检索结果-内蒙古大学图书馆

On the benefits of self-taught learning for brain decoding

GIGASCIENCE 2023年第12期12卷 giad029页

作者： Germani, Elodie Fromont, Elisa Maumet, Camille Univ Rennes Inria CNRS InsermIRISA UMR 6074Empenn ERL U 1228 F-35000 Rennes France Univ Rennes IUF CNRS IRISA UMR 6074Inria F-35000 Rennes France

Context: We study the benefits of using a large public neuroimaging database composed of functional magnetic resonance imaging (fMRI) statistic maps, in a self-taught learning framework, for improving brain decoding on new tasks. First, we leverage the NeuroVault database to train, on a selection of relevant statistic maps, a convolutional autoencoder to reconstruct these maps. Then, we use this trained encoder to initialize a supervised convolutional neural network to classify tasks or cognitive processes of unseen statistic maps from large collections of the NeuroVault database. Results: We show that such a self-taught learning process always improves the performance of the classifiers, but the magnitude of the benefits strongly depends on the number of samples available both for pretraining and fine-tuning the models and on the complexity of the targeted downstream task. Conclusion: The pretrained model improves the classification performance and displays more generalizable features, less sensitive to individual differences.

关键词： self-taught learning brain decoding autoencoder convolutional neural network deep learning

来源：评论

学校读者我要写书评

暂无评论

Class imbalance should not throw you off balance: Choosing the right classifiers and performance metrics for brain decoding with imbalanced data

引用

NEUROIMAGE 2023年第1期277卷 120253-120253页

作者： Tholke, Philipp Mantilla-Ramos, Yorguin-Jose Abdelhedi, Hamza Maschke, Charlotte Dehgan, Arthur Harel, Yann Kemtur, Anirudha Berrada, Loubna Mekki Sahraoui, Myriam Young, Tammy Pepin, Antoine Bellemare El Khantour, Clara Landry, Mathieu Pascarella, Annalisa Hadid, Vanessa Combrisson, Etienne O'Byrne, Jordan Jerbi, Karim Univ Montreal Cognit & Computat Neurosci Lab CoCo Lab 2900Boul Edouard Montpetit Montreal PQ H3T 1J4 Canada Osnabruck Univ Inst Cognit Sci Neuer Graben 29 Schloss D-49074 Osnabruck Lower Saxony Germany Univ Antioquia Fac Med Neuropsychol & Behav Grp GRUNECO 53-108 Medellin Medellin 050010 Colombia McGill Univ Integrated Program Neurosci 1033 Pine Ave Montreal PQ H3A0G4 Canada Univ Alberta Dept Comp Sci 116 St & 85 Ave Edmonton AB T6G 2R3 Canada Concordia Univ Dept Mus 1550 De Maisonneuve Blvd W Montreal PQ H3H 1G8 Canada Natl Res Council Italy Inst Appl Math Mauro Picone Rome Italy Aix Marseille Univ Inst Neurosci Timone INT CNRS F-13005 Marseille France Mila Quebec Inst 6666 Rue St Urbain Montreal PQ H2S 3H1 Canada Quebec Neuroai AI Res Ctr UNIQUE Ctr 3744 Rue Jean Brillant Montreal PQ H3T 1P1 Canada

Machine learning (ML) is increasingly used in cognitive, computational and clinical neuroscience. The reliable and efficient application of ML requires a sound understanding of its subtleties and limitations. Training ML models on datasets with imbalanced classes is a particularly common problem, and it can have severe consequences if not adequately addressed. With the neuroscience ML user in mind, this paper provides a didactic assessment of the class imbalance problem and illustrates its impact through systematic manipulation of data imbalance ratios in (i) simulated data and (ii) brain data recorded with electroencephalography (EEG), magnetoencephalography (MEG) and functional magnetic resonance imaging (fMRI). Our results illustrate how the widely-used Accuracy (Acc) metric, which measures the overall proportion of successful predictions, yields misleadingly high performances, as class imbalance increases. Because Acc weights the per-class ratios of correct predictions proportionally to class size, it largely disregards the performance on the minority class. A binary classification model that learns to systematically vote for the majority class will yield an artificially high decoding accuracy that directly reflects the imbalance between the two classes, rather than any genuine generalizable ability to discriminate between them. We show that other evaluation metrics such as the Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC), and the less common Balanced Accuracy (BAcc) metric -defined as the arithmetic mean between sensitivity and specificity, provide more reliable performance evaluations for imbalanced data. Our findings also highlight the robustness of Random Forest (RF), and the benefits of using stratified cross-validation and hyperprameter optimization to tackle data imbalance. Critically, for neuroscience ML applications that seek to minimize overall classification error, we recommend the routine use of BAcc, which in the specifi

