Pub Date : 2024-07-08DOI: 10.3389/fncom.2024.1367148
Marko Wilke
The first step in spatial normalization of magnetic resonance (MR) images commonly is an affine transformation, which may be vulnerable to image imperfections (such as inhomogeneities or “unusual” heads). Additionally, common software solutions use internal starting estimates to allow for a more efficient computation, which may pose a problem in datasets not conforming to these assumptions (such as those from children). In this technical note, three main questions were addressed: one, does the affine spatial normalization step implemented in SPM12 benefit from an initial inhomogeneity correction. Two, does using a complexity-reduced image version improve robustness when matching “unusual” images. And three, can a blind “brute-force” application of a wide range of parameter combinations improve the affine fit for unusual datasets in particular. A large database of 2081 image datasets was used, covering the full age range from birth to old age. All analyses were performed in Matlab. Results demonstrate that an initial removal of image inhomogeneities improved the affine fit particularly when more inhomogeneity was present. Further, using a complexity-reduced input image also improved the affine fit and was beneficial in younger children in particular. Finally, blindly exploring a very wide parameter space resulted in a better fit for the vast majority of subjects, but again particularly so in infants and young children. In summary, the suggested modifications were shown to improve the affine transformation in the large majority of datasets in general, and in children in particular. The changes can easily be implemented into SPM12.
{"title":"A three-step, “brute-force” approach toward optimized affine spatial normalization","authors":"Marko Wilke","doi":"10.3389/fncom.2024.1367148","DOIUrl":"https://doi.org/10.3389/fncom.2024.1367148","url":null,"abstract":"The first step in spatial normalization of magnetic resonance (MR) images commonly is an affine transformation, which may be vulnerable to image imperfections (such as inhomogeneities or “unusual” heads). Additionally, common software solutions use internal starting estimates to allow for a more efficient computation, which may pose a problem in datasets not conforming to these assumptions (such as those from children). In this technical note, three main questions were addressed: one, does the affine spatial normalization step implemented in SPM12 benefit from an initial inhomogeneity correction. Two, does using a complexity-reduced image version improve robustness when matching “unusual” images. And three, can a blind “brute-force” application of a wide range of parameter combinations improve the affine fit for unusual datasets in particular. A large database of 2081 image datasets was used, covering the full age range from birth to old age. All analyses were performed in Matlab. Results demonstrate that an initial removal of image inhomogeneities improved the affine fit particularly when more inhomogeneity was present. Further, using a complexity-reduced input image also improved the affine fit and was beneficial in younger children in particular. Finally, blindly exploring a very wide parameter space resulted in a better fit for the vast majority of subjects, but again particularly so in infants and young children. In summary, the suggested modifications were shown to improve the affine transformation in the large majority of datasets in general, and in children in particular. The changes can easily be implemented into SPM12.","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141568415","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}
Pub Date : 2024-07-02DOI: 10.3389/fncom.2024.1397819
Zhixian Han, Anne B. Sereno
Many studies have shown that the human visual system has two major functionally distinct cortical visual pathways: a ventral pathway, thought to be important for object recognition, and a dorsal pathway, thought to be important for spatial cognition. According to our and others previous studies, artificial neural networks with two segregated pathways can determine objects' identities and locations more accurately and efficiently than one-pathway artificial neural networks. In addition, we showed that these two segregated artificial cortical visual pathways can each process identity and spatial information of visual objects independently and differently. However, when using such networks to process multiple objects' identities and locations, a binding problem arises because the networks may not associate each object's identity with its location correctly. In a previous study, we constrained the binding problem by training the artificial identity pathway to retain relative location information of objects. This design uses a location map to constrain the binding problem. One limitation of that study was that we only considered two attributes of our objects (identity and location) and only one possible map (location) for binding. However, typically the brain needs to process and bind many attributes of an object, and any of these attributes could be used to constrain the binding problem. In our current study, using visual objects with multiple attributes (identity, luminance, orientation, and location) that need to be recognized, we tried to find the best map (among an identity map, a luminance map, an orientation map, or a location map) to constrain the binding problem. We found that in our experimental simulations, when visual attributes are independent of each other, a location map is always a better choice than the other kinds of maps examined for constraining the binding problem. Our findings agree with previous neurophysiological findings that show that the organization or map in many visual cortical areas is primarily retinotopic or spatial.
