Title: Topology Simplification Algorithm for Segmentation of Medical Scans
1Topology Simplification Algorithm for
Segmentationof Medical Scans
Université catholique de Louvain
Committee Prof B. Macq (Advisor) Prof L.
Vandendorpe (Chairman) Prof A.H. Barr Prof S.K.
Warfield Dr C. De Vleeschouwer
Sylvain Jaume Ph.D. Private Defense December 17,
2003
2Agenda
- Introduction
- Theory of Topology
- Related Work
- Algorithm
- Results
- Conclusion
PhD Defense Topology Simplification Algorithm
for Segmentation of Medical Scans S. Jaume Dec
17, 2003 2
3Introduction I Data
- MRI, CT, PET, US provide
- volumetric images
256 x 256 x 124 voxels
PhD Defense Topology Simplification Algorithm
for Segmentation of Medical Scans S. Jaume Dec
17, 2003 3
4Introduction II Application
- Neuroscience maps brain functions
to brain boundary (surface)
- Mean brain scan brain surface
PhD Defense Topology Simplification Algorithm
for Segmentation of Medical Scans S. Jaume Dec
17, 2003 4
5Introduction III Goal
- Segmentation classification of
voxels representing the brain
- errors difficult to find
- holes at brain boundary
- correction of segmentation
- automated correction
6Topology I Continuous Topology
- Study of shape properties preserved
through deformations, twistings,
and stretchings (but no tearings)
- Homeomorphism equivalence
- sphere ellipsoid
- torus cup
Massey 1967
PhD Defense Topology Simplification Algorithm
for Segmentation of Medical Scans S. Jaume Dec
17, 2003 6
7Topology II Non-Separating Loops
Non-separating loops
- Closed lines on the surface
- Surface still in one piece
- Move from one side to the other
Topology simplification
B
A
A
B
8Topology III Discrete Topology
X -C F E V
g ( 2 K X ) / 2
C cubes
V vertices
F faces
K components
E edges
g genus, holes
F 6 , E 12, V 8, X 2, g 0 hole
F 16 , E 32, V 16, X 0, g 1 hole
- But no localization, no simplification
9Related Work I Various Methods
- Conquering voxels Mangin95, Han03
Problem large unconquered regions
- Deformable surfaces Davatzikos95, Bischoff03
Problem do not enter into brain folds
- Mesh methods Axen98, Guskov01, Fischl01
Problem complexity
10Related Work II Reeb Graph
11Related Work II Reeb Graph
12Related Work II Reeb Graph
13Related Work II Reeb Graph
hole between 2 planes
no cycle in the graph
Need another method to detect holes between 2
planes
14Algorithm Outline
Have we enclosed a hole?
Contribution single exploration of image
What is the extent of the hole?
Contribution more accurate localization
How to remove the hole from the image?
Contribution less complex rasterization
15Algorithm I Topology Detection
Have we enclosed a hole?
16Algorithm I Topology Detection
Have we enclosed a hole?
- Hole starts? or 2 branches?
17Algorithm I Topology Detection
Have we enclosed a hole?
18Algorithm I Topology Detection
Have we enclosed a hole?
19Algorithm I Topology Detection
Have we enclosed a hole?
20Algorithm II Topology Localization
destination contour
- shortest path around hole
start contour
Reeb loop
cross loop
21Algorithm III Topology Simplification
How to remove the hole from the image?
Rasterization transform loop surface
into voxels
22Results I Visualization
23Results II Statistics
24Discussion Comparison
25Conclusion
- Algorithm to provide brain surface from
segmentation
- Reduced complexity with wavefront traversal
- Better accuracy with a shorter loop
- Reduced complexity for rasterization of loop
- Software available for doctors
26Perspectives
- Automated segmentation is possible
- Other applications data compression, texture
mapping
- Understanding topology recognition, indexation
search
27Agenda
- Medical Scans
- Segmentation
- Continuous Topology
- Generating Loops
- Discrete Topology
- Various Methods
- Reeb Graph Methods
- Contributions
- Topology Detection
- Topology Localization
- Topology Simplification
- Visualization of Results
- Statistics
- Conclusion
1. Introduction
2. Theory of Topology
3. Related Work
4. Algorithm
5. Results
6. Conclusions
PhD Defense Topology Simplification Algorithm
for Segmentation of Medical Scans S. Jaume Dec
17, 2003 27