T-Snake(2)

1
T-Snake(2)

• Reference
• Tim McInerney, Demetri Terzopoulos, T-snakes
  Topology adaptive snakes, Medical Image Analysis,
  No.4 2000,pp73-91

2
Review

• T-snakes model
• A closed 2D contour consisting of a set of nodes
  connected in series.
• A discrete approximation to a conventional
  parametric snakes model.

3
T-snake Algorithm

• 1. For M time steps
• (a) compute the external forces and internal
  forces acting on T-snake nodes and elements
• (b) update the node position
• 2. Perform reparameterization phase I
• 3. Perform reparameterization phase II

4
T-snake Algorithm

• 4. For all T-snake elements, check valid or not
• Valid if corresponding grid cell is still a
  boundary cell
• Invalid T-snake elements and unused nodes are
  discarded
• 5. Use the grid vertices turned on in Phase II
  above ( if any) to determine new boundary cells
  and hence new T-snake nodes and elements

5
Apply T-snakes to medical image

• Geometric flexibility
• To segment and reconstruct objects with
  significant protrusions, tubular objects, or
  objects with bifurcations.
• Less sensitive to the initial placement

6
Apply T-snakes to medical image

• Topological adaptability
• Seamlessly split or merge and adapt to the
  topology of the target object

7
Apply T-snakes to medical image

• Multiple T-Snakes
• Evolve concurrently on different CPUs t improve
  performance.
• Seed T-snakes on several objects
• Potentially automatic segmentation

8
Apply T-snakes to medical image

• Topology preservation
• T-Snake can maintain the topology, guarantee
  that no self-intersections will occur
• Topology-preserving deformation

9
Apply T-snakes to medical image

• Interactive control
• Intuitive interactive capability associated with
  standard snake is maintained.
• User can exert attraction or repulsion forces
  using mouse.

10
T-Surfaces

• Topology adaptive surfaces (T-surfaces)
• A discrete deformable closed-surface model
• A closed oriented triangular surface mesh