{"title":"A spatial map: a propitious choice for constraining the binding problem","authors":"Zhixian Han, Anne B. Sereno","doi":"10.3389/fncom.2024.1397819","DOIUrl":"https://doi.org/10.3389/fncom.2024.1397819","url":null,"abstract":"Many studies have shown that the human visual system has two major functionally distinct cortical visual pathways: a ventral pathway, thought to be important for object recognition, and a dorsal pathway, thought to be important for spatial cognition. According to our and others previous studies, artificial neural networks with two segregated pathways can determine objects' identities and locations more accurately and efficiently than one-pathway artificial neural networks. In addition, we showed that these two segregated artificial cortical visual pathways can each process identity and spatial information of visual objects independently and differently. However, when using such networks to process multiple objects' identities and locations, a binding problem arises because the networks may not associate each object's identity with its location correctly. In a previous study, we constrained the binding problem by training the artificial identity pathway to retain relative location information of objects. This design uses a location map to constrain the binding problem. One limitation of that study was that we only considered two attributes of our objects (identity and location) and only one possible map (location) for binding. However, typically the brain needs to process and bind many attributes of an object, and any of these attributes could be used to constrain the binding problem. In our current study, using visual objects with multiple attributes (identity, luminance, orientation, and location) that need to be recognized, we tried to find the best map (among an identity map, a luminance map, an orientation map, or a location map) to constrain the binding problem. We found that in our experimental simulations, when visual attributes are independent of each other, a location map is always a better choice than the other kinds of maps examined for constraining the binding problem. Our findings agree with previous neurophysiological findings that show that the organization or map in many visual cortical areas is primarily retinotopic or spatial.","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141527565","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}
IntroductionConstructing an accurate and comprehensive knowledge graph of specific diseases is critical for practical clinical disease diagnosis and treatment, reasoning and decision support, rehabilitation, and health management. For knowledge graph construction tasks (such as named entity recognition, relation extraction), classical BERT-based methods require a large amount of training data to ensure model performance. However, real-world medical annotation data, especially disease-specific annotation samples, are very limited. In addition, existing models do not perform well in recognizing out-of-distribution entities and relations that are not seen in the training phase.MethodIn this study, we present a novel and practical pipeline for constructing a heart failure knowledge graph using large language models and medical expert refinement. We apply prompt engineering to the three phases of schema design: schema design, information extraction, and knowledge completion. The best performance is achieved by designing task-specific prompt templates combined with the TwoStepChat approach.ResultsExperiments on two datasets show that the TwoStepChat method outperforms the Vanillia prompt and outperforms the fine-tuned BERT-based baselines. Moreover, our method saves 65% of the time compared to manual annotation and is better suited to extract the out-of-distribution information in the real world.
