Title: A Unified Feature Registration Framework for Brain Anatomical Alignment
1A Unified Feature RegistrationFramework for
Brain Anatomical Alignment
- Haili Chui, Robert Schultz, Lawrence Win, James
Duncan and Anand Rangarajan
Image Processing and Analysis Group Departments
of Electrical Engineering and Diagnostic
Radiology Yale University Department of
Computer Information Science and
Engineering University of Florida
2Brain Anatomical Alignment
- Brains are different
- Shape.
- Structure.
- Direct comparison of brains between different
subjects is not very accurate. - Statistically and quantitatively more accurate
study requires the brain image data to be put in
a common normalized space through alignment. - Examples of areas that need brain registration
- Studying structure-function connection.
- Tracking temporal changes.
- Generating probabilistic atlases.
- Creating deformable atlases.
3Studying Function-Structure Connection
4Inter-Subject Brain Registration
- Inter-subject brain registration
- Alignment of brain MRI images from different
subjects to remove some of the shape variability. - Difficulties
- Complexity of the brain structure.
- Variability between brains.
- Brain feature registration
- Choose a few salient structural features as a
concise representation of the brain for matching. - Overcome complexity only model important
structural features. - Overcome variability only model consistent
features.
5Previous Work 3D Sulcal Point Matching
Feature Extraction
Extracted Point Features
6Previous Work 3D Sulcal Point Matching
Overlay of 5 subjects before TPS alignment
7A Unified Feature Registration Method
8Non-rigid Feature Point Registration
9Unification of Different Features
- Ability to incorporate different types of
geometrical features. - Points.
- Curves.
- Open surface ribbons.
- Closed surfaces.
- Simultaneously register all features --- utilize
the spatial inter-relationship between different
features to improve registration.
10Joint Clustering-Matching Algorithm (JCM)
11Overcome Sub-sampling Problem
- Sub-sampling (e.g. clustering) reduces
computational cost for matching.
- In-consistency problem with sub-sampling
- The in-consistency can be overcome by
sub-sampling (clustering) and matching
simultaneously.
12Joint Clustering-Matching Algorithm (JCM)
- JCM
- Reduce computational cost using sub-sampled
cluster centers. - Accomplish optimal cluster placement through
joint clustering and matching. - Symmetric two way matching.
13JCM Energy Function
Point Set X
Point Set Y
Clustering
Clustering
Clusters Center Set V
Cluster Center Set U
Annealing
14JCM Energy Function
- Clustering and regularization energy function
- First two terms perform clustering, next four
perform non-rigid matching and last two are
entropy terms.
15JCM Example
- Matching 2 face patterns with JCM (click to play
movie).
16Experiments
17Comparison of Different Features
- Different features can be used in our approach.
18Synthetic Study Setup
19Results Method I vs. Method III
- Outer cortical surface alone can not provide
adequate information for sub-cortical structures.
- Combination of two features works better.
20Results Method II vs. Method III
- Major sulcal ribbons alone are too sparse --- the
brain structures that are relatively far away
from the ribbons got poorly aligned. - Combination of two features works better.
21Conclusion
- Combination of different features improves
registration. - Unified brain feature registration approach
- Capable of estimating non-rigid transformations
without the correspondence information. - General unified framework.
- Symmetric.
- Efficient.
22Acknowledgements
- Members of the Image Processing and Analysis
Group at Yale University - Hemant Tagare.
- Lawrence Staib.
- Xiaolan Zeng.
- Xenios Papademetris.
- Oskar Skrinjar.
- Yongmei Wang.
- Colleagues in the brain registration project
- Joseph Walline.
- Partially supported is by grants from the
Whitaker Foundation, NSF, and NIH.
23Future Work
24Estimating An Average Shape
- Given multiple sample shapes (sample point sets),
compute the average shape for which the joint
distance between the samples and the average is
the shortest.
Average ?
- Difficult if the correspondences between the
sample points are unknown.
25Super Clustering-Matching Algorithm (SCM)
26(No Transcript)
27End
- Further Information
- Web site http//noodle.med.yale.edu/chui/
28End
292D Examples of RPM
30(No Transcript)
31(No Transcript)
32Example Application Face Matching
33Example Application Face Matching