E. Olivetti, Thien Bao Nguyen, E. Garyfallidis, Nivedita Agarwal, P. Avesani
We developed a novel interactive system for human brain tractography segmentation to assist neuroanatomists in identifying white matter anatomical structures of interest from diffusion magnetic resonance imaging (dMRI) data. The difficulty in segmenting and navigating tractographies lies in the very large number of reconstructed neuronal pathways, i.e. the streamlines, which are in the order of hundreds of thousands with modern dMRI techniques. The novelty of our system resides in presenting the user a clustered version of the tractography in which she selects some of the clusters to identify a superset of the streamlines of interest. This superset is then re-clustered at a finer scale and again the user is requested to select the relevant clusters. The process of re-clustering and manual selection is iterated until the remaining streamlines faithfully represent the desired anatomical structure of interest. In this work we present a solution to solve the computational issue of clustering a large number of streamlines under the strict time constraints requested by the interactive use. The solution consists in embedding the streamlines into a Euclidean space and then in adopting a state-of-the art scalable implementation of the k-means algorithm. We tested the proposed system on tractographies from amyotrophic lateral sclerosis (ALS) patients and healthy subjects that we collected for a forthcoming study about the systematic differences between their corticospinal tracts.
{"title":"Fast Clustering for Interactive Tractography Segmentation","authors":"E. Olivetti, Thien Bao Nguyen, E. Garyfallidis, Nivedita Agarwal, P. Avesani","doi":"10.1109/PRNI.2013.20","DOIUrl":"https://doi.org/10.1109/PRNI.2013.20","url":null,"abstract":"We developed a novel interactive system for human brain tractography segmentation to assist neuroanatomists in identifying white matter anatomical structures of interest from diffusion magnetic resonance imaging (dMRI) data. The difficulty in segmenting and navigating tractographies lies in the very large number of reconstructed neuronal pathways, i.e. the streamlines, which are in the order of hundreds of thousands with modern dMRI techniques. The novelty of our system resides in presenting the user a clustered version of the tractography in which she selects some of the clusters to identify a superset of the streamlines of interest. This superset is then re-clustered at a finer scale and again the user is requested to select the relevant clusters. The process of re-clustering and manual selection is iterated until the remaining streamlines faithfully represent the desired anatomical structure of interest. In this work we present a solution to solve the computational issue of clustering a large number of streamlines under the strict time constraints requested by the interactive use. The solution consists in embedding the streamlines into a Euclidean space and then in adopting a state-of-the art scalable implementation of the k-means algorithm. We tested the proposed system on tractographies from amyotrophic lateral sclerosis (ALS) patients and healthy subjects that we collected for a forthcoming study about the systematic differences between their corticospinal tracts.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116106408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
B. Hunyadi, Marco Signoretto, S. Debener, S. Huffel, M. Vos
Choosing an appropriate approach for single-trial EEG classification is a key factor in brain computer interfaces (BCIs). Here we consider an auditory oddball paradigm, recorded in normal indoor and walking outdoor conditions. The signal of interest, namely the P300 component of the event related potential (ERP), unlike noise, is a structured signal in the multidimensional space spanned by channels, time and frequency or possibly other types of features. Therefore, we apply spectral regularization using nuclear norm on a tensorial representation of the EEG data. Due to the a-priori structural information conveyed by the nuclear norm penalty, we expect an improved performance compared to traditional approaches, especially under noisy conditions and in case of small sample sizes.
{"title":"Classification of Structured EEG Tensors Using Nuclear Norm Regularization: Improving P300 Classification","authors":"B. Hunyadi, Marco Signoretto, S. Debener, S. Huffel, M. Vos","doi":"10.1109/PRNI.2013.34","DOIUrl":"https://doi.org/10.1109/PRNI.2013.34","url":null,"abstract":"Choosing an appropriate approach for single-trial EEG classification is a key factor in brain computer interfaces (BCIs). Here we consider an auditory oddball paradigm, recorded in normal indoor and walking outdoor conditions. The signal of interest, namely the P300 component of the event related potential (ERP), unlike noise, is a structured signal in the multidimensional space spanned by channels, time and frequency or possibly other types of features. Therefore, we apply spectral regularization using nuclear norm on a tensorial representation of the EEG data. Due to the a-priori structural information conveyed by the nuclear norm penalty, we expect an improved performance compared to traditional approaches, especially under noisy conditions and in case of small sample sizes.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"356 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122766788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Karen Sandø Ambrosen, Tue Herlau, T. Dyrby, Mikkel N. Schmidt, Morten Mørup
The growing focus in neuroimaging on analyzing brain connectivity calls for powerful and reliable statistical modeling tools. We examine the Infinite Relational Model (IRM) as a tool to identify and compare structure in brain connectivity graphs by contrasting its performance on graphs from the same subject versus graphs from different subjects. The inferred structure is most consistent between graphs from the same subject, however, the model is able to predict links in graphs from different subjects on par with results within a subject. The framework proposed can be used as a statistical modeling tool for the identification of structure and quantification of similarity in graphs of brain connectivity in general.