{"title":"Knowledge graph construction for heart failure using large language models with prompt engineering","authors":"Tianhan Xu, Yixun Gu, Mantian Xue, Renjie Gu, Bin Li, Xiang Gu","doi":"10.3389/fncom.2024.1389475","DOIUrl":"https://doi.org/10.3389/fncom.2024.1389475","url":null,"abstract":"IntroductionConstructing an accurate and comprehensive knowledge graph of specific diseases is critical for practical clinical disease diagnosis and treatment, reasoning and decision support, rehabilitation, and health management. For knowledge graph construction tasks (such as named entity recognition, relation extraction), classical BERT-based methods require a large amount of training data to ensure model performance. However, real-world medical annotation data, especially disease-specific annotation samples, are very limited. In addition, existing models do not perform well in recognizing out-of-distribution entities and relations that are not seen in the training phase.MethodIn this study, we present a novel and practical pipeline for constructing a heart failure knowledge graph using large language models and medical expert refinement. We apply prompt engineering to the three phases of schema design: schema design, information extraction, and knowledge completion. The best performance is achieved by designing task-specific prompt templates combined with the TwoStepChat approach.ResultsExperiments on two datasets show that the TwoStepChat method outperforms the Vanillia prompt and outperforms the fine-tuned BERT-based baselines. Moreover, our method saves 65% of the time compared to manual annotation and is better suited to extract the out-of-distribution information in the real world.","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141508661","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}
Pub Date : 2024-06-28DOI: 10.3389/fncom.2024.1425008
Jyoti Arora, Ghadir Altuwaijri, Ali Nauman, Meena Tushir, Tripti Sharma, Deepali Gupta, Sung Won Kim
In clinical research, it is crucial to segment the magnetic resonance (MR) brain image for studying the internal tissues of the brain. To address this challenge in a sustainable manner, a novel approach has been proposed leveraging the power of unsupervised clustering while integrating conditional spatial properties of the image into intuitionistic clustering technique for segmenting MRI images of brain scans. In the proposed technique, an Intuitionistic-based clustering approach incorporates a nuanced understanding of uncertainty inherent in the image data. The measure of uncertainty is achieved through calculation of hesitation degree. The approach introduces a conditional spatial function alongside the intuitionistic membership matrix, enabling the consideration of spatial relationships within the image. Furthermore, by calculating weighted intuitionistic membership matrix, the algorithm gains the ability to adapt its smoothing behavior based on the local context. The main advantages are enhanced robustness with homogenous segments, lower sensitivity to noise, intensity inhomogeneity and accommodation of degree of hesitation or uncertainty that may exist in the real-world datasets. A comparative analysis of synthetic and real datasets of MR brain images proves the efficiency of the suggested approach over different algorithms. The paper investigates how the suggested research methodology performs in medical industry under different circumstances including both qualitative and quantitative parameters such as segmentation accuracy, similarity index, true positive ratio, false positive ratio. The experimental outcomes demonstrate that the suggested algorithm outperforms in retaining image details and achieving segmentation accuracy.
{"title":"Conditional spatial biased intuitionistic clustering technique for brain MRI image segmentation","authors":"Jyoti Arora, Ghadir Altuwaijri, Ali Nauman, Meena Tushir, Tripti Sharma, Deepali Gupta, Sung Won Kim","doi":"10.3389/fncom.2024.1425008","DOIUrl":"https://doi.org/10.3389/fncom.2024.1425008","url":null,"abstract":"In clinical research, it is crucial to segment the magnetic resonance (MR) brain image for studying the internal tissues of the brain. To address this challenge in a sustainable manner, a novel approach has been proposed leveraging the power of unsupervised clustering while integrating conditional spatial properties of the image into intuitionistic clustering technique for segmenting MRI images of brain scans. In the proposed technique, an Intuitionistic-based clustering approach incorporates a nuanced understanding of uncertainty inherent in the image data. The measure of uncertainty is achieved through calculation of hesitation degree. The approach introduces a conditional spatial function alongside the intuitionistic membership matrix, enabling the consideration of spatial relationships within the image. Furthermore, by calculating weighted intuitionistic membership matrix, the algorithm gains the ability to adapt its smoothing behavior based on the local context. The main advantages are enhanced robustness with homogenous segments, lower sensitivity to noise, intensity inhomogeneity and accommodation of degree of hesitation or uncertainty that may exist in the real-world datasets. A comparative analysis of synthetic and real datasets of MR brain images proves the efficiency of the suggested approach over different algorithms. The paper investigates how the suggested research methodology performs in medical industry under different circumstances including both qualitative and quantitative parameters such as segmentation accuracy, similarity index, true positive ratio, false positive ratio. The experimental outcomes demonstrate that the suggested algorithm outperforms in retaining image details and achieving segmentation accuracy.","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141508683","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}
Pub Date : 2024-06-26DOI: 10.3389/fncom.2024.1379368
Liming Cheng, Jiaqi Xiong, Junwei Duan, Yuhang Zhang, Chun Chen, Jingxin Zhong, Zhiguo Zhou, Yujuan Quan
IntroductionEpilepsy is a common neurological condition that affects a large number of individuals worldwide. One of the primary challenges in epilepsy is the accurate and timely detection of seizure. Recently, the graph regularized broad learning system (GBLS) has achieved superior performance improvement with its flat structure and less time-consuming training process compared to deep neural networks. Nevertheless, the number of feature and enhancement nodes in GBLS is predetermined. These node settings are also randomly selected and remain unchanged throughout the training process. The characteristic of randomness is thus more easier to make non-optimal nodes generate, which cannot contribute significantly to solving the optimization problem.MethodsTo obtain more optimal nodes for optimization and achieve superior automatic detection performance, we propose a novel broad neural network named self-adaptive evolutionary graph regularized broad learning system (SaE-GBLS). Self-adaptive evolutionary algorithm, which can construct mutation strategies in the strategy pool based on the experience of producing solutions for selecting network parameters, is incorporated into SaE-GBLS model for optimizing the node parameters. The epilepsy seizure is automatic detected by our proposed SaE-GBLS model based on three publicly available EEG datasets and one private clinical EEG dataset.Results and discussionThe experimental results indicate that our suggested strategy has the potential to perform as well as current machine learning approaches.