关键词： Class imbalance Machine learning Classification Performance metrics Electroencephalography Magnetoencephalography brain decoding Balanced accuracy

来源：评论

学校读者我要写书评

暂无评论

Interpretable, highly accurate brain decoding of subtly distinct brain states from functional MRI using intrinsic functional networks and long short-term memory recurrent neural networks

引用

NEUROIMAGE 2019年 202卷 116059-000页

作者： Li, Hongming Fan, Yong Univ Penn Perelman Sch Med Dept Radiol Ctr Biomed Image Comp & Analyt Philadelphia PA 19104 USA

decoding brain functional states underlying cognitive processes from functional MRI (fMRI) data using multivariate pattern analysis (MVPA) techniques has achieved promising performance for characterizing brain activation patterns and providing neurofeedback signals. However, it remains challenging to decode subtly distinct brain states for individual fMRI data points due to varying temporal durations and dependency among different cognitive processes. In this study, we develop a deep learning based framework for brain decoding by leveraging recent advances in intrinsic functional network modeling and sequence modeling using long short-term memory (LSTM) recurrent neural networks (RNNs). Particularly, subject-specific intrinsic functional networks (FNs) are computed from resting-state fMRI data and are used to characterize functional signals of task fMRI data with a compact representation for building brain decoding models, and LSTM RNNs are adopted to learn brain decoding mappings between functional profiles and brain states. Validation results on fMRI data from the HCP dataset have demonstrated that brain decoding models built on training data using the proposed method could learn discriminative latent feature representations and effectively distinguish subtly distinct working memory tasks of different subjects with significantly higher accuracy than conventional decoding models. Informative FNs of the brain decoding models identified as brain activation patterns of working memory tasks were largely consistent with the literature. The method also obtained promising decoding performance on motor and social cognition tasks. Our results suggest that LSTM RNNs in conjunction with FNs could build interpretable, highly accurate brain decoding models.

关键词： brain decoding Working memory Intrinsic functional networks Recurrent neural networks Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Visual Representation Model for fMRI-based brain decoding

Visual Representation Model for fMRI-based Brain Decoding

引用

2019第二届电子，通讯与控制工程国际会议

作者： Piyawat Saengpetch Luepol Pipanmemekaporn Suwatchai Kamolsantiroj Department of Computer and Information Science King Mongkut's University of Technology North Bangkok

Classification of brain activity patterns has enabled to infer what a person in mind. Among brain activity signals, functional Magnetic Resonance Imaging(fMRI) is considered as the most reliable source to decode the neural activity patterns. While fMRI-based brain decoders exist, the accuracy is often limited by lacking of training samples. Most of the existing fMRI-based brain decoders overcome the limitation by designing semantic features for encoding numerous classes and training a model to predict these encoded features from fMRI patterns. However, what kind of features for accurately decoding the fMRI patterns remain unclear. In this work, a novel fMRI-based brain decoding model is present. Unlike traditional approaches that use text-derived features, we show that visual features derived from images can be well predicted for decoding fMRI patterns. Moreover, we propose a multi-task method that effectively learns a compact but discriminative model for characterizing neural coding. Experimental results conducted on fMRI datasets demonstrated that our proposed models achieve encouraging performance compared to state-of-the-art fMRI-based brain decoders.

关键词： brain decoding fMRI Multi-task learning Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Ensembling brain Regions for brain decoding

Ensembling Brain Regions for Brain Decoding

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society

作者： Sarper Alkan Fatos T. Yarman-Vural the Department of Cognitive Science Middle East Technical University Ankara Turkey and Department of Mechatronics Engineering Cankaya University Ankara Turkey Faculty of Computer Enginering Middle East Technical University Ankara Turkey

ISBN: (纸本)9781424492695

In this study, we propose a new method which ensembles the brain regions for brain decoding. The ensemble is generated by clustering the fMRI images recorded during an experimental set-up which measures the cognitive states associated to semantic categories. Initially, voxel clusters are formed by using hierarchical agglomerative clustering with correlation as the similarity metric. Then, for each voxel cluster, a support vector machine (SVM) classifier is trained to estimate the class-posteriori probabilities. Lastly, the class-posteriori probabilities are ensembled by concatenating them under the same feature space, which are then used to train a meta-layer SVM for the final classification of the cognitive states. By using the voxel clusters, we aim to utilize the distributed, but complementing nature of the semantic representations in the brain and improve the classification accuracy. Thus, we make an existential claim that the brain regions provide a natural basis for ensemble learning which should be superior to the random clusters formed over a selected set of voxels. Our approach yields to better classification accuracies in Mitchell [1] dataset on most of the subjects, when compared to state-of-the-art which emphasizes voxel selection and ensemble learning with random subspaces.

