2014 Project Week:MultiAtlas MultiImage Segmentation

From NAMIC
Jump to: navigation, search
Home < 2014 Project Week:MultiAtlas MultiImage Segmentation


Key Investigators

  • Minjeong Kim, Dinggang Shen, UNC Chapel Hill
  • Xiaofeng Liu, Jim Miller, GE Research

Project Description

Objective

To deal with the limitations of existing pairwise registration methods between images with large shape difference, we develop an algorithm for multi-atlas-based multi-image segmentation of brain images and release it as a Slicer module.

Approach, Plan

Our algorithm in the module performs 1) a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 2) an iterative groupwise segmentation method for simultaneous consideration of segmentation information propagated from all available images, including the atlases and other newly segmented target images.

Progress

We have developed the Slicer module called MABMIS and fully tested it using LONI LPBA40 and IXI datasets. The result by our Slicer module shows 2% improvement compared to pairwise registration framework in terms of the averaged overlap ratio between automatic segmentation and ground truth labels. We are releasing our Slice module in NITRC (http://www.nitrc.org/projects/mabmis_slicer4/).