{"title":"Frontiers | SaE-GBLS: an effective self-adaptive evolutionary optimized graph-broad model for EEG-based automatic epileptic seizure detection","authors":"Liming Cheng, Jiaqi Xiong, Junwei Duan, Yuhang Zhang, Chun Chen, Jingxin Zhong, Zhiguo Zhou, Yujuan Quan","doi":"10.3389/fncom.2024.1379368","DOIUrl":"https://doi.org/10.3389/fncom.2024.1379368","url":null,"abstract":"IntroductionEpilepsy is a common neurological condition that affects a large number of individuals worldwide. One of the primary challenges in epilepsy is the accurate and timely detection of seizure. Recently, the graph regularized broad learning system (GBLS) has achieved superior performance improvement with its flat structure and less time-consuming training process compared to deep neural networks. Nevertheless, the number of feature and enhancement nodes in GBLS is predetermined. These node settings are also randomly selected and remain unchanged throughout the training process. The characteristic of randomness is thus more easier to make non-optimal nodes generate, which cannot contribute significantly to solving the optimization problem.MethodsTo obtain more optimal nodes for optimization and achieve superior automatic detection performance, we propose a novel broad neural network named self-adaptive evolutionary graph regularized broad learning system (SaE-GBLS). Self-adaptive evolutionary algorithm, which can construct mutation strategies in the strategy pool based on the experience of producing solutions for selecting network parameters, is incorporated into SaE-GBLS model for optimizing the node parameters. The epilepsy seizure is automatic detected by our proposed SaE-GBLS model based on three publicly available EEG datasets and one private clinical EEG dataset.Results and discussionThe experimental results indicate that our suggested strategy has the potential to perform as well as current machine learning approaches.","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141587737","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}
Pub Date : 2024-06-26DOI: 10.3389/fncom.2024.1418280
Lubna Kiran, Asim Zeb, Qazi Nida Ur Rehman, Taj Rahman, Muhammad Shehzad Khan, Shafiq Ahmad, Muhammad Irfan, Muhammad Naeem, Shamsul Huda, Haitham Mahmoud
Neuroscience is a swiftly progressing discipline that aims to unravel the intricate workings of the human brain and mind. Brain tumors, ranging from non-cancerous to malignant forms, pose a significant diagnostic challenge due to the presence of more than 100 distinct types. Effective treatment hinges on the precise detection and segmentation of these tumors early. We introduce a cutting-edge deep-learning approach employing a binary convolutional neural network (BCNN) to address this. This method is employed to segment the 10 most prevalent brain tumor types and is a significant improvement over current models restricted to only segmenting four types. Our methodology begins with acquiring MRI images, followed by a detailed preprocessing stage where images undergo binary conversion using an adaptive thresholding method and morphological operations. This prepares the data for the next step, which is segmentation. The segmentation identifies the tumor type and classifies it according to its grade (Grade I to Grade IV) and differentiates it from healthy brain tissue. We also curated a unique dataset comprising 6,600 brain MRI images specifically for this study. The overall performance achieved by our proposed model is 99.36%. The effectiveness of our model is underscored by its remarkable performance metrics, achieving 99.40% accuracy, 99.32% precision, 99.45% recall, and a 99.28% F-Measure in segmentation tasks.
