2008 Winter Project Week GroupwiseReg

Return to 2008_Winter_Project_Week

Figure 1: On the left is shown a stack of images and a sample pixel stack around a cortical region. On the left is shown the Gaussian(blue) fittet to a real sample from the dataset we used along with the non-parametric density estimate(red). Note that the distribution is bi-modal because of white matter-gray matter transaction.

Key Investigators

• MIT: Serdar Balci, Polina Golland
• Kitware: Brad Davis
• SCI: Casey Goodlett

Objective

We have developed techniques for finding the optimal geodesic path (or anchor tract) between two regions of interest in DWMRI data.

The objectives of this project are to port the Fast Sweeping and optimal geodesic path tractography code to ITK as well as the code to provide for volumetric segmentation of DW-MRI data.

See our Project Page for more details.

Approach, Plan

Our approach is described by the references below. Our challenge is to build the ITK infrastructure (such as new ITK iterators) to support this algorithm. Our main purpose at the Project Week is to collaborate on new algorithms and clinical data to provide the best solutions for our DBP partners.

Progress

June 2007 Project Week

During this Project Week, we did a lot of algorithmic design work, focusing on leveraging optimal or geodesic path information to provide for volumetric segmentations of fiber bundles. Working with Marek Kubicki and the Harvard DBP, we were able to begin the process of applying our algorithm to the full cingulum bundle with new labelmaps and to a new fiber bundle - Arcuate. We have recently achieved significant results in volumetric segmentations using a locally-constrained region-based technique (see the images above).

Jan 2007 Project Half Week

We finished the itkDirectionalIterator which will be needed in the Fast Sweeping implementation. Furthermore, we made progress in porting our Matlab code to ITK.

References

• J. Melonakos, M. Niethammer, V. Mohan, M. Kubicki, J. Miller, A. Tannenbaum. Locally-Constrained Region-Based Methods for DW-MRI Segmentation. Submitted to MMBIA 2007.
• V. Mohan, J. Melonakos, M. Niethammer, M. Kubicki, and A. Tannenbaum. Finsler Level Set Segmentation for Imagery in Oriented Domains. BMVC 2007.
• J. Melonakos, V. Mohan, M. Niethammer, K. Smith, M. Kubicki, and A. Tannenbaum. Finsler Tractography for White Matter Connectivity Analysis of the Cingulum Bundle. MICCAI 2007.
• J. Melonakos, E. Pichon, S. Angenet, and A. Tannenbaum. Finsler Active Contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, to appear in 2007.
• E. Pichon and A. Tannenbaum. Curve segmentation using directional information, relation to pattern detection. In IEEE International Conference on Image Processing (ICIP), volume 2, pages 794-797, 2005.
• E. Pichon, C-F Westin, and A. Tannenbaum. A Hamilton-Jacobi-Bellman approach to high angular resolution diffusion tractography. In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), pages 180-187, 2005.