2014 Summer Project Week:Atlas Selection

• 

  Projects List

Key Investigators

• Kanglin Chen (Fraunhofer MEVIS Germany)
• Gregory Sharp (Harvard Medical School)

Project Description

Objective

Atlas selection is used for image segmentation. Normally, a single image is chosen as an atlas and the structures are segmented manually. The segmentation is transferred to patient data using non-linear image registration. However, the choice of single atlas is difficult. We will develop an average atlas using image registration and reconstruction. The average atlas makes the registration to patient data more robust.

Approach, Plan

An average atlas construction is based on image registration and reconstruction. We plan to construct the average atlas with merged segmentation using real 3D datasets and validate them.

Progress

The algorithms for average atlas construction is finished. We have the datasets.

Atlas construction and its validation

• Datasets

We have 20 datasets

• Algorithm for atlas construction
• Results