{"title":"Comparing Structural Brain Connectivity by the Infinite Relational Model","authors":"Karen Sandø Ambrosen, Tue Herlau, T. Dyrby, Mikkel N. Schmidt, Morten Mørup","doi":"10.1109/PRNI.2013.22","DOIUrl":"https://doi.org/10.1109/PRNI.2013.22","url":null,"abstract":"The growing focus in neuroimaging on analyzing brain connectivity calls for powerful and reliable statistical modeling tools. We examine the Infinite Relational Model (IRM) as a tool to identify and compare structure in brain connectivity graphs by contrasting its performance on graphs from the same subject versus graphs from different subjects. The inferred structure is most consistent between graphs from the same subject, however, the model is able to predict links in graphs from different subjects on par with results within a subject. The framework proposed can be used as a statistical modeling tool for the identification of structure and quantification of similarity in graphs of brain connectivity in general.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126428883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Machine learning has obvious applications to the diagnosis of disease, and for many neurological conditions features extracted from brain images allow classifiers based on neuroimaging biomarkers to provide a useful complement to more traditional diagnostic methods based on symptoms and psychological testing. However the labels used in the training of such systems frequently depend on standard clinical diagnostic methods, meaning they are not completely reliable in many cases. This uncertainty makes the problems this causes hard to study, as it is difficult to measure both the extent of mislabelling and its effect on results. To avoid this problem, we perform classification of gender based on imaging, as this is definitely known for each subject. We then deliberately make known proportions of the training labels incorrect. This allows us to assess the effect of the level of label noise on classification accuracy, and evaluate methods that allow for the mislabelled data. The methods are wrappers using existing well known classifier algorithms. The results indicate that the methods can be significantly effective at realistic levels of noise in the training labels, but care must be taken in choosing which method to apply depending on the level of label noise.
{"title":"Wrapper Methods to Correct Mislabelled Training Data","authors":"Jonathan Young, J. Ashburner, S. Ourselin","doi":"10.1109/PRNI.2013.51","DOIUrl":"https://doi.org/10.1109/PRNI.2013.51","url":null,"abstract":"Machine learning has obvious applications to the diagnosis of disease, and for many neurological conditions features extracted from brain images allow classifiers based on neuroimaging biomarkers to provide a useful complement to more traditional diagnostic methods based on symptoms and psychological testing. However the labels used in the training of such systems frequently depend on standard clinical diagnostic methods, meaning they are not completely reliable in many cases. This uncertainty makes the problems this causes hard to study, as it is difficult to measure both the extent of mislabelling and its effect on results. To avoid this problem, we perform classification of gender based on imaging, as this is definitely known for each subject. We then deliberately make known proportions of the training labels incorrect. This allows us to assess the effect of the level of label noise on classification accuracy, and evaluate methods that allow for the mislabelled data. The methods are wrappers using existing well known classifier algorithms. The results indicate that the methods can be significantly effective at realistic levels of noise in the training labels, but care must be taken in choosing which method to apply depending on the level of label noise.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130549471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Luca Dodero, Sebastiano Vascon, L. Giancardo, A. Gozzi, Diego Sona, Vittorio Murino
We present an unsupervised approach based on the Dominant Sets framework to automatically segment the white matter fibers into bundles. This framework, rooted in the Game Theory, allows for the automatic determination of the number of clusters from the data itself, without any prior assumption. The clustered bundles are a key information for the generation of unbiased structural connectivity atlases. We have thoroughly validated our algorithm both quantitatively and qualitatively. Indeed, we used biologically plausible synthetic datasets to numerically validate the performance in terms of Precision, Recall and other measures employed in the literature. We also evaluated the algorithm on a real Diffusion Tensor Imaging tractography of a whole mouse brain obtaining promising results. In fact, some of the most prominent brain structures determined by the algorithm correspond to white matter expected anatomy.
