A1259788553ZIVkM

1
Blind Separation of sources in function MRI
Sequences
Presented By Eldad Klaiman Limor
Goldenberg Supervised By Michael Alex
Bronstein Dr. Michael Zibulevsky
The Kasher Contest - In memory of Yehoraz Kasher

2
The Problem

• functional MRI
• Important tool for studying the human brain
  activity.
• High spatial resolution, flexibility,
  harmlessness made it popular.
• The BOLD technique produce an image of the
  blood oxygenation level throughout the brain.
• A sequence of scans is in a short period of time,
  when the subject is asked to perform some task.
  High oxygenation levels represent high activity
  of the brain regions responsible for the task.

• Blind Source Separation
• Linear mixture of independent sources
• No a priori information is known about their
  properties.
• Blind Source Separation" the problem of
  separating such sources.
• There exist powerful tools to solve it.
• Focus on the approach of sparse representations,
  which has proved its advantages in different
  works in the field.

3
fMRI-BSS Model

• Noise removal
• Identify Background
• Sparse Representation

4
fMRI Simulation

• Background Brain Image.
• Spatial Function
• Hemodynamics
• Gaussian Noise

5
fMRI simulator GUI
6
fMRI Simulator - Results
fMRI frames
Hemodynamics
7
Preprocessing Sparse Representations

• Wavelet Packets is used to create sparse
  images.
• Best Node is selected by sparseness Criteria
• Scatter plot of resulting images
• chasing the illusive X

8
Geometric Separation

• Clustering - FCM.
• Angle Histogram.

9
Separation Example
Source 1 3 spatial components
Source 2 2 spatial components
10
Issues Encountered

• Preprocessing Zero-mean, LPF, etc.
• Sparseness Criteria Shannon entropy selected.
• Stability / Parametric Sensitivity thresholds.

11
Principal Component Analysis

• Problems of high ordermore mixtures than
  sources
• Problem dimension reduced using PCA

PRINCOMP( )
12
PCA Revelations
13
ICA - Infomax

• Artificial Neural Network Viewpoint,maximize
  output Entropy.
• InfoMax ICA Matlab Toolbox(courtesy of Scott
  Makeig Co.)
• Preliminary Results can be obtained without
  mixture preprocessing.

14
ICA Separation Example
15
ICA Notes

• Sign and Order limitations.
• Improved robustness and quality, compared to
  geometric separation.
• In most cases, the sparse representation improved
  the quality of separation.

16
Application on the Real Thing
17
Real fMRI Issues
False Artifact Sources created due to head
movement, Noise.
Background separated from activity sources.
18
Conclusions

• Achieved good results by geometric and ICA
  separation.
• ICA robustness, quality.
• PCA model selection, added values.
• Potential as fMRI analysis tool.
• Quick, low cost.
• Exact knowledge of simulation flow - not needed.
• Not relying on high time resolution.

19
Further Progress

• A new horizon for fMRI-ICA academic research and
  projects.
• A friendly and enhanced fMRI-ICA application
  was developed for simple, user-oriented
  application of algorithm.
• Experimental application of the separation
  algorithm on LORETA (EEG-CAT).

20
Thanks to

• Nethaniels Brain
• Dr. Michael Zibulevsky
• Johanan Erez and the Lab team
• Michael Alex Bronstein
• Anat Grinfeld

21
Sparseness Criteria

• L1
• L0
• Shannon Entropy
• Clusters

Back