关键词： Ensembling brain Regions brain decoding SVM

来源：评论

学校读者我要写书评

暂无评论

A cross-modal adaptation approach for brain decoding

A cross-modal adaptation approach for brain decoding

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Pouya Ghaemmaghami Moin Nabi Yan Yan Giuseppe Riccardi Nicu Sebe Department of Information Engineering and Computer Science University of Trento Italy

ISBN: (纸本)9781509041183

brain decoding has become a hot topic in many recent brain studies. In a typical neuroimaging experiment, participants are presented with different categories of stimuli while their concurrent brain activity is recorded. Then a classifier is trained on the features extracted from the recorded brain data to discriminate different target stimuli classes. It is a common practice to hypothesize that the stimulus-related information exists in the brain data if the decoder can accurately predict the target stimulus category. However, most of the neuroimaging studies suffer from few and noisy samples. These constraints affects the performance of such decoding systems. In order to cope with this limitation, a dictionary learning approach is used in this paper to transfer knowledge from the multimedia domain to the brain domain. We show that such cross-modal domain adaptation yields better performance of the learning algorithm in the brain domain. This is the first study in the direction of cross-modal adaptation by joint dictionary learning on multimedia and brain modality.

关键词： brain decoding signal processing multimedia information retrieval domain adaptation genre classification signal processing Cross-modal Cerebrum decoding information retrieval Stimuli MULTI-MEDIA SYSTEM Domain Dictionaries as Topic learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Correntropy-Based Logistic Regression With Automatic Relevance Determination for Robust Sparse brain Activity decoding

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2023年第8期70卷 2416-2429页

作者： Li, Yuanhao Chen, Badong Shi, Yuxi Yoshimura, Natsue Koike, Yasuharu Tokyo Inst Technol Inst Innovat Res Yokohama 2268503 Japan Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot XIan Peoples R China Tokyo Inst Technol Inst Innovat Res Tokyo Japan

Objective: Recent studies have used sparse classifications to predict categorical variables from high-dimensional brain activity signals to expose human's mental states and intentions, selecting the relevant features automatically in the model training process. However, existing sparse classification models will likely be prone to the performance degradation which is caused by the noise inherent in the brain recordings. To address this issue, we aim to propose a new robust and sparse classification algorithm in this study. Methods: To this end, we introduce the correntropy learning framework into the automatic relevance determination based sparse classification model, proposing a new correntropy-based robust sparse logistic regression algorithm. To demonstrate the superior brain activity decoding performance of the proposed algorithm, we evaluate it on a synthetic dataset, an electroencephalogram (EEG) dataset, and a functional magnetic resonance imaging (fMRI) dataset. Results: The extensive experimental results confirm that not only the proposed method can achieve higher classification accuracy in a noisy and high-dimensional classification task, but also it would select those more informative features for the decoding tasks. Conclusion: Integrating the correntropy learning approach with the automatic relevance determination technique will significantly improve the robustness with respect to the noise, leading to more adequate robust sparse brain decoding algorithm. Significance: It provides a more powerful approach in the real-world brain activity decoding and the brain-computer interfaces.

关键词： brain decoding correntropy learning automatic relevance determination electroencephalogram functional magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for brain Encoding and decoding 44

Deep Learning for Brain Encoding and Decoding

引用

44th Annual Meeting of the Cognitive Science Society: Cognitive Diversity, CogSci 2022

作者： Oota, Subba Reddy Arora, Jashn Gupta, Manish Bapi, Raju S. Toneva, Mariya Inria Bordeaux France IIIT Hyderabad India Microsoft Hyderabad India Princeton Neuroscience Institute United States LaBRI - Laboratoire Bordelais de Recherche en Informatique France IMN - Institut des Maladies Neurodégénératives Bordeaux France

