Machine Learning SIG: Difference between revisions

From MEG Core
Jump to navigation Jump to search
Content added Content deleted
Line 38: Line 38:
##Artifact <ref>[https://www.sciencedirect.com/science/article/pii/S1053811921006777] MEGnet: Automatic ICA-based artifact removal for MEG using spatiotemporal convolutional neural networks
##Artifact <ref>[https://www.sciencedirect.com/science/article/pii/S1053811921006777] MEGnet: Automatic ICA-based artifact removal for MEG using spatiotemporal convolutional neural networks
Alex H.Treacher et al.</ref>
Alex H.Treacher et al.</ref>
##Signal of interest – Spike detection for epilepsy
##Signal of interest – Spike detection for epilepsy <ref>[https://pubmed.ncbi.nlm.nih.gov/31831410/] 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 </ref> <ref> [https://www.frontiersin.org/articles/10.3389/fninf.2017.00043/full] 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 </ref> <ref> [https://www.nature.com/articles/s41598-019-55861-w] 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 </ref>
##Signal/sequence predicts correct response
##Signal/sequence predicts correct response
#Temporal learning models – RNN DL / markov model <ref> [https://www.frontiersin.org/articles/10.3389/fnins.2018.00603/full] 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</ref>
#Temporal learning models – RNN DL / markov model <ref> [https://www.frontiersin.org/articles/10.3389/fnins.2018.00603/full] 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</ref>

Revision as of 20:36, 8 November 2021

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. Multivariate time series classification between conditions [1][2]
      1. Filtering Issues[3]
    2. Realtime - Brain computer interface / neurofeedback
  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 [4]
  3. Prediction of future condition / Biomarkers
    1. What signals predict conversion from mild cognitive impairment to Alzheimer [5] [6]
    2. What signals predict recovery from traumatic brain injury
    3. What signals predict poor outcome for epilepsy surgery
  4. Multimodal Integration
    1. Timing derived from MEG / localization from fMRI [7]
    2. Signal comparison between naturalistic viewing data MEG/fMRI
  5. Signal classification
    1. Artifact [8]
    2. Signal of interest – Spike detection for epilepsy [9] [10] [11]
    3. Signal/sequence predicts correct response
  6. Temporal learning models – RNN DL / markov model [12]
  7. Inferences from deep learning models
    1. CNN on images vs. CNN of brain responses to same images [13][14]

Preliminary Resources

MNE Python Decoding MNE Python Decoding at Source
SciKit Learn
Keras

Relevant Papers

Language Decoding

  1. ↑ [1] Encoding and Decoding Neuronal Dynamics: Methodological Framework to Uncover the Algorithms of Cognition
  2. ↑ [2] Decoding Dynamic Brain Patterns from Evoked Responses: A Tutorial on Multivariate Pattern Analysis Applied to Time Series Neuroimaging Data
  3. ↑ [3] High-pass filtering artifacts in multivariate classification of neural time series data
  4. ↑ [4] An automatic MEG low-frequency source imaging approach for detecting injuries in mild and moderate TBI patients with blast and non-blast causes
  5. ↑ [5] 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
  6. ↑ [6] 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
  7. ↑ [7] Resolving human object recognition in space and time: Radoslaw Martin Cichy, Dimitrios Pantazis & Aude Oliva Nature Neuroscience volume 17, pages455–462 (2014)
  8. ↑ [8] MEGnet: Automatic ICA-based artifact removal for MEG using spatiotemporal convolutional neural networks Alex H.Treacher et al.
  9. ↑ [9] 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
  10. ↑ [10] 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
  11. ↑ [11] 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
  12. ↑ [12] 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
  13. ↑ [13] 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
  14. ↑ [14] Performance-optimized hierarchical models only partially predict neural responses during perceptual decision making: Laura Gwilliams, Jean-Rémi King
Retrieved from "https://megcore.nih.gov/index.php?title=Machine_Learning_SIG&oldid=4719"