Integration of visual information, anatomic constraints and prior shape knowledge for medical segmentations
View Patent ↗This invention relates to the integration of visual information, anatomic constraints, prior shape knowledge, and level set representations for the segmentation of medical images. An embodiment according to the present invention comprises a level set variational framework that uses a bi-directional boundary flow, an intensity-based regional component that maximizes the a posteriori segmentation probability, a physiology-based module that constrains the solution space and a term that accounts for shape-driven consistency. All modules are expressed in an energetic form and the resulting objective function is optimized using a gradient descent method.
1. A method for segmentation of medical images comprising the steps of:
inputting a mathematical functional into a system for tracking moving interfaces, wherein said mathematical functional accounts for global/local shape properties of a physiological object of interest that is to be recovered;
visualizing image information wherein said information includes boundary and regional data; and
recovering said physiological object of interest by optimizing said mathematical functional integrated with said image information.
2. The method of claim 1 , further comprising the step of combining said mathematical functional with a level set objective function having a medical shape model.
3. The method of claim 2 , wherein said level set objective function includes a bi-directional boundary flow.
4. The method of claim 2 , wherein said medical shape model includes a medical shape model having a degree of variability.
5. The method of claim 1 , further comprising the step of combining said mathematical functional with a physiology based functional for constraining the solution space and a term that accounts for shape driven consistency.
6. The method of claim 1 , further comprising the step of combining said mathematical functional with an intensity regional function that maximizes a posteriori segmentation probability.
7. The method of claim 1 , further comprising the step of optimizing a resulting objective function using a gradient descent method.
8. A method for segmentation of medical images comprising the steps of:
developing a medical shape model on level set space for tracking moving interfaces;
using said medical shape model for introducing a physiological shape prior in an energetic form; and
recovering a physiological object of interest by minimizing non-stationary distance between an evolving interface and said medical shape model.
9. The method of claim 8 , wherein said medical shape model is developed using a variational framework to create a non-stationary pixel-wise model that accounts for shape variabilities.
10. The method of claim 8 , further comprising the step of minimizing non-stationary distance between an evolving interface and said medical shape model.
11. The method of claim 8 , further comprising the step of integrating said medical shape model and said physiological shape prior in energetic form into a data-driven variational method that performs image segmentation.
12. The method of claim 8 , further comprising the step of integrating an intensity-based regional module that maximizes a posteriori segmentation probability.
13. The method of claim 8 , further comprising the step of integrating a physiology-based module that constrains solution space and a term that accounts for shape driven consistency.
14. The method of claim 8 , further comprising the step of optimizing a resulting objective function using a gradient descent method.
15. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for segmentation of medical images, the method steps comprising:
developing a medical shape model on level set space for tracking moving interfaces;
using said medical shape model for introducing a physiological shape prior in an energetic form; and
recovering a physiological object of interest by minimizing non-stationary distance between an evolving interface and said medical shape model.
16. The program storage device of claim 15 , wherein said medical shape model is developed using a variational framework to create a non-stationary pixel-wise model that accounts for shape variabilities.
17. The program storage device of claim 15 , wherein the method steps further comprise the step of minimizing non-stationary distance between an evolving interface and said medical shape model.
18. The program storage device of claim 15 , wherein the method steps further comprise the step of integrating said medical shape model and said physiological shape prior in energetic form into a data-driven variational method that performs image segmentation.
19. The program storage device of claim 15 , wherein the method steps further comprise the step of integrating an intensity-based regional module that maximizes a posteriori segmentation probability.
20. The program storage device of claim 15 , wherein the method steps further comprise the step of integrating a physiology-based module that constrains solution space and a term that accounts for shape driven consistency.
21. The program storage device of claim 15 , wherein the method steps further comprise the step of optimizing a resulting objective function using a gradient descent method.