{"title":"An enhanced pattern detection and segmentation of brain tumors in MRI images using deep learning technique","authors":"Lubna Kiran, Asim Zeb, Qazi Nida Ur Rehman, Taj Rahman, Muhammad Shehzad Khan, Shafiq Ahmad, Muhammad Irfan, Muhammad Naeem, Shamsul Huda, Haitham Mahmoud","doi":"10.3389/fncom.2024.1418280","DOIUrl":"https://doi.org/10.3389/fncom.2024.1418280","url":null,"abstract":"Neuroscience is a swiftly progressing discipline that aims to unravel the intricate workings of the human brain and mind. Brain tumors, ranging from non-cancerous to malignant forms, pose a significant diagnostic challenge due to the presence of more than 100 distinct types. Effective treatment hinges on the precise detection and segmentation of these tumors early. We introduce a cutting-edge deep-learning approach employing a binary convolutional neural network (BCNN) to address this. This method is employed to segment the 10 most prevalent brain tumor types and is a significant improvement over current models restricted to only segmenting four types. Our methodology begins with acquiring MRI images, followed by a detailed preprocessing stage where images undergo binary conversion using an adaptive thresholding method and morphological operations. This prepares the data for the next step, which is segmentation. The segmentation identifies the tumor type and classifies it according to its grade (Grade I to Grade IV) and differentiates it from healthy brain tissue. We also curated a unique dataset comprising 6,600 brain MRI images specifically for this study. The overall performance achieved by our proposed model is 99.36%. The effectiveness of our model is underscored by its remarkable performance metrics, achieving 99.40% accuracy, 99.32% precision, 99.45% recall, and a 99.28% F-Measure in segmentation tasks.","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141508684","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}
Pub Date : 2024-06-24DOI: 10.3389/fncom.2024.1426653
Elías Mateo Fernández Santoro, Arun Karim, Pascal Warnaar, Chris I. De Zeeuw, Aleksandra Badura, Mario Negrello
The investigation of the dynamics of Purkinje cell (PC) activity is crucial to unravel the role of the cerebellum in motor control, learning and cognitive processes. Within the cerebellar cortex (CC), these neurons receive all the incoming sensory and motor information, transform it and generate the entire cerebellar output. The relatively homogenous and repetitive structure of the CC, common to all vertebrate species, suggests a single computation mechanism shared across all PCs. While PC models have been developed since the 70′s, a comprehensive review of contemporary models is currently lacking. Here, we provide an overview of PC models, ranging from the ones focused on single cell intracellular PC dynamics, through complex models which include synaptic and extrasynaptic inputs. We review how PC models can reproduce physiological activity of the neuron, including firing patterns, current and multistable dynamics, plateau potentials, calcium signaling, intrinsic and synaptic plasticity and input/output computations. We consider models focusing both on somatic and on dendritic computations. Our review provides a critical performance analysis of PC models with respect to known physiological data. We expect our synthesis to be useful in guiding future development of computational models that capture real-life PC dynamics in the context of cerebellar computations.
