Filters








179 Hits in 4.4 sec

Bayesian Learning of Probabilistic Dipole Inversion for Quantitative Susceptibility Mapping [article]

Jinwei Zhang, Hang Zhang, Mert Sabuncu, Pascal Spincemaille, Thanh Nguyen, Yi Wang
2020 arXiv   pre-print
A learning-based posterior distribution estimation method, Probabilistic Dipole Inversion (PDI), is proposed to solve quantitative susceptibility mapping (QSM) inverse problem in MRI with uncertainty estimation  ...  In PDI, such CNN is firstly trained on healthy subjects dataset with labels by maximizing the posterior Gaussian distribution loss function as used in Bayesian deep learning.  ...  Conclusion We developed a Bayesian dipole inversion framework for quantitative susceptibility mapping by combining variational inference and Bayesian deep learning.  ... 
arXiv:2004.12573v1 fatcat:doixboxtnjafpo7waly5vaq7uy

Probabilistic Dipole Inversion for Adaptive Quantitative Susceptibility Mapping [article]

Jinwei Zhang, Hang Zhang, Mert Sabuncu, Pascal Spincemaille, Thanh Nguyen, Yi Wang
2021 arXiv   pre-print
A learning-based posterior distribution estimation method, Probabilistic Dipole Inversion (PDI), is proposed to solve the quantitative susceptibility mapping (QSM) inverse problem in MRI with uncertainty  ...  In PDI, a deep convolutional neural network (CNN) is used to represent the multivariate Gaussian distribution as the approximate posterior distribution of susceptibility given the input measured field.  ...  Acknowledgments The authors would like to thank Adrian Dalca for useful feedback and discussions.  ... 
arXiv:2009.04251v6 fatcat:po67cugrmnfdxlzcz5mffrd5aa

Electrophysiological Source Imaging: A Noninvasive Window to Brain Dynamics

Bin He, Abbas Sohrabpour, Emery Brown, Zhongming Liu
2018 Annual Review of Biomedical Engineering  
It offers increasingly improved spatial resolution and intrinsically high temporal resolution for imaging large-scale brain activity and connectivity on a wide range of timescales.  ...  We review methodological developments in electrophysiological source imaging over the past three decades and envision its future advancement into a powerful functional neuroimaging technology for basic  ...  Given the Bayes' theorem, Bayesian algorithms maximize the posterior distribution of sources given measurements while assuming a prior probabilistic distribution of the sources.  ... 
doi:10.1146/annurev-bioeng-062117-120853 pmid:29494213 pmcid:PMC7941524 fatcat:xypqgl7snbbnnidrn5ddepj6tu

Image Reconstruction in Electrical Impedance Tomography Based on Structure-Aware Sparse Bayesian Learning

Shengheng Liu, Jiabin Jia, Yimin D. Zhang, Yunjie Yang
2018 IEEE Transactions on Medical Imaging  
Index Terms-Inverse problem, electrical impedance tomography (EIT), sparse Bayesian learning (SBL), image reconstruction, maximum a posteriori (MAP) estimation.  ...  In this paper, we propose an efficient and highresolution EIT image reconstruction method in the framework of sparse Bayesian learning.  ...  Roininen at the Sodankylä Geophysical Observatory, University of Oulu, and Dr. Z.-L. Zhang at the AT&T, for helpful discussions.  ... 
doi:10.1109/tmi.2018.2816739 pmid:29994084 fatcat:knq4bi6mpbcs7il7c4pnkw5ql4

Data-driven modeling of time-domain induced polarization [article]

Charles L. Bérubé, Pierre Bérubé
2021 arXiv   pre-print
We demonstrate four applications of VAEs to model and process IP data: (1) representative synthetic data generation, (2) unsupervised Bayesian denoising and data uncertainty estimation, (3) quantitative  ...  VAEs are Bayesian neural networks that aim to learn a latent statistical distribution to encode extensive data sets as lower dimension representations.  ...  Bayesian framework Broadly speaking, VAE are probabilistic AE.  ... 
arXiv:2107.14796v1 fatcat:jjarbdicbfgytigpj62qlzhybe