{"title":"Automatic White Matter Fiber Clustering Using Dominant Sets","authors":"Luca Dodero, Sebastiano Vascon, L. Giancardo, A. Gozzi, Diego Sona, Vittorio Murino","doi":"10.1109/PRNI.2013.62","DOIUrl":"https://doi.org/10.1109/PRNI.2013.62","url":null,"abstract":"We present an unsupervised approach based on the Dominant Sets framework to automatically segment the white matter fibers into bundles. This framework, rooted in the Game Theory, allows for the automatic determination of the number of clusters from the data itself, without any prior assumption. The clustered bundles are a key information for the generation of unbiased structural connectivity atlases. We have thoroughly validated our algorithm both quantitatively and qualitatively. Indeed, we used biologically plausible synthetic datasets to numerically validate the performance in terms of Precision, Recall and other measures employed in the literature. We also evaluated the algorithm on a real Diffusion Tensor Imaging tractography of a whole mouse brain obtaining promising results. In fact, some of the most prominent brain structures determined by the algorithm correspond to white matter expected anatomy.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125628783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sofie Therese Hansen, Carsten Stahlhut, L. K. Hansen
EEG imaging, the estimation of the cortical source distribution from scalp electrode measurements, poses an extremely ill-posed inverse problem. Recent work by Delorme et al. (2012) supports the hypothesis that distributed source solutions are sparse. We show that direct search for sparse solutions as implemented by the Variational Garrote (Kappen, 2011) provides excellent estimates compared with other widely used schemes, is computationally attractive, and by its separation of 'where' and 'what' degrees of freedom paves the road for the introduction of genuine prior information.
{"title":"Sparse Source EEG Imaging with the Variational Garrote","authors":"Sofie Therese Hansen, Carsten Stahlhut, L. K. Hansen","doi":"10.1109/PRNI.2013.36","DOIUrl":"https://doi.org/10.1109/PRNI.2013.36","url":null,"abstract":"EEG imaging, the estimation of the cortical source distribution from scalp electrode measurements, poses an extremely ill-posed inverse problem. Recent work by Delorme et al. (2012) supports the hypothesis that distributed source solutions are sparse. We show that direct search for sparse solutions as implemented by the Variational Garrote (Kappen, 2011) provides excellent estimates compared with other widely used schemes, is computationally attractive, and by its separation of 'where' and 'what' degrees of freedom paves the road for the introduction of genuine prior information.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133519309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study quantifies the effects of health and lifestyle markers on individual brain aging in dementia-free elderly subjects, revealed by a relevance vector regression approach. In males, markers of metabolic syndrome as well as alcohol abuse were significantly related to increased Brain AGE scores of up to 9 years. In females, markers of healthy liver and kidney functions and an adequate supply of nutrients were significantly related to decreased Brain AGE scores.
{"title":"Gender-Specific Effects of Health and Lifestyle Markers on Individual BrainAGE","authors":"K. Franke, M. Ristow, Christian Gaser","doi":"10.1109/PRNI.2013.33","DOIUrl":"https://doi.org/10.1109/PRNI.2013.33","url":null,"abstract":"This study quantifies the effects of health and lifestyle markers on individual brain aging in dementia-free elderly subjects, revealed by a relevance vector regression approach. In males, markers of metabolic syndrome as well as alcohol abuse were significantly related to increased Brain AGE scores of up to 9 years. In females, markers of healthy liver and kidney functions and an adequate supply of nutrients were significantly related to decreased Brain AGE scores.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"270 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121307356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. H. Kefayati, H. Sheikhzadeh, H. Rabiee, A. Soltani-Farani
Functional behavior of the brain can be captured using functional Magnetic Resonance Imaging (fMRI). Even though fMRI signals have temporal and spatial structures, most studies have neglected the temporal structure when inferring mental states (brain decoding). This has two main side effects: 1. Degradation in brain decoding performance due to lack of temporal information in the model, 2. Inability to provide temporal interpretability. Few studies have targeted this issue but have had less success due to the burdening challenges related to high feature-to-instance ratio. In this study, a novel model for incorporating temporal information while maintaining a low feature-to-instance ratio, is proposed. Experimental results show the effectiveness of the model compared to recent state of the art approaches.