研究浦肯野细胞(PC)的动态活动对于揭示小脑在运动控制、学习和认知过程中的作用至关重要。在小脑皮层(CC)中,这些神经元接收所有传入的感觉和运动信息,将其转化并产生整个小脑输出。小脑皮层的结构相对单一且具有重复性,是所有脊椎动物的共同特征,这表明所有小脑皮层都有一个共同的计算机制。虽然 PC 模型自上世纪 70 年代就已出现,但目前还缺乏对当代模型的全面回顾。在本文中,我们将概述 PC 模型,从侧重于单细胞胞内 PC 动态的模型,到包括突触和突触外输入的复杂模型。我们回顾了 PC 模型如何再现神经元的生理活动,包括发射模式、电流和多稳态动力学、高原电位、钙信号、内在和突触可塑性以及输入/输出计算。我们考虑的模型既关注体细胞计算,也关注树突计算。我们的综述结合已知的生理数据,对 PC 模型进行了重要的性能分析。我们希望我们的综述有助于指导未来计算模型的开发,从而在小脑计算的背景下捕捉现实生活中的PC动态。
{"title":"Frontiers | Purkinje cell models: past, present and future","authors":"Elías Mateo Fernández Santoro, Arun Karim, Pascal Warnaar, Chris I. De Zeeuw, Aleksandra Badura, Mario Negrello","doi":"10.3389/fncom.2024.1426653","DOIUrl":"https://doi.org/10.3389/fncom.2024.1426653","url":null,"abstract":"The investigation of the dynamics of Purkinje cell (PC) activity is crucial to unravel the role of the cerebellum in motor control, learning and cognitive processes. Within the cerebellar cortex (CC), these neurons receive all the incoming sensory and motor information, transform it and generate the entire cerebellar output. The relatively homogenous and repetitive structure of the CC, common to all vertebrate species, suggests a single computation mechanism shared across all PCs. While PC models have been developed since the 70′s, a comprehensive review of contemporary models is currently lacking. Here, we provide an overview of PC models, ranging from the ones focused on single cell intracellular PC dynamics, through complex models which include synaptic and extrasynaptic inputs. We review how PC models can reproduce physiological activity of the neuron, including firing patterns, current and multistable dynamics, plateau potentials, calcium signaling, intrinsic and synaptic plasticity and input/output computations. We consider models focusing both on somatic and on dendritic computations. Our review provides a critical performance analysis of PC models with respect to known physiological data. We expect our synthesis to be useful in guiding future development of computational models that capture real-life PC dynamics in the context of cerebellar computations.","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141568416","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}
Pub Date : 2024-06-24DOI: 10.3389/fncom.2024.1423051
Saeed Iqbal, Adnan N. Qureshi, Musaed Alhussein, Khursheed Aurangzeb, Imran Arshad Choudhry, Muhammad Shahid Anwar
The classification of medical images is crucial in the biomedical field, and despite attempts to address the issue, significant challenges persist. To effectively categorize medical images, collecting and integrating statistical information that accurately describes the image is essential. This study proposes a unique method for feature extraction that combines deep spatial characteristics with handmade statistical features. The approach involves extracting statistical radiomics features using advanced techniques, followed by a novel handcrafted feature fusion method inspired by the ResNet deep learning model. A new feature fusion framework (FusionNet) is then used to reduce image dimensionality and simplify computation. The proposed approach is tested on MRI images of brain tumors from the BraTS dataset, and the results show that it outperforms existing methods regarding classification accuracy. The study presents three models, including a handcrafted-based model and two CNN models, which completed the binary classification task. The recommended hybrid approach achieved a high F1 score of 96.12 ± 0.41, precision of 97.77 ± 0.32, and accuracy of 97.53 ± 0.24, indicating that it has the potential to serve as a valuable tool for pathologists.
{"title":"Hybrid deep spatial and statistical feature fusion for accurate MRI brain tumor classification","authors":"Saeed Iqbal, Adnan N. Qureshi, Musaed Alhussein, Khursheed Aurangzeb, Imran Arshad Choudhry, Muhammad Shahid Anwar","doi":"10.3389/fncom.2024.1423051","DOIUrl":"https://doi.org/10.3389/fncom.2024.1423051","url":null,"abstract":"The classification of medical images is crucial in the biomedical field, and despite attempts to address the issue, significant challenges persist. To effectively categorize medical images, collecting and integrating statistical information that accurately describes the image is essential. This study proposes a unique method for feature extraction that combines deep spatial characteristics with handmade statistical features. The approach involves extracting statistical radiomics features using advanced techniques, followed by a novel handcrafted feature fusion method inspired by the ResNet deep learning model. A new feature fusion framework (FusionNet) is then used to reduce image dimensionality and simplify computation. The proposed approach is tested on MRI images of brain tumors from the BraTS dataset, and the results show that it outperforms existing methods regarding classification accuracy. The study presents three models, including a handcrafted-based model and two CNN models, which completed the binary classification task. The recommended hybrid approach achieved a high F1 score of 96.12 ± 0.41, precision of 97.77 ± 0.32, and accuracy of 97.53 ± 0.24, indicating that it has the potential to serve as a valuable tool for pathologists.","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141508685","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}
Pub Date : 2024-06-20DOI: 10.3389/fncom.2024.1387077
Josue O. Caro, Yilong Ju, Ryan Pyle, Sourav Dey, Wieland Brendel, Fabio Anselmi, Ankit B. Patel