Molecule Identification with Rotational Spectroscopy and Probabilistic Deep Learning [article]

Michael C. McCarthy, Kin Long Kelvin Lee
2020 arXiv   pre-print
A proof-of-concept framework for identifying molecules of unknown elemental composition and structure using experimental rotational data and probabilistic deep learning is presented.  ...  In each model, we utilize dropout layers as an approximation to Bayesian sampling, which subsequently generates probabilistic predictions from otherwise deterministic models.  ...  Supporting Information Available The following files are available free of charge. Dataset used for the model training can be made available upon request.  ... 
arXiv:2003.12388v2 fatcat:t7n2ichaondllh3lreebccj5zi

Active Inference, Curiosity and Insight

Karl J. Friston, Marco Lin, Christopher D. Frith, Giovanni Pezzulo, J. Allan Hobson, Sasha Ondobaka
2017 Neural Computation  
We use simulations of abstract rule learning and approximate Bayesian inference to show that minimizing (expected) variational free energy leads to active sampling of novel contingencies.  ...  This article offers a formal account of curiosity and insight in terms of active (Bayesian) inference.  ...  We thank our reviewers for detailed and helpful guidance in reporting this work. Disclosure Statement We have no disclosures or conflict of interest.  ... 
doi:10.1162/neco_a_00999 pmid:28777724 fatcat:vdshax4ocbfzhkbg5dvwqspnoi

Electromagnetic Source Imaging via a Data-Synthesis-Based Denoising Autoencoder [article]

Gexin Huang, Zhu Liang Yu, Wei Wu, Ke Liu, ZhengHui Gu, Feifei Qi, YuanQing Li, Jiawen Liang
2021 arXiv   pre-print
All the generated data are used to drive the neural network to automatically learn inverse mapping.  ...  Inspired by deep learning approaches, a novel data-synthesized spatio-temporal denoising autoencoder method (DST-DAE) method was proposed to solve the ESI inverse problem.  ...  Sparse Bayesian learning approaches (SBL) [12] - [14] cast the inverse problem under a empirical Bayesian framework where hyperparameters can be automatically determined and sparse solutions can be  ... 
arXiv:2010.12876v5 fatcat:ksayyliw3rg6nkkbhirukk4gq4

Pathomechanisms of HIV-Associated Cerebral Small Vessel Disease: A Comprehensive Clinical and Neuroimaging Protocol and Analysis Pipeline

Kyle D Murray, Meera V Singh, Yuchuan Zhuang, Md Nasir Uddin, Xing Qiu, Miriam T Weber, Madalina E Tivarus, Henry Z Wang, Bogachan Sahin, Jianhui Zhong, Sanjay B Maggirwar, Giovanni Schifitto
2020 Frontiers in Neurology  
, tissue susceptibility, and blood perfusion.  ...  Methods and Design: Subjects are followed for three years and evaluated by flow cytometric analysis of whole blood (to measure platelet activation, platelet monocyte complexes, and markers of monocyte  ...  ACKNOWLEDGMENTS We would like to acknowledge the contributions of additional team members to the efforts of this study, including study coordination, statistical support, image processing assistance, and  ... 
doi:10.3389/fneur.2020.595463 pmid:33384655 pmcid:PMC7769815 fatcat:mdxpzurd7zazbbq77x5zbhadxu

Performance evaluation of inverse methods for identification and characterization of oscillatory brain sources: Ground truth validation & empirical evidences [article]

Tamesh Halder, Siddharth Talwar, Amit Jaiswal, Arpan Banerjee
2018 bioRxiv   pre-print
Often, to extract source level information in the cortex, researchers have to rely on inverse techniques that generate probabilistic estimation of the cortical activation underlying EEG/ MEG data from  ...  First, we simulated EEG data with point dipole (single and two-point), as well as, distributed dipole modelling techniques to validate the accuracy and sensitivity of each one of these methods of source  ...  Though, dynamic statistical parametric mapping (dSPM) (Liu et al., 2002) and sparse Bayesian learning (SBL) (Ramírez et al., 2010) has been developed to improve upon the estimates of spatial filter  ... 
doi:10.1101/395780 fatcat:4je4kj7upzfenf6rnhtg2gtofe

