2011 Summer Project Week RSS for AFib Ablation
Robust Statistical Segmentation (RSS) for the Atrial Fibrillation Ablation Therapy... Atrial fibrillation (AF) is characterized by rapid and dysynchronous contractions of the atria, in conjunction with structural changes in the atrial tissue. One treatment, catheter ablation, neutralizes, or isolates, the electrical sources of AF by applying radiofrequency energy with an intracardiac catheter. Magnetic resonance imaging (MRI) has been used to examine and quantify remodeling in the atrial wall before and after catheter ablation. However, the current workflow to evaluate the degree of remodeling in the atrial wall depends on a variety of tools and manual segmentation of that structure.
- Utah: Rob MacLeod, Josh Cates, and Josh Blauer
- GE Global: Kedar Patwardhan
- Isomics: Steve Pieper
- Georgia Tech: Yi Gao, Wassim Haddad, and Allen Tannenbaum
- Automated segmentation of the atrial wall, based on RSS
- Consolidate and streamline current segmentation workflow
- Refine registration pipeline for pre- and post-ablation contrast MRI scans
- Integrate RSS tool into the Editor module
- We are currently developing a registration pipeline specific to pre- and post-ablation contrast MRI scans
- We plan to use Project Week to work with collaborators to test, debug, and further refine this registration pipeline
- We will add editor module wrappers to call the RSS CLI package. We also plan to improve the clinical usability by simplifying the user interaction required for setting algorithm parameters.
- This week we worked out the specification of our preablation/postablation registration module. We will use standard ITK registration methods and the general strategy suggested by Alex Z. Some question whether we can use the BrainsFIT module in Slicer4-- (Need to follow up with Hans to see if there will be a port).
- First cut of integrated editor module ready (tested on windows).
- Will use new EditorExtensionTemplate
- We planned a validation paper for auto left atrial segmentation with Yi and Behnood.
This work will be delivered to the NA-MIC Kit as a:
- Slicer Module
- Built-in: No
- Extension -- commandline: No
- Extension -- loadable: YES
- Slicer Module
1 Y. Gao, B. Gholami, R.S. MacLeod, J. Blauer, W.M. Haddad, and A.R. Tannenbaum, Segmentation of the Endocardial Wall of the Left Atrium using Local-Region Based Active Contours and Statistical Shape Learning, Proceedings of SPIE Medical Imaging 2010, Vol. 7623, 76234Z.
2 C.J. McGann, E.G. Kholmovski, R.S. Oakes, J.J. Blauer, M. Daccarett, N. Segerson, K.J. Airey, N. Akoum, E. Fish, T.J. Badger, E.V. DiBella, D. Parker, R.S. MacLeod, N.F. Marrouche. “New Magnetic Resonance Imaging-Based Method for Defining the Extent of Left Atrial Wall Injury After the Ablation of Atrial Fibrillation,” In Journal of the American College of Cardiology, Vol. 52, No. 15, pp. 1263--1271. Oct 7, 2008. http://www.sci.utah.edu/publications/mcgann08/mcg2008.pdf