Adversarial attacks are still a significant challenge for neural networks. Recent efforts have shown that adversarial perturbations typically contain high-frequency features, but the root cause of this phenomenon remains unknown. Inspired by theoretical work on linear convolutional models, we hypothesize that translational symmetry in convolutional operations together with localized kernels implicitly bias the learning of high-frequency features, and that this is one of the main causes of high frequency adversarial examples. To test this hypothesis, we analyzed the impact of different choices of linear and non-linear architectures on the implicit bias of the learned features and adversarial perturbations, in spatial and frequency domains. We find that, independently of the training dataset, convolutional operations have higher frequency adversarial attacks compared to other architectural parameterizations, and that this phenomenon is exacerbated with stronger locality of the kernel (kernel size) end depth of the model. The explanation for the kernel size dependence involves the Fourier Uncertainty Principle: a spatially-limited filter (local kernel in the space domain) cannot also be frequency-limited (local in the frequency domain). Using larger convolution kernel sizes or avoiding convolutions (e.g., by using Vision Transformers or MLP-style architectures) significantly reduces this high-frequency bias. Looking forward, our work strongly suggests that understanding and controlling the implicit bias of architectures will be essential for achieving adversarial robustness.
{"title":"Translational symmetry in convolutions with localized kernels causes an implicit bias toward high frequency adversarial examples","authors":"Josue O. Caro, Yilong Ju, Ryan Pyle, Sourav Dey, Wieland Brendel, Fabio Anselmi, Ankit B. Patel","doi":"10.3389/fncom.2024.1387077","DOIUrl":"https://doi.org/10.3389/fncom.2024.1387077","url":null,"abstract":"Adversarial attacks are still a significant challenge for neural networks. Recent efforts have shown that adversarial perturbations typically contain high-frequency features, but the root cause of this phenomenon remains unknown. Inspired by theoretical work on linear convolutional models, we hypothesize that <jats:italic>translational symmetry in convolutional operations</jats:italic> together with <jats:italic>localized kernels implicitly bias the learning of high-frequency features</jats:italic>, and that this is one of the main causes of <jats:italic>high frequency adversarial examples</jats:italic>. To test this hypothesis, we analyzed the impact of different choices of linear and <jats:italic>non-linear</jats:italic> architectures on the implicit bias of the learned features and adversarial perturbations, in spatial and frequency domains. We find that, independently of the training dataset, convolutional operations have higher frequency adversarial attacks compared to other architectural parameterizations, and that this phenomenon is exacerbated with stronger locality of the kernel (kernel size) end depth of the model. The explanation for the kernel size dependence involves the Fourier Uncertainty Principle: a spatially-limited filter (local kernel in the space domain) cannot also be frequency-limited (local in the frequency domain). Using larger convolution kernel sizes or avoiding convolutions (e.g., by using Vision Transformers or MLP-style architectures) significantly reduces this high-frequency bias. Looking forward, our work strongly suggests that understanding and controlling the implicit bias of architectures will be essential for achieving adversarial robustness.","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141508686","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}
Pub Date : 2024-06-19eCollection Date: 2024-01-01DOI: 10.3389/fncom.2024.1393122
Congshan Sun, Cong Xu, Hongwei Li, Hongjian Bo, Lin Ma, Haifeng Li
Epilepsy is a common chronic brain disorder. Detecting epilepsy by observing electroencephalography (EEG) is the main method neurologists use, but this method is time-consuming. EEG signals are non-stationary, nonlinear, and often highly noisy, so it remains challenging to recognize epileptic EEG signals more accurately and automatically. This paper proposes a novel classification system of epileptic EEG signals for single-channel EEG based on the attention network that integrates time-frequency and nonlinear dynamic features. The proposed system has three novel modules. The first module constructs the Hilbert spectrum (HS) with high time-frequency resolution into a two-channel parallel convolutional network. The time-frequency features are fully extracted by complementing the high-dimensional features of the two branches. The second module constructs a grayscale recurrence plot (GRP) that contains more nonlinear dynamic features than traditional RP, fed into the residual-connected convolution module for effective learning of nonlinear dynamic features. The third module is the feature fusion module based on a self-attention mechanism to assign optimal weights to different types of features and further enhance the information extraction capability of the system. Therefore, the system is named HG-SANet. The results of several classification tasks on the Bonn EEG database and the Bern-Barcelona EEG database show that the HG-SANet can effectively capture the contribution degree of the extracted features from different domains, significantly enhance the expression ability of the model, and improve the accuracy of the recognition of epileptic EEG signals. The HG-SANet can improve the diagnosis and treatment efficiency of epilepsy and has broad application prospects in the fields of brain disease diagnosis.
