Difference between revisions of "2009 Winter Project Week fMRI Clustering"

From NAMIC Wiki
Jump to: navigation, search
 
(5 intermediate revisions by the same user not shown)
Line 23: Line 23:
  
 
<h1>Approach, Plan</h1>
 
<h1>Approach, Plan</h1>
Our approach for comparing the locations of scar to sites of RF ablation is summarized in the ISMRM 2008 reference below. The main challenge to this approach is to measure the distance between each scarred pixel, and each RF ablation site, and then the distance from each RF ablation site, to the nearest scarred pixel.  <foo>.
+
Our approach is to use clustering methods to partition the whole brain into functionally coherent regions. Currently, the most common approach for functional connectivity analysis is seed-based correlation analysis. This method requires the user to identify a "seed" region of interest and identifies voxels significantly correlated with the mean time course of this ROI. In contrast, clustering algorithms are entirely data-driven and do not require any prior information about the brain's spatial or functional organization.
  
Our plan for the project week is to first try to measure the closest distances between MRI scar and Carto data <bar>,and then to measure distances between Carto data and closest scar.  We also wish to colorize the Carto surface, based on voltage data.  We also wish to streamline the MR angiography segmentation method.
+
We consider two different clustering algorithms: K-Means clustering and Spectral Clustering. To enable clustering of the entire brain volume, we use the Nystrom Method to approximate the necessary spectral decompositions.
 +
 
 +
Our plan for project week is to start pre-processing the new dataset of healthy subjects and schizophrenia patients using FSL. This includes standard fMRI preprocessing as well as additional preprocessing for functional connectivity analysis. If time permits, we would like to obtain preliminary clustering results and understand the strengths/limitations of the above clustering methods.
 
</div>
 
</div>
  
Line 31: Line 33:
  
 
<h1>Progress</h1>
 
<h1>Progress</h1>
 +
It has previously been shown that both K-Means clustering and Spectral Clustering produce reasonable partitions across subjects (A. Venkataraman et. al). However, the study was carried out on a dataset of 45 healthy young adults. These results have not been tested/compared across different populations.
  
Software for the registration between electrophysiology Carto data and the MR angiogram has been implemented, using the ITK/VTK platform (see ISMRM 2008 abstract, Taclas et al, and figure above). This week we wrote code to quantitatively determine the distances between each ablation location, and the closest region of scar, and to determine the distances between each pixel of scar, and the nearest ablation point.   Therefore we accomplished our goal!
+
Over this past week, we have successfully pre-processed an initial set of 12 subjects (4 healthy, 8 schizophrenia patients) using specialized functional connectivity analysis scripts. We have also obtained preliminary K-Means and Spectral Clustering results. We are able to see well-known structures within the brain, such as the default network. More importantly, we have identified new challenges in working with this new data. For example, since there is a greater variability among the schizophrenia subjects, it is no longer reasonable to represent the population based on the group clustering average. Therefore, we are seeking alternative models and a more intelligent feature space for working with resting state fMRI data. Hopefully, this new representation will give more consistent and meaningful partitions for individual subjects.
 
 
 
</div>
 
</div>
  
Line 41: Line 43:
  
 
===References===
 
===References===
*Peters DC, Wylie JV, Hauser TH, Kissinger KV, Botnar RM, Essebag V, Josephson ME, Manning WJ. Detection of pulmonary vein and left atrial scar after catheter ablation with three-dimensional navigator-gated delayed enhancement MR imaging: initial experience. Radiology 2007; 243:690-695.
+
*A. Venkataraman et. al. "Exploring Functional Connectivity in fMRI via Clustering." Submitted to ICASSP 2009.
* Taclas JE, Wylie JV, Hauser TH, Manning WJ, Josephson ME, Peters, DC. Correlation and Visualization of Left Atrial Scar due to Pulmonary Vein Ablation with Recorded Ablation Sites. Proceedings of the 16th scientific meeting of the International Society for Magnetic Resonance in Medicine (2008), Toronto, CA, p. 1042.
+
*M.D.Fox and M.E.Raichle, "Spontaneous Fluctuations in Brain Activity Observed with Functional Magnetic Resonance Imaging." Nature, vol.8, pp.700-711, 2007.
*Malchano ZJ, Neuzil P, Cury RC, Holmvang G, Weichet J, Schmidt EJ, Ruskin JN, Reddy VY. Integration of cardiac CT/MR imaging with three-dimensional electroanatomical mapping to guide catheter manipulation in the left atrium: implications for catheter ablation of atrial fibrillation. J Cardiovasc Electrophysiol 2006; 17:1221-1229.
+
*B.Biswat et. al. "Functional Connectivity in the Motor Cortex of Resting Human Brain using Echo-Planar MRI." MRM, vol.34, pp.537-541, 1995.
 +
*C.Fowlkes et. al. "Spectral Grouping Using the Nystrom Method." IEEE PAMI, vol.26, pp.214-225, 2004.
 +
*P.Golland et. al. "Detection of Spatial Activation Patterns as Unsupervised Segmentation of fMRI Data." MICCAI, pp.110-118, 2007.

