Difference between revisions of "2014 Summer Project Week:Atlas Selection"
| Line 32: | Line 32: | ||
<div style="width: 27%; float: left; padding-right: 3%;"> | <div style="width: 27%; float: left; padding-right: 3%;"> | ||
<h3>Progress</h3> | <h3>Progress</h3> | ||
| + | * We developed algorithms for atlas construction, programming in Matlab and visualization in Slicer. | ||
| + | * We constructed an atlas of 40 datasets for H&N and merged segmentations into the atlas. | ||
</div> | </div> | ||
</div> | </div> | ||
Revision as of 19:57, 26 June 2014
Home < 2014 Summer Project Week:Atlas Selection
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, image segmentation based on single atlas is not stable. To improve the segmentation we can select multiple images, which are suitable for image segmentation and after registration we can merge the segmentations to a final one. The selection of these images can be based on an atlas. The procedure defines in the following steps:
- Construct an atlas based on a database
- Every image of the database is aligned to the atlas after atlas construction
- Register the atlas to a new image and transfer the database to the new image
- Compare the transformed database to the new image and select some well-matched images
- Merge the segmentations of these images to a final one based on e.g. "weighted voting" or STAPLE algorithms
The crucial step of atlas selection is atlas construction and the focus of this project is to construct an atlas and validate the atlas using segmentation.
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
- We developed algorithms for atlas construction, programming in Matlab and visualization in Slicer.
- We constructed an atlas of 40 datasets for H&N and merged segmentations into the atlas.
Project Results
- We have 20 datasets for H&N including lung and chest. For example
- We select the ROI of every data excluding lung and chest. For each data there exist the segmentations of brain stem, left and right parotids. For example
- We constructed an atlas from 20 datasets of ROI, and merged the segmentations. These segmentations are probability maps of
brain stem, left and right parotids.