癫痫是一种常见的慢性脑部疾病。通过观察脑电图(EEG)检测癫痫是神经学家使用的主要方法,但这种方法耗时较长。脑电信号是非稳态、非线性的,而且通常噪声很大,因此要更准确、更自动地识别癫痫脑电信号仍是一项挑战。本文提出了一种基于注意力网络的新型单通道脑电图信号分类系统,该系统综合了时间频率和非线性动态特征。该系统有三个新颖的模块。第一个模块在双通道并行卷积网络中构建具有高时频分辨率的希尔伯特频谱(HS)。通过对两个分支的高维特征进行补充,充分提取时频特征。第二个模块是构建灰度递归图(GRP),它比传统的 RP 包含更多的非线性动态特征,并将其输入残差连接卷积模块,以有效学习非线性动态特征。第三个模块是基于自注意机制的特征融合模块,为不同类型的特征分配最佳权重,进一步提高系统的信息提取能力。因此,该系统被命名为 HG-SANet。在波恩脑电数据库和伯尔尼-巴塞罗那脑电数据库上进行的多项分类任务结果表明,HG-SANet 能有效捕捉不同领域提取特征的贡献度,显著增强模型的表达能力,提高癫痫脑电信号的识别准确率。HG-SANet可以提高癫痫的诊断和治疗效率,在脑疾病诊断领域具有广阔的应用前景。
{"title":"A novel multi-feature fusion attention neural network for the recognition of epileptic EEG signals.","authors":"Congshan Sun, Cong Xu, Hongwei Li, Hongjian Bo, Lin Ma, Haifeng Li","doi":"10.3389/fncom.2024.1393122","DOIUrl":"10.3389/fncom.2024.1393122","url":null,"abstract":"<p><p>Epilepsy is a common chronic brain disorder. Detecting epilepsy by observing electroencephalography (EEG) is the main method neurologists use, but this method is time-consuming. EEG signals are non-stationary, nonlinear, and often highly noisy, so it remains challenging to recognize epileptic EEG signals more accurately and automatically. This paper proposes a novel classification system of epileptic EEG signals for single-channel EEG based on the attention network that integrates time-frequency and nonlinear dynamic features. The proposed system has three novel modules. The first module constructs the Hilbert spectrum (HS) with high time-frequency resolution into a two-channel parallel convolutional network. The time-frequency features are fully extracted by complementing the high-dimensional features of the two branches. The second module constructs a grayscale recurrence plot (GRP) that contains more nonlinear dynamic features than traditional RP, fed into the residual-connected convolution module for effective learning of nonlinear dynamic features. The third module is the feature fusion module based on a self-attention mechanism to assign optimal weights to different types of features and further enhance the information extraction capability of the system. Therefore, the system is named HG-SANet. The results of several classification tasks on the Bonn EEG database and the Bern-Barcelona EEG database show that the HG-SANet can effectively capture the contribution degree of the extracted features from different domains, significantly enhance the expression ability of the model, and improve the accuracy of the recognition of epileptic EEG signals. The HG-SANet can improve the diagnosis and treatment efficiency of epilepsy and has broad application prospects in the fields of brain disease diagnosis.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11219577/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141497603","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}