Front Comput Neurosci [JOURNAL]
Sun
200 papers
FacialNet: facial emotion recognition for mental health analysis using UNet segmentation with transfer learning model.
Na IS, Aldrees A, Hakeem A … +6 more , Mohaisen L, Umer M, AlHammadi DA, Alsubai S, Innab N, Ashraf I
Front Comput Neurosci · 2024 · PMID 39737446 · Full text
Facial emotion recognition (FER) can serve as a valuable tool for assessing emotional states, which are often linked to mental health. However, mental health encompasses a broad range of factors that go beyond facial exp...
Facial emotion recognition (FER) can serve as a valuable tool for assessing emotional states, which are often linked to mental health. However, mental health encompasses a broad range of factors that go beyond facial expressions. While FER provides insights into certain aspects of emotional well-being, it can be used in conjunction with other assessments to form a more comprehensive understanding of an individual's mental health. This research work proposes a framework for human FER using UNet image segmentation and transfer learning with the EfficientNetB4 model (called FacialNet). The proposed model demonstrates promising results, achieving an accuracy of 90% for six emotion classes (happy, sad, fear, pain, anger, and disgust) and 96.39% for binary classification (happy and sad). The significance of FacialNet is judged by extensive experiments conducted against various machine learning and deep learning models, as well as state-of-the-art previous research works in FER. The significance of FacialNet is further validated using a cross-validation technique, ensuring reliable performance across different data splits. The findings highlight the effectiveness of leveraging UNet image segmentation and EfficientNetB4 transfer learning for accurate and efficient human facial emotion recognition, offering promising avenues for real-world applications in emotion-aware systems and effective computing platforms. Experimental findings reveal that the proposed approach performs substantially better than existing works with an improved accuracy of 96.39% compared to existing 94.26%.
Research on adverse event classification algorithm of da Vinci surgical robot based on Bert-BiLSTM model.
Li T, Zhu W, Xia W … +3 more , Wang L, Li W, Zhang P
Front Comput Neurosci · 2024 · PMID 39737445 · Full text
This study aims to enhance the classification accuracy of adverse events associated with the da Vinci surgical robot through advanced natural language processing techniques, thereby ensuring medical device safety and pro...
This study aims to enhance the classification accuracy of adverse events associated with the da Vinci surgical robot through advanced natural language processing techniques, thereby ensuring medical device safety and protecting patient health. Addressing the issues of incomplete and inconsistent adverse event records, we employed a deep learning model that combines BERT and BiLSTM to predict whether adverse event reports resulted in patient harm. We developed the Bert-BiLSTM-Att_dropout model specifically for text classification tasks with small datasets, optimizing the model's generalization ability and key information capture through the integration of dropout and attention mechanisms. Our model demonstrated exceptional performance on a dataset comprising 4,568 da Vinci surgical robot adverse event reports collected from 2013 to 2023, achieving an average F1 score of 90.15%, significantly surpassing baseline models such as GRU, LSTM, BiLSTM-Attention, and BERT. This achievement not only validates the model's effectiveness in text classification within this specific domain but also substantially improves the usability and accuracy of adverse event reporting, contributing to the prevention of medical incidents and reduction of patient harm. Furthermore, our research experimentally confirmed the model's performance, alleviating the data classification and analysis burden for healthcare professionals. Through comparative analysis, we highlighted the potential of combining BERT and BiLSTM in text classification tasks, particularly for small datasets in the medical field. Our findings advance the development of adverse event monitoring technologies for medical devices and provide critical insights for future research and enhancements.
Learning dynamic cognitive map with autonomous navigation.
de Tinguy D, Verbelen T, Dhoedt B
Front Comput Neurosci · 2024 · PMID 39723170 · Full text
Inspired by animal navigation strategies, we introduce a novel computational model to navigate and map a space rooted in biologically inspired principles. Animals exhibit extraordinary navigation prowess, harnessing memo...
Inspired by animal navigation strategies, we introduce a novel computational model to navigate and map a space rooted in biologically inspired principles. Animals exhibit extraordinary navigation prowess, harnessing memory, imagination, and strategic decision-making to traverse complex and aliased environments adeptly. Our model aims to replicate these capabilities by incorporating a dynamically expanding cognitive map over predicted poses within an active inference framework, enhancing our agent's generative model plasticity to novelty and environmental changes. Through structure learning and active inference navigation, our model demonstrates efficient exploration and exploitation, dynamically expanding its model capacity in response to anticipated novel un-visited locations and updating the map given new evidence contradicting previous beliefs. Comparative analyses in mini-grid environments with the clone-structured cognitive graph model (CSCG), which shares similar objectives, highlight our model's ability to rapidly learn environmental structures within a single episode, with minimal navigation overlap. Our model achieves this without prior knowledge of observation and world dimensions, underscoring its robustness and efficacy in navigating intricate environments.
