2013 Summer Project Week:CARMA AutoLASeg
- Utah: Salma Bengali, Alan Morris, Josh Cates, Gopal Veni, Ross Whitaker, Rob MacLeod
The goal of this project is to implement Gopal and Ross' segmentation method: "Left atrial wall segmentation using intensity profile based feature detector and optimal graph-cuts." Our objective is to implement this method in Slicer. There are several fairly involved steps for the entire segmentation process, including:
- An LA shape model building phase
- User input to identify the center of a region of interest
- Computation of the segmentation, given a new LGE-MRI image
- Surface reconstruction of the output point set and (optionally) scan-conversion of the surface mesh to a binary segmentation volume.
We plan to implement this algorithm as a Slicer command-line module.
This module is nearly complete, and visualization of the output result is much better but will need some bug fixes such as proper centering. We have decided to store the training model data on a website like Midas, and leave it to the user to download the data. We will soon make it available in the nightly Slicer build.
This work will be delivered to the NA-MIC Kit as a Slicer module as part of the existing Cardiac MRI Toolkit extension.