来源：评论

学校读者我要写书评

暂无评论

Editorial: Inter- and Intra-subject Variability in brain Imaging and decoding

引用

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE 2021年 15卷 791129页

作者： Wei, Chun-Shu Keller, Corey J. Li, Junhua Lin, Yuan-Pin Nakanishi, Masaki Wagner, Johanna Wu, Wei Zhang, Yu Jung, Tzyy-Ping Natl Yang Ming Chiao Tung Univ Dept Comp Sci Hsinchu Taiwan Natl Yang Ming Chiao Tung Univ Inst Educ Hsinchu Taiwan Natl Yang Ming Chiao Tung Univ Inst Elect & Control Engn Hsinchu Taiwan Stanford Univ Dept Psychiat & Behav Sci Stanford CA USA Univ Essex Sch Comp Sci & Elect Engn Colchester Essex England Natl Sun Yat Sen Univ Inst Med Sci & Technol Kaohsiung Taiwan Natl Sun Yat Sen Univ Dept Elect Engn Kaohsiung Taiwan Univ Calif San Diego Inst Neural Computat San Diego CA USA Lehigh Univ Dept Bioengn Bethlehem PA 18015 USA

[...]questions arise about how to observe, analyze, and model inter- and intra-subject variability, what researchers might gain or lose from this variability, and how to cope with the variability in brain imaging and decoding. According to the findings, patients with different genotypes have different neuroimaging characteristics on causality connections and structural characteristics in the frontal-striatum-thalamus pathway, implying the importance of personalized clinical interventions. The authors measure and show significant test-retest reliability of neuronal activation and physiological responses associated with acute psychosocial stress using Montreal Imaging Stress Tasks. Funding This work was supported by the Ministry of Science and Technology of Taiwan (MOST 109-2222-E-009-006-MY3, 109-2221-E-110-009-MY3), the Higher Education Sprout Project of the National Yang Ming Chiao Tung University and Ministry of Education of Taiwan, the US Army Research Laboratory (W911NF2120154), the US National Science Foundation (CBET-1935860), the US National Institute of Mental Health (R01MH126639 and R01MH129018), Burroughs Wellcome Fund (Career Award for Medical Scientists), a gift to UC San Diego from The Swartz Foundation (Sag Harbor, NY), the National Natural Science Foundation of China (61806149), and the Guangdong Basic and Applied Basic Research Foundation (2020A1515010991).

关键词： human variability neuroimaging brain decoding brain-computer interface EEG MEG fMRI fNIRS

来源：评论

学校读者我要写书评

暂无评论

Perceived Image decoding From brain Activity Using Shared Information of Multi-Subject fMRI Data

引用

IEEE ACCESS 2021年 9卷 26593-26606页

作者： Akamatsu, Yusuke Harakawa, Ryosuke Ogawa, Takahiro Haseyama, Miki Hokkaido Univ Grad Sch Informat Sci & Technol Sapporo Hokkaido 0600814 Japan Nagaoka Univ Technol Dept Elect Elect & Informat Engn Nagaoka Niigata 9402188 Japan Hokkaido Univ Fac Informat Sci & Technol Sapporo Hokkaido 0600814 Japan

decoding a person's cognitive contents from evoked brain activity is becoming important in the field of brain-computer interaction. Previous studies have decoded a perceived image from functional magnetic resonance imaging (fMRI) activity by constructing brain decoding models that were trained with a single subject's fMRI data. However, accurate decoding is still challenging since fMRI data acquired from only a single subject have several disadvantageous characteristics such as small sample size, noisy nature, and high dimensionality. In this article, we propose a method to decode categories of perceived images from fMRI activity using shared information of multi-subject fMRI data. Specifically, by aggregating fMRI data of multiple subjects that contain a large number of samples, we extract a low-dimensional latent representation shared by multi-subject fMRI data. Then the latent representation is nonlinearly transformed into visual features and semantic features of the perceived images to identify categories from various candidate categories. Our approach leverages rich information obtained from multi-subject fMRI data and improves the decoding performance. Experimental results obtained by using two public fMRI datasets showed that the proposed method can more accurately decode categories of perceived images from fMRI activity than previous approaches using a single subject's fMRI data.

关键词： Functional magnetic resonance imaging Visualization decoding Semantics Data models brain modeling Bayes methods brain decoding functional magnetic resonance imaging (fMRI) multi-subject fMRI data latent variable model Bayesian inference

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：