Editorial: Symmetry as a guiding principle in artificial and brain neural networks, volume II.
Anselmi F, Patel AB
Front Comput Neurosci · 2024 · PMID 39717755 · Full text
Abstract loading — click title to view on PubMed.
A framework for optimal control of oscillations and synchrony applied to non-linear models of neural population dynamics.
Salfenmoser L, Obermayer K
Front Comput Neurosci · 2024 · PMID 39712002 · Full text
We adapt non-linear optimal control theory (OCT) to control oscillations and network synchrony and apply it to models of neural population dynamics. OCT is a mathematical framework to compute an efficient stimulation for...
We adapt non-linear optimal control theory (OCT) to control oscillations and network synchrony and apply it to models of neural population dynamics. OCT is a mathematical framework to compute an efficient stimulation for dynamical systems. In its standard formulation, it requires a well-defined reference trajectory as target state. This requirement, however, may be overly restrictive for oscillatory targets, where the exact trajectory shape might not be relevant. To overcome this limitation, we introduce three alternative cost functionals to target oscillations and synchrony without specification of a reference trajectory. We successfully apply these cost functionals to single-node and network models of neural populations, in which each node is described by either the Wilson-Cowan model or a biophysically realistic high-dimensional mean-field model of exponential integrate-and-fire neurons. We compute efficient control strategies for four different control tasks. First, we drive oscillations from a stable stationary state at a particular frequency. Second, we switch between stationary and oscillatory stable states and find a translational invariance of the state-switching control signals. Third, we switch between in-phase and out-of-phase oscillations in a two-node network, where all cost functionals lead to identical OC signals in the minimum-energy limit. Finally, we (de-) synchronize an (a-) synchronously oscillating six-node network. In this setup, for the desynchronization task, we find very different control strategies for the three cost functionals. The suggested methods represent a toolbox that enables to include oscillatory phenomena into the framework of non-linear OCT without specification of an exact reference trajectory. However, task-specific adjustments of the optimization parameters have to be performed to obtain informative results.
Spike-HAR++: an energy-efficient and lightweight parallel spiking transformer for event-based human action recognition.
Lin X, Liu M, Chen H
Front Comput Neurosci · 2024 · PMID 39659428 · Full text
Event-based cameras are suitable for human action recognition (HAR) by providing movement perception with highly dynamic range, high temporal resolution, high power efficiency and low latency. Spike Neural Networks (SNNs...
Event-based cameras are suitable for human action recognition (HAR) by providing movement perception with highly dynamic range, high temporal resolution, high power efficiency and low latency. Spike Neural Networks (SNNs) are naturally suited to deal with the asynchronous and sparse data from the event cameras due to their spike-based event-driven paradigm, with less power consumption compared to artificial neural networks. In this paper, we propose two end-to-end SNNs, namely Spike-HAR and Spike-HAR++, to introduce spiking transformer into event-based HAR. Spike-HAR includes two novel blocks: a spike attention branch, which enables model to focus on regions with high spike rates, reducing the impact of noise to improve the accuracy, and a parallel spike transformer block with simplified spiking self-attention mechanism, increasing computational efficiency. To better extract crucial information from high-level features, we modify the architecture of the spike attention branch and extend it in Spike-HAR to a higher dimension, proposing Spike-HAR++ to further enhance classification performance. Comprehensive experiments were conducted on four HAR datasets: SL-Animals-DVS, N-LSA64, DVS128 Gesture and DailyAction-DVS, to demonstrate the superior performance of our proposed model. Additionally, the proposed Spike-HAR and Spike-HAR++ require only 0.03 and 0.06 mJ, respectively, to process a sequence of event frames, with model sizes of only 0.7 and 1.8 M. This efficiency positions it as a promising new SNN baseline for the HAR community. Code is available at Spike-HAR++.
Model of the HVC neural network as a song motor in zebra finch.
Xia P, Abarbanel HDI
Front Comput Neurosci · 2024 · PMID 39635339 · Full text
The nucleus HVC within the avian song system produces crystalized instructions which lead to precise, learned vocalization in zebra finches (). This paper proposes a model of the HVC neural network based on the physiolog...
