and an F1-score of 83.942%, surpassing standard benchmarks in most pertinent evaluative measures.
Discussion: The results underscore the superior performance of the deep learning-based approach in understanding and predicting health-related risks in adolescents. It underscores the value of this methodology in advancing the precision of health risk assessments, offering an enhanced tool for early detection and potential intervention strategies in this sensitive developmental stage.
{"title":"Multi-scale asynchronous correlation and 2D convolutional autoencoder for adolescent health risk prediction with limited fMRI data.","authors":"Di Gao, Guanghao Yang, Jiarun Shen, Fang Wu, Chao Ji","doi":"10.3389/fncom.2024.1478193","DOIUrl":"https://doi.org/10.3389/fncom.2024.1478193","url":null,"abstract":"<p><strong>Introduction: </strong>Adolescence is a fundamental period of transformation, encompassing extensive physical, psychological, and behavioral changes. Effective health risk assessment during this stage is crucial for timely intervention, yet traditional methodologies often fail to accurately predict mental and behavioral health risks due to the intricacy of neural dynamics and the scarcity of quality-annotated fMRI datasets.</p><p><strong>Methods: </strong>This study introduces an innovative deep learning-based framework for health risk assessment in adolescents by employing a combination of a two-dimensional convolutional autoencoder (2DCNN-AE) with multi-sequence learning and multi-scale asynchronous correlation information extraction techniques. This approach facilitates the intricate analysis of spatial and temporal features within fMRI data, aiming to enhance the accuracy of the risk assessment process.</p><p><strong>Results: </strong>Upon examination using the Adolescent Risk Behavior (AHRB) dataset, which includes fMRI scans from 174 individuals aged 17-22, the proposed methodology exhibited a significant improvement over conventional models. It attained a precision of 83.116%, a recall of 84.784%, and an F1-score of 83.942%, surpassing standard benchmarks in most pertinent evaluative measures.</p><p><strong>Discussion: </strong>The results underscore the superior performance of the deep learning-based approach in understanding and predicting health-related risks in adolescents. It underscores the value of this methodology in advancing the precision of health risk assessments, offering an enhanced tool for early detection and potential intervention strategies in this sensitive developmental stage.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"18 ","pages":"1478193"},"PeriodicalIF":2.1,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11518741/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142544667","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}