Segmentation of the colon for accurate virtual navigation
AssigneeKentucky Imaging Technologies, LLC
InventorsAmal Farag, Salwa Elshazly
Life of this patent
Estimating the term…
Abstract
The present development is a method for generating a computer-aided accurate segmentation of an irregular structure, such as a colon The approach is based on a multi-tiered information propagation framework using statistical and variational methods. First, an initial segmentation using a method such as intensity based or shape-model registration for a volume of a typical CT is generated. The segmented image is subjected to a global/convex continuous minimization approach. After minimization, the data goes through post processing, and then the final segmented irregular structure output volume is generated.
Claims13
A method for generating an enhanced computerized image of an irregularly-shaped structure, the method comprising:
- a. generating an initial segmentation of the irregularly-shaped structure that encompasses air regions and soft tissue;
- b. after obtaining the initial segmentation output, generalizing a global/convex formulation to obtain the contrast-filled areas or high-attenuation areas or a combination thereof that were not extracted in step (a), wherein the global/convex formulation is a generalization of a variational method into a 3D space, and wherein the variational model is defined by the two-phase piecewise constant approximation of the Mumford-Shah model:
- min
- Ω
- I
-
- c
- 1
-
- c
- 2
-
- {
- E
- ACWE
-
- (
- Ω
- I
- ,
- c
- 1
-
- c
- 2
- ,
- λ
- )
- =
- per
-
- (
- Ω
- I
- )
- +
- λ
-
- ∫
- Ω
- I
-
- (
- c
- 1
- -
- (
- I
-
- (
- x
- )
- )
- 2
-
- dx
- +
- λ
-
- ∫
- Ω
- /
- Ω
- I
-
- (
- c
- 2
- -
- (
- I
-
- (
- x
- )
- )
- 2
-
- dx
- }
- where I is the given image, λ is a positive parameter controlling the tradeoff between regularization process and fidelity of solution with respect to I, ΩI is a closed subset of the image domain Ω, per (ΩI) is its perimeter, and c1c2∈R, and,
- c. post processing to provide a final segmentation of the irregularly-shaped structure.
Dependencies are inferred from the claim text.