The nucleus HVC within the avian song system produces crystalized instructions which lead to precise, learned vocalization in zebra finches (). This paper proposes a model of the HVC neural network based on the physiological properties of individual HVC neurons, their synaptic interactions calibrated by experimental measurements, as well as the synaptic signal into this region which triggers song production. This neural network model comprises of two major neural populations in this area: neurons projecting to the nucleus RA and interneurons. Each single neuron model of HVC is constructed with conductance-based ion currents of fast Na and K and a leak channel, while the interneuron model includes extra transient Ca current and hyperpolarization-activated inward current. The synaptic dynamics is formed with simulated delivered neurotransmitter pulses from presynaptic cells and neurotransmitter receptor opening rates of postsynaptic neurons. We show that this network model qualitatively exhibits observed electrophysiological behaviors of neurons independent or in the network, as well as the importance of bidirectional interactions between the HVC neuron and the HVC neuron. We also simulate the pulse input from A11 neuron group to HVC. This signal successfully suppresses the interneuron, which leads to sequential firing of projection neurons that matches measured burst onset, duration, and spike quantities during the zebra finch motif. The result provides a biophysically based model characterizing the dynamics and functions of the HVC neural network as a song motor, and offers a reference for synaptic coupling strength in the avian brain.
A novel method for optimizing epilepsy detection features through multi-domain feature fusion and selection.
Kong G, Ma S, Zhao W … +3 more , Wang H, Fu Q, Wang J
Front Comput Neurosci · 2024 · PMID 39629143 · Full text
BACKGROUND: The methods used to detect epileptic seizures using electroencephalogram (EEG) signals suffer from poor accuracy in feature selection and high redundancy. This problem is addressed through the use of a novel...
BACKGROUND: The methods used to detect epileptic seizures using electroencephalogram (EEG) signals suffer from poor accuracy in feature selection and high redundancy. This problem is addressed through the use of a novel multi-domain feature fusion and selection method (PMPSO). METHOD: Discrete Wavelet Transforms (DWT) and Welch are used initially to extract features from different domains, including frequency domain, time-frequency domain, and non-linear domain. The first step in the detection process is to extract important features from different domains, such as frequency domain, time-frequency domain, and non-linear domain, using methods such as Discrete Wavelet Transform (DWT) and Welch. To extract features strongly correlated with epileptic classification detection, an improved particle swarm optimization (PSO) algorithm and Pearson correlation analysis are combined. Finally, Support Vector Machines (SVM), Artificial Neural Networks (ANN), Random Forest (RF) and XGBoost classifiers are used to construct epileptic seizure detection models based on the optimized detection features. RESULT: According to experimental results, the proposed method achieves 99.32% accuracy, 99.64% specificity, 99.29% sensitivity, and 99.32% score, respectively. CONCLUSION: The detection performance of the three classifiers is compared using 10-fold cross-validation. Surpassing other methods in detection accuracy. Consequently, this optimized method for epilepsy seizure detection enhances the diagnostic accuracy of epilepsy seizures.
Modeling functional connectivity changes during an auditory language task using line graph neural networks.
Acker S, Liang J, Sinaii N … +6 more , Wingert K, Kurosu A, Rajan S, Inati S, Theodore WH, Biassou N
Front Comput Neurosci · 2024 · PMID 39619151 · Full text
Functional connectivity (FC) refers to the activation correlation between different brain regions. FC networks as typically represented as graphs with brain regions of interest (ROIs) as nodes and functional correlation...
Functional connectivity (FC) refers to the activation correlation between different brain regions. FC networks as typically represented as graphs with brain regions of interest (ROIs) as nodes and functional correlation as edges. Graph neural networks (GNNs) are machine learning architectures used to analyze FC graphs. However, traditional GNNs are limited in their ability to characterize FC edge attributes because they typically emphasize the importance of ROI node-based brain activation data. Line GNNs convert the edges of the original graph to nodes in the transformed graph, thereby emphasizing the FC between brain regions. We hypothesize that line GNNs will outperform traditional GNNs in FC applications. We investigated the performance of two common GNN architectures (GraphSAGE and GCN) trained on line and traditional graphs predicting task-associated FC changes across two datasets. The first dataset was from the Human Connectome Project (HCP) with 205 participants, the second was a dataset with 12 participants. The HCP dataset detailed FC changes in participants during a story-listening task, while the second dataset included the FC changes in a different auditory language task. Our findings from the HCP dataset indicated that line GNNs achieved lower mean squared error compared to traditional GNNs, with the line GraphSAGE model outperforming the traditional GraphSAGE by 18% ( < 0.0001). When applying the same models to the second dataset, both line GNNs also showed statistically significant improvements over their traditional counterparts with little to no overfitting. We believe this shows that line GNN models demonstrate promising utility in FC studies.
Sex differences in brain MRI using deep learning toward fairer healthcare outcomes.
Dibaji M, Ospel J, Souza R … +1 more , Bento M
Front Comput Neurosci · 2024 · PMID 39606583 · Full text
This study leverages deep learning to analyze sex differences in brain MRI data, aiming to further advance fairness in medical imaging. We employed 3D T1-weighted Magnetic Resonance images from four diverse datasets: Cal...