{"title":"Semi-spatiotemporal fMRI Brain Decoding","authors":"M. H. Kefayati, H. Sheikhzadeh, H. Rabiee, A. Soltani-Farani","doi":"10.1109/PRNI.2013.54","DOIUrl":"https://doi.org/10.1109/PRNI.2013.54","url":null,"abstract":"Functional behavior of the brain can be captured using functional Magnetic Resonance Imaging (fMRI). Even though fMRI signals have temporal and spatial structures, most studies have neglected the temporal structure when inferring mental states (brain decoding). This has two main side effects: 1. Degradation in brain decoding performance due to lack of temporal information in the model, 2. Inability to provide temporal interpretability. Few studies have targeted this issue but have had less success due to the burdening challenges related to high feature-to-instance ratio. In this study, a novel model for incorporating temporal information while maintaining a low feature-to-instance ratio, is proposed. Experimental results show the effectiveness of the model compared to recent state of the art approaches.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126431167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a new method for the analysis of fMRI time series. The aim is to identify functionally-relevant transient "bursts" of inter-regional coupling between brain areas, using a fully data-driven approach. We use inter-subjects synchronization (i.e. correlation between time series of different subjects who are presented with the same sensory input) to isolate relevant transients in the fMRI time series. Next, we apply a first cluster analysis to group together areas that show such synchronized activity in a concurrent manner. Finally, a second cluster analysis identifies patterns of the fMRI signal that repeat consistently across the different transients. The final output of the analysis is a set of networks that show transient patterns of functionally relevant fMRI signal, consistently over specific windows of the time series. Importantly, the fMRI signal can differ between different areas belonging to the same network. This new approach is particularly suited to investigate multi-components control processes using naturalistic stimuli during fMRI.
{"title":"Detection of Transient Inter-regional Coupling in fMRI Time Series: A New Method Combining Inter-subjects Synchronization and Cluster-Analyses","authors":"Cécile Bordier, E. Macaluso","doi":"10.1109/PRNI.2013.39","DOIUrl":"https://doi.org/10.1109/PRNI.2013.39","url":null,"abstract":"We present a new method for the analysis of fMRI time series. The aim is to identify functionally-relevant transient \"bursts\" of inter-regional coupling between brain areas, using a fully data-driven approach. We use inter-subjects synchronization (i.e. correlation between time series of different subjects who are presented with the same sensory input) to isolate relevant transients in the fMRI time series. Next, we apply a first cluster analysis to group together areas that show such synchronized activity in a concurrent manner. Finally, a second cluster analysis identifies patterns of the fMRI signal that repeat consistently across the different transients. The final output of the analysis is a set of networks that show transient patterns of functionally relevant fMRI signal, consistently over specific windows of the time series. Importantly, the fMRI signal can differ between different areas belonging to the same network. This new approach is particularly suited to investigate multi-components control processes using naturalistic stimuli during fMRI.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116795741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Viviana Siless, Sergio Medina, G. Varoquaux, B. Thirion
Diffusion-weighted Magnetic Resonance Imaging (dMRI) can unveil the microstructure of the brain white matter. The analysis of the anisotropy observed in the dMRI contrast with tractography methods can help to understand the pattern of connections between brain regions and characterize neurological diseases. Because of the amount of information produced by such analyses and the errors carried by the reconstruction step, it is necessary to simplify this output. Clustering algorithms can be used to group samples that are similar according to a given metric. We propose to explore the well-known clustering algorithm k-means and a recently available one, Quick Bundles [1]. We propose an efficient procedure to associate k-means with Point Density Model, a recently proposed metric to analyze geometric structures. We analyze the performance and usability of these algorithms on manually labeled data and a database a 10 subjects.
弥散加权磁共振成像(dMRI)可以揭示脑白质的微观结构。dMRI观察到的各向异性与神经束造影方法的对比分析可以帮助理解脑区域之间的连接模式和表征神经系统疾病。由于这种分析产生的信息量和重建步骤所带来的误差，有必要简化这种输出。聚类算法可用于根据给定的度量对相似的样本进行分组。我们建议探索著名的聚类算法k-means和最近可用的Quick Bundles[1]。我们提出了一种将k-means与最近提出的用于分析几何结构的度量点密度模型(Point Density Model)相关联的有效方法。我们分析了这些算法在人工标记数据和包含10个主题的数据库上的性能和可用性。
{"title":"A Comparison of Metrics and Algorithms for Fiber Clustering","authors":"Viviana Siless, Sergio Medina, G. Varoquaux, B. Thirion","doi":"10.1109/PRNI.2013.56","DOIUrl":"https://doi.org/10.1109/PRNI.2013.56","url":null,"abstract":"Diffusion-weighted Magnetic Resonance Imaging (dMRI) can unveil the microstructure of the brain white matter. The analysis of the anisotropy observed in the dMRI contrast with tractography methods can help to understand the pattern of connections between brain regions and characterize neurological diseases. Because of the amount of information produced by such analyses and the errors carried by the reconstruction step, it is necessary to simplify this output. Clustering algorithms can be used to group samples that are similar according to a given metric. We propose to explore the well-known clustering algorithm k-means and a recently available one, Quick Bundles [1]. We propose an efficient procedure to associate k-means with Point Density Model, a recently proposed metric to analyze geometric structures. We analyze the performance and usability of these algorithms on manually labeled data and a database a 10 subjects.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"IA-19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126561637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：