Proceedings: ISBET 200 – 14th World Congress of the International Society for Brain Electromagnetic Topography, November 19-23, 2003

Yoshio Okada
2003 Brain Topography  
Strengths and weakness of several forward and inverse methods will be discussed. ).  ...  A standardized realistic head model, 3D whole head and cortical mapping, and various inverse source algorithms have been implemented in a highly interactive source analysis module.  ...  of the subject's anatomical information, does not require prior determination of the number of dipoles, and yields quantitative probabilistic inferences that are one of the hallmarks of the Bayesian inference  ... 
doi:10.1023/b:brat.0000019284.29068.8d fatcat:tpvp3dcojrczjkuzcu3xefyizy

Reconstruction of the lattice Hamiltonian models from the observations of microscopic degrees of freedom in the presence of competing interactions [article]

Sai Mani Prudhvi Valleti, Lukas Vlcek, Maxim Ziatdinov, Rama K. Vasudevan, Sergei V. Kalinin
2020 arXiv   pre-print
The emergence of scanning probe and electron beam imaging techniques have allowed quantitative studies of atomic structure and minute details of electronic and vibrational structure on the level of individual  ...  Here, we explore the reconstruction of exchange integrals in the Hamiltonian for the lattice model with two competing interactions from the observations of the microscopic degrees of freedom and establish  ...  Machine learning analysis of the phase diagram An alternative approach for mapping phase diagrams in simulated lattice models is based on the machine learning and statistical analysis of the local spin  ... 
arXiv:2001.06854v1 fatcat:tdf4zvvn6jbk5kdt3aaiftnscu

2020 Index IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 13

2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
., +, JSTARS 2020 632-641 Potential of Ensemble Learning to Improve Tree-Based Classifiers for Landslide Susceptibility Mapping.  ...  ., +, JSTARS 2020 3644-3655 Potential of Ensemble Learning to Improve Tree-Based Classifiers for Landslide Susceptibility Mapping.  ...  A New Deep-Learning-Based Approach for Earthquake-Triggered Landslide Detection From Single-Temporal RapidEye Satellite Imagery. Yi, Y., +, JSTARS 2020  ... 
doi:10.1109/jstars.2021.3050695 fatcat:ycd5qt66xrgqfewcr6ygsqcl2y

Dynamic Bayesian networks for evaluation of Granger causal relationships in climate reanalyses

Dylan Harries, Terence J. O'Kane
2021 Journal of Advances in Modeling Earth Systems  
Key Points: • Bayesian structure learning provides a principled approach to quantifying uncertainty in estimated network structures for relationships between climate modes • Dynamic Bayesian networks estimated  ...  severe limitation that Abstract We apply a Bayesian structure learning approach to study interactions between global climate modes, so illustrating its use as a framework for developing process-based  ...  Acknowledgments The authors wish to thank two anonymous reviewers and the handling editor for their comments and suggestions, which greatly improved the quality of the manuscript. D.  ... 
doi:10.1029/2020ms002442 fatcat:qmoidctehndwxndn7by34ouf2i

Causal analysis of competing atomistic mechanisms in ferroelectric materials from high-resolution Scanning Transmission Electron Microscopy data [article]

Maxim Ziatdinov, Chris Nelson, Xiaohang Zhang, Rama Vasudevan, Eugene Eliseev, Anna N. Morozovska, Ichiro Takeuchi, Sergei V. Kalinin
2020 arXiv   pre-print
However, the fundamental limitation of machine learning methods is their correlative nature, leading to extreme susceptibility to confounding factors.  ...  Machine learning has emerged as a powerful tool for the analysis of mesoscopic and atomically resolved images and spectroscopy in electron and scanning probe microscopy, with the applications ranging from  ...  Microscopy (STEM) enabled studies of chemical composition down to the single atom level [22] [23] [24] and, via quantitative mapping of structural distortions, enabled visualization of order parameter  ... 
arXiv:2002.04245v2 fatcat:tk3etbwahrcqjgz762e55zbwxy
« Previous Showing results 1 — 15 out of 179 results