This study leverages deep learning to analyze sex differences in brain MRI data, aiming to further advance fairness in medical imaging. We employed 3D T1-weighted Magnetic Resonance images from four diverse datasets: Calgary-Campinas-359, OASIS-3, Alzheimer's Disease Neuroimaging Initiative, and Cambridge Center for Aging and Neuroscience, ensuring a balanced representation of sexes and a broad demographic scope. Our methodology focused on minimal preprocessing to preserve the integrity of brain structures, utilizing a Convolutional Neural Network model for sex classification. The model achieved an accuracy of 87% on the test set without employing total intracranial volume (TIV) adjustment techniques. We observed that while the model exhibited biases at extreme brain sizes, it performed with less bias when the TIV distributions overlapped more. Saliency maps were used to identify brain regions significant in sex differentiation, revealing that certain supratentorial and infratentorial regions were important for predictions. Furthermore, our interdisciplinary team, comprising machine learning specialists and a radiologist, ensured diverse perspectives in validating the results. The detailed investigation of sex differences in brain MRI in this study, highlighted by the sex differences map, offers valuable insights into sex-specific aspects of medical imaging and could aid in developing sex-based bias mitigation strategies, contributing to the future development of fair AI algorithms. Awareness of the brain's differences between sexes enables more equitable AI predictions, promoting fairness in healthcare outcomes. Our code and saliency maps are available at https://github.com/mahsadibaji/sex-differences-brain-dl.
Editorial: Computational modeling and machine learning methods in neurodevelopment and neurodegeneration: from basic research to clinical applications.
Montobbio N, Maffulli R, Abrol A … +1 more , Martínez-Cañada P
Front Comput Neurosci · 2024 · PMID 39583891 · Full text
Abstract loading — click title to view on PubMed.
Simulated synapse loss induces depression-like behaviors in deep reinforcement learning.
Chalmers E, Duarte S, Al-Hejji X … +3 more , Devoe D, Gruber A, McDonald RJ
Front Comput Neurosci · 2024 · PMID 39569353 · Full text
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 appro...
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.
Systematic review of cognitive impairment in drivers through mental workload using physiological measures of heart rate variability.
Raza MS, Murtaza M, Cheng CT … +2 more , Muslam MMA, Albahlal BM
Front Comput Neurosci · 2024 · PMID 39544489 · Full text
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. Th...
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.
Facial emotion recognition using deep quantum and advanced transfer learning mechanism.
Alsubai S, Alqahtani A, Alanazi A … +2 more , Sha M, Gumaei A
Front Comput Neurosci · 2024 · PMID 39539995 · Full text
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, detectin...
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.
BrainNet: an automated approach for brain stress prediction utilizing electrodermal activity signal with XLNet model.
Xuanzhi L, Hakeem A, Mohaisen L … +5 more , Umer M, Khan MA, Alsenan S, Alsubai S, Innab N
Front Comput Neurosci · 2024 · PMID 39512386 · Full text
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 indivi...
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.
Latent dynamics of primary sensory cortical population activity structured by fluctuations in the local field potential.
Sederberg A, Pala A, Stanley GB
Front Comput Neurosci · 2024 · PMID 39507683 · Full text
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 th...
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.
Multi-stage semi-supervised learning enhances white matter hyperintensity segmentation.
Duarte KTN, Sidhu AS, Barros MC … +7 more , Gobbi DG, McCreary CR, Saad F, Camicioli R, Smith EE, Bento MP, Frayne R
Front Comput Neurosci · 2024 · PMID 39502452 · Full text
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 (F...
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 (-measure, , and Hausdorff distance) and found significant improvements with our method compared to conventional ( < 0.001) and transfer-learning ( < 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.
Data-centric automated approach to predict autism spectrum disorder based on selective features and explainable artificial intelligence.
Aldrees A, Ojo S, Wanliss J … +5 more , Umer M, Khan MA, Alabdullah B, Alsubai S, Innab N
Front Comput Neurosci · 2024 · PMID 39498381 · Full text
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. It...
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.
A combinatorial deep learning method for Alzheimer's disease classification-based merging pretrained networks.
Slimi H, Balti A, Abid S … +1 more , Sayadi M
Front Comput Neurosci · 2024 · PMID 39483205 · Full text
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, high...
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.
Multi-scale asynchronous correlation and 2D convolutional autoencoder for adolescent health risk prediction with limited fMRI data.
Gao D, Yang G, Shen J … +2 more , Wu F, Ji C
Front Comput Neurosci · 2024 · PMID 39473785 · Full text
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 interv...
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.
About
- Frequency
- Sun
- Papers found
- 200
- RSS feed
- Subscribe