While medical imaging typically provides massive amounts of data, the extraction of relevant information for predictive diagnosis remains a difficult challenge. Functional MRI (fMRI) data, that provide an indirect measure of task-related or spontaneous neuronal activity, are classically analyzed in a mass-univariate procedure yielding statistical parametric maps. This analysis framework disregards some important principles of brain organization: population coding, distributed and overlapping representations. Multivariate pattern analysis, i.e., the prediction of behavioural variables from brain activation patterns better captures this structure. To cope with the high dimensionality of the data, the learning method has to be regularized. However, the spatial structure of the image is not taken into account in standard regularization methods, so that the extracted features are often hard to interpret. More informative and interpretable results can be obtained with the l_1 norm of the image gradient, a.k.a. its Total Variation (TV), as regularization. We apply for the first time this method to fMRI data, and show that TV regularization is well suited to the purpose of brain mapping while being a powerful tool for brain decoding. Moreover, this article presents the first use of TV regularization for classification.
并行MRI是一种快速成像技术,能够在空间中采集高分辨率图像。它依赖于$k$空间欠采样和具有互补灵敏度曲线的多个接收器线圈,以便重建完整的视场(FOV)图像。并行成像的性能主要取决于重建算法,其可以在原始$k$空间(GRAPPA、SMASH)中进行,也可以在图像域(SENSE类方法)中进行。为了提高广泛使用的SENSE算法的性能,已经有效地研究了小波域中的2D或切片特定的正则化。在本文中,我们扩展了这种方法,使用三维小波表示,以处理所有切片在一起,并解决重建文物传播相邻切片。该扩展还解释了功能性MRI(fMRI)中连续扫描之间存在的时间相关性。所提出的4D重建方案是完全\emph{unsupervised},在这个意义上,所有正则化参数估计在极大似然意义上的参考扫描。这种扩展引起的增益首先说明EPI图像重建,但也测量在快速事件相关的功能磁共振成像协议的统计灵敏度。对于不同的感兴趣对比度,并在$2\times2\times3$ mm $^3$ EPI图像上使用不同的并行加速因子,所提出的4D-UWR-SENSE算法在受试者和组水平(15个受试者)上的重建性能优于SENSE。
Spatio-temporal wavelet regularization for parallel MRI reconstruction: application to functional MRI
University of Toulouse(图卢兹大学);CEA-NeuroSpin(法国原子能和替代能源委员会-NeuroSpin);University Paris-Est(巴黎东大学)
并行MRI是一种快速成像技术,能够在空间或/和时间上采集高分辨率图像。并行成像的性能在很大程度上取决于重建算法,该算法可以在原始k空间(GRAPPA,SMASH)或图像域(SENSE类方法)中进行。为了提高广泛使用的SENSE算法的性能,在小波域中的二维或切片特定的正则化已被深入研究。在本文中,我们扩展了这种方法,使用三维小波表示,以处理所有切片在一起,并解决重建文物传播相邻切片。这种扩展(3D-无约束小波正则化-SENSE:3D-UWR-SENSE)引起的增益在不考虑时间采集的解剖图像重建上得到验证。另一个重要的扩展解释了功能性MRI(fMRI)中连续扫描之间存在的时间相关性。除了2D+t采集方案的情况下,解决了一些其他方法,如kt-FOXLS,我们的方法允许我们处理3D+t采集方案,广泛用于神经成像。所得到的3D-UWR-SENSE和4D-UWR-SENSE重建方案在参考扫描上以极大似然意义估计所有正则化参数的意义上是完全无监督的。这种扩展引起的增益在解剖和功能图像重建上示出,并且还在快速事件相关fMRI协议期间针对4D-UWR-SENSE方法的统计灵敏度方面进行测量。我们的4D-UWR-SENSE算法在受试者和组水平(15名受试者)上优于SENSE重建,适用于不同的感兴趣对比度(例如,运动或计算任务),并在2x2 x3 mm 3 EPI图像上使用不同的并行加速因子(R=2和R…
The Pictorial Cortex: Zero-Shot Cross-Subject fMRI-to-Image Reconstruction via Compositional Latent Modeling
Institute of Science and Technology for Brain-inspired Intelligence (ISTBI), Fudan University(脑启发智能科学与技术研究院,复旦大学);School of Data Science, Fudan University(复旦大学数据科学学院);Fudan ISTBI–ZJNU Algorithm Centre for Brain-Inspired Intelligence, Zhejiang Normal University(复旦ISTBI-浙师大脑启发智能算法中心,浙江师范大学);Shanghai Innovation Institute(上海创新研究院);Nanyang Technological University(南洋理工大学)
CNeuroMod-THINGS, a densely-sampled fMRI dataset for visual neuroscience
Max Planck Institute for Human Cognitive and Brain Sciences(马克斯·普朗克人类认知与脑科学研究所);Centre de recherche de l’Institut universitaire de gériatrie de Montréal(蒙特利尔大学老年医学研究中心);Université de Montréal(蒙特利尔大学);Martin Luther University Halle-Wittenberg(马丁·路德大学哈勒-维滕贝格);Université de Genève(日内瓦大学);Justus Liebig University Giessen(吉森尤斯图斯·李比希大学);Center for Mind, Brain and Behavior (CMBB), Universities of Marburg, Giessen, and Darmstadt(心智、大脑与行为中心(马尔堡大学、吉森大学和达姆施塔特工业大学))
Sharing deep generative representation for perceived image reconstruction from human brain activity
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Center for Excellence in Brain Science and Intelligence Technology, CAS(中国科学院脑科学与智能技术卓越创新中心)
Basque Center on Cognition, Brain, and Language (BCBL)(巴斯克认知、大脑与语言中心(BCBL));Athinoula A. Martinos Center for Biomedical Imaging, Harvard Medical School(哈佛医学院 Athinoula A. Martinos 生物医学成像中心);Ikerbasque, Basque Foundation for Science(伊克尔巴斯克基金会(巴斯克科学基金会));CSAIL, Massachusetts Institute of Technology (MIT)(麻省理工学院计算机科学与人工智能实验室(CSAIL))
Motion Correction and Volumetric Reconstruction for Fetal Functional Magnetic Resonance Imaging Data
Medical University of Vienna(维也纳医科大学);King's College London(伦敦国王学院);Nathan Kline Institute(内森·克莱恩研究所);Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院)
Deep Neural Encoder-Decoder Model to Relate fMRI Brain Activity with Naturalistic Stimuli
Neuro-X Institute, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland(Neuro-X研究所,瑞士联邦理工学院(EPFL),日内瓦,瑞士);Department of Radiology and Medical Informatics, University of Geneva, Geneva, Switzerland(放射学与医学信息学系,日内瓦大学,日内瓦,瑞士);Swiss Center for Affective Sciences, University of Geneva, Geneva, Switzerland(瑞士情感科学中心,日内瓦大学,日内瓦,瑞士);Geneva Neuroscience Center, University of Geneva, Geneva, Switzerland(日内瓦神经科学中心,日内瓦大学,日内瓦,瑞士)
NeuralOOD: Improving Out-of-Distribution Generalization Performance with Brain-machine Fusion Learning Framework
Faculty of Education, Capital Normal University(首都师范大学教育学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Chinese Academy of Sciences(中国科学院脑认知与类脑智能技术重点实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)