Machine Learning SIG

From MEG Core
Revision as of 09:56, 8 April 2022 by Jstout (talk | contribs) (→‎MEG)
Jump to navigation Jump to search

Objectives

Advance general knowledge of machine learning techniques within the MEG community. Discuss journal articles, replicate techniques on NIH data, develop new ML techniques at NIH.

Format

  1. Specific Projects (Weekly)
    1. Code Review
    2. Project updates
    3. Question and Answer Clinic for users
  2. General (Monthly)
    1. Journal Club
    2. Hackathons – implement novel technique from JC with provided data
    3. Tutorial Workshops - instruct worked out examples with provided code/data
    4. General ML training
      1. Parameter tuning
      2. Model optimization
      3. Techniques
      4. Toolbox tutorials (Scikit-learn / keras)

Analysis Types

  1. Decoding[1][2]
    1. Multivariate time series classification between conditions [3][4][5][6]
      1. Filtering Issues[7]
      2. Converting Classifier Weights into Images [8]
    2. Temporal Generalization [9]
    3. Realtime - Brain computer interface / neurofeedback [10][11][12] [13][14]
    4. Language Phoneme Decoding [15]
  2. Subject classification
    1. eg. Healthy Control vs Major Depressive Disorder
    2. What are the significant features (brain regions, Hz)
    3. Automated diagnosis of TBI from MEG low frequency signals [16]
  3. Prediction of future condition / Biomarkers
    1. What signals predict conversion from mild cognitive impairment to Alzheimer’s Disease [17] [18]
    2. What signals predict recovery from traumatic brain injury [19]
    3. What signals predict poor outcome for epilepsy surgery
  4. Multimodal Integration [20]
    1. Timing derived from MEG / localization from fMRI [21]
    2. Signal comparison between naturalistic viewing data MEG/fMRI
    3. Combining DTI and MEG [22]
    4. Multimodal imaging classification [23]
  5. Signal classification
    1. Artifact [24] [25]
    2. Signal of interest – Spike detection for epilepsy [26] [27] [28]
    3. Signal/sequence predicts correct response
  6. Temporal learning models - Sequence learning
    1. Recurrent Neural Networks
    2. Markov Models[29][30] [31]
  7. Inferences from deep learning models
    1. Convolutional Neural Networks (CNN) on images vs. CNN of brain responses to same images [32][33]

Resources

General

SciKit Learn
Keras
UCI Dataset Archive
Machine Learning Primer[34]

Helpful Machine Learning Info

Feature Selection

MEG

MNE Python Decoding
MNE Python Decoding at Source
RealTime MEG
Deep Learning Decoding
MNE Representational Similarity Analysis Example MNE RSA Project
Toolbox for Trial-Masked Robust Detrending to overcome decoding issues from filtering
Micro-State analysis - clustering of data into states
MNE Feature Extraction