Latest revision as of 21:54, 8 January 2009

Home < 2009 Winter Project Week fMRI Clustering



Key Investigators

  • MIT: Archana Venkataraman
  • BWH: Marek Kubicki
  • MIT: Polina Golland

Objective

We are developing methods to characterize differences between healthy subjects and patients with Schizophrenia. Our work uses resting state fMRI data to pinpoint brain regions with "similar" voxel time courses. Resting state data is thought to capture spontaneous, low-frequency oscillations in the brain, and it is commonly used for functional connectivity analysis. The goal of this work is to pinpoint brain structures which are indicative of each population (healthy vs. Schizophrenic).

Approach, Plan

Our approach is to use clustering methods to partition the whole brain into functionally coherent regions. Currently, the most common approach for functional connectivity analysis is seed-based correlation analysis. This method requires the user to identify a "seed" region of interest and identifies voxels significantly correlated with the mean time course of this ROI. In contrast, clustering algorithms are entirely data-driven and do not require any prior information about the brain's spatial or functional organization.

We consider two different clustering algorithms: K-Means clustering and Spectral Clustering. To enable clustering of the entire brain volume, we use the Nystrom Method to approximate the necessary spectral decompositions.

Our plan for project week is to start pre-processing the new dataset of healthy subjects and schizophrenia patients using FSL. This includes standard fMRI preprocessing as well as additional preprocessing for functional connectivity analysis. If time permits, we would like to obtain preliminary clustering results and understand the strengths/limitations of the above clustering methods.

Progress

It has previously been shown that both K-Means clustering and Spectral Clustering produce reasonable partitions across subjects (A. Venkataraman et. al). However, the study was carried out on a dataset of 45 healthy young adults. These results have not been tested/compared across different populations.

Over this past week, we have successfully pre-processed an initial set of 12 subjects (4 healthy, 8 schizophrenia patients) using specialized functional connectivity analysis scripts. We have also obtained preliminary K-Means and Spectral Clustering results. We are able to see well-known structures within the brain, such as the default network. More importantly, we have identified new challenges in working with this new data. For example, since there is a greater variability among the schizophrenia subjects, it is no longer reasonable to represent the population based on the group clustering average. Therefore, we are seeking alternative models and a more intelligent feature space for working with resting state fMRI data. Hopefully, this new representation will give more consistent and meaningful partitions for individual subjects.


References

  • A. Venkataraman et. al. "Exploring Functional Connectivity in fMRI via Clustering." Submitted to ICASSP 2009.
  • M.D.Fox and M.E.Raichle, "Spontaneous Fluctuations in Brain Activity Observed with Functional Magnetic Resonance Imaging." Nature, vol.8, pp.700-711, 2007.
  • B.Biswat et. al. "Functional Connectivity in the Motor Cortex of Resting Human Brain using Echo-Planar MRI." MRM, vol.34, pp.537-541, 1995.
  • C.Fowlkes et. al. "Spectral Grouping Using the Nystrom Method." IEEE PAMI, vol.26, pp.214-225, 2004.
  • P.Golland et. al. "Detection of Spatial Activation Patterns as Unsupervised Segmentation of fMRI Data." MICCAI, pp.110-118, 2007.