NIH

Biowulf Deep Learning Course
Biowulf DeepLearning Tools

NIMH Machine Learning in Neuroimaging
Center for Multimodal Neuroimaging
NIH-AI

Other Resources

TowardsDataScience
KDNuggets
Distill
OPENAI
FASTAI

Relevant Papers

  1. ↑ [1] Deconstructing multivariate decoding for the study of brain function: Martin N.Hebart, Chris I.Baker
  2. ↑ [2] An introduction to time-resolved decoding analysis for M/EEG:Thomas A. Carlson, Tijl Grootswagers, Amanda K. Robinson
  3. ↑ [3] Encoding and Decoding Neuronal Dynamics: Methodological Framework to Uncover the Algorithms of Cognition
  4. ↑ [4] Decoding Dynamic Brain Patterns from Evoked Responses: A Tutorial on Multivariate Pattern Analysis Applied to Time Series Neuroimaging Data
  5. ↑ [5] Multivariate pattern analysis for MEG: A comparison of dissimilarity measures - Matthias Guggenmos, Philipp Sterzer, Radoslaw Martin Cichy
  6. ↑ [6] Recurrent processes support a cascade of hierarchical decisions - Laura Gwilliams, Jean-Remi King
  7. ↑ [7] High-pass filtering artifacts in multivariate classification of neural time series data
  8. ↑ [8] On the interpretation of weight vectors of linear models in multivariate neuroimaging : Stefan Haufe,Frank Meinecke,Kai Görgen,Sven Dähne,John-Dylan Haynes,Benjamin Blankertz,Felix Bießmann
  9. ↑ [9] Characterizing the dynamics of mental representations: the temporal generalization method - J-R.King, S.Dehaene
  10. ↑ [10] Targeted Reinforcement of Neural Oscillatory Activity with Real-time Neuroimaging Feedback : Esther Florin, Elizabeth Bock, Sylvain Baillet
  11. ↑ [11] Real-time MEG neurofeedback training of posterior alpha activity modulates subsequent visual detection performance: Yuka O.Okazaki, Jörn M.Horschig, Lisa Luther, Robert Oostenveld, Ikuya Murakami, OleJensen
  12. ↑ [12] Alpha Synchrony and the Neurofeedback Control of Spatial Attention: Yasaman Bagherzadeh, Daniel Baldauf, Dimitrios Pantazis, Robert Desimone
  13. ↑ [13] Neurofeedback training of the upper alpha frequency band in EEG improves cognitive performance Benedikt Zoefel, René J.Huster, Christoph S.Herrmann
  14. ↑ [14] Implementation of a beam forming technique in real-time magnetoencephalography: Hiroki Ora, Kouji Takano, Toshihiro Kawase, Sunao Iwaki,Lauri Parkkonen Kenji Kansaku
  15. ↑ [15] Laura Gwilliams, Jean-Remi King,Alec Marantz & David Poeppel
  16. ↑ [16] An automatic MEG low-frequency source imaging approach for detecting injuries in mild and moderate TBI patients with blast and non-blast causes
  17. ↑ [17] Aberrant MEG multi-frequency phase temporal synchronization predictsconversion from mild cognitive impairment-to-Alzheimer's disease: Sandra Pusil, Stavros I. Dimitriadis, María Eugenia López, Ernesto Pereda, Fernando Maestú
  18. ↑ [18] Deep-MEG: spatiotemporal CNN features and multiband ensemble classification for predicting the early signs of Alzheimer’s disease with magnetoencephalography: Antonio Giovannetti, Gianluca Susi, Paola Casti, Arianna Mencattini, Sandra Pusil, María Eugenia López, Corrado Di Natale & Eugenio Martinelli
  19. ↑ [19] Assessing Recovery from Mild Traumatic Brain Injury (Mtbi) using Magnetoencephalography (MEG): An Application of the Synchronous Neural Interactions (SNI) Test : Don R. Thorpe, Brian E. Engdahl, Arthur Leuthold, Apostolos P. Georgopoulos
  20. ↑ [20] A M/EEG-fMRI Fusion Primer: Resolving Human Brain Responses in Space and Time: Radoslaw M.Cichy Aude Oliva
  21. ↑ [21] Resolving human object recognition in space and time: Radoslaw Martin Cichy, Dimitrios Pantazis & Aude Oliva Nature Neuroscience volume 17, pages455–462 (2014)
  22. ↑ [22] Using joint ICA to link function and structure using MEG and DTI in schizophrenia J.M.Stephen, B.A.Coffman, R.E.Jung, J.R.Bustillo, C.J.Aine, V.D.Calhoun
  23. ↑ [23] Multimodal Classification of Schizophrenia Patients with MEG and fMRI Data Using Static and Dynamic Connectivity Measures: Mustafa S. Cetin, Jon M. Houck, Barnaly Rashid, Oktay Agacoglu, Julia M. Stephen, Jing Sui, Jose Canive, Andy Mayer, Cheryl Aine, Juan R. Bustillo and Vince D. Calhoun
  24. ↑ [24] MEGnet: Automatic ICA-based artifact removal for MEG using spatiotemporal convolutional neural networks Alex H.Treacher et al.
  25. ↑ [25] ICLabel: An automated electroencephalographic independent component classifier, dataset, and website: Luca Pion-Tonachini, Ken Kreutz-Delgado, Scott Makeig
  26. ↑ [26] EMS-Net: A Deep Learning Method for Autodetecting Epileptic Magnetoencephalography Spikes: Li Zheng, Pan Liao, Shen Luo, Jingwei Sheng, Pengfei Teng, Guoming Luan, Jia-Hong Gao
  27. ↑ [27] Automated Detection of Epileptic Biomarkers in Resting-State Interictal MEG Data: Miguel C. Soriano, Guiomar Niso, Jillian Clements, Silvia Ortín, Sira Carrasco, María Gudín, Claudio R. Mirasso and Ernesto Pereda
  28. ↑ [28] A Long Short-Term Memory neural network for the detection of epileptiform spikes and high frequency oscillations: A. V. Medvedev, G. I. Agoureeva & A. M. Murro
  29. ↑ [29] Task-Evoked Dynamic Network Analysis Through Hidden Markov Modeling: Andrew J. Quinn, Diego Vidaurre, Romesh Abeysuriya, Robert Becker,Anna C. Nobre1, and Mark W. Woolrich
  30. ↑ [30] Transient spectral events in resting state MEG predict individual task responses - R. Becker, D. Vidaurre, A.J. Quinn, R.G. Abeysuriya, O. Parker Jones, S. Jbabdi, M.W. Woolrich
  31. ↑ [31] Spontaneous network activity <35 ​Hz accounts for variability in stimulus-induced gamma responses - Jan Hirschmann, Sylvain Baillet, Mark Woolrich, Alfons Schnitzler, Diego Vidaurre, Esther Florin
  32. ↑ [32] Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence: Radoslaw Martin Cichy 1,2 , Aditya Khosla 1 , Dimitrios Pantazis 3 , Antonio Torralba 1 & Aude Oliva 1
  33. ↑ [33] Performance-optimized hierarchical models only partially predict neural responses during perceptual decision making: Laura Gwilliams, Jean-Rémi King
  34. ↑ [34] Evaluating the Machine Learning Literature: A Primer and User’s Guide for Psychiatrists Adrienne Grzenda, M.D., Ph.D., Nina V. Kraguljac, M.D., William M. McDonald, M.D., Charles Nemeroff, M.D., Ph.D., John Torous, M.D., M.B.I., Jonathan E. Alpert, M.D., Ph.D., Carolyn I. Rodriguez, M.D., Ph.D., Alik S. Widge, M.D., Ph.D.
Retrieved from "https://megcore.nih.gov/index.php?title=Machine_Learning_SIG&oldid=5080"