System and method for validating an image segmentation algorithm

• US 20070081724A1
• Filed: 01/09/2006
• Published: 04/12/2007
• Est. Priority Date: 01/31/2005
• Status: Active Grant

• Current Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Zhang, Li, Zhang, Tiantian
• Granted Patent: US 7,907,756 B2
• Time in Patent Office: Days
• US Class Current: 382/173
• CPC Class Codes: G06V 10/26 Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion

Abstract

A system and method for validating an image segmentation algorithm are provided. The method for validating an image segmentation algorithm comprises: determining a region of interest in an image; segmenting the image from a first point in the region of interest by using a computer-based segmentation algorithm to obtain a first segmentation result; segmenting the image from a second point in the region of interest by using the computer-based segmentation algorithm to obtain a second segmentation result; and comparing the first segmentation result with the second segmentation result to determine a consistency of the computer-based segmentation algorithm.

Claims

1. A method for validating an image segmentation algorithm, comprising:

determining a region of interest in an image;

segmenting the image from a first point in the region of interest by using a computer-based segmentation algorithm to obtain a first segmentation result;

segmenting the image from a second point in the region of interest by using the computer-based segmentation algorithm to obtain a second segmentation result; and

comparing the first segmentation result with the second segmentation result to determine a consistency of the computer-based segmentation algorithm.

2. The method of claim 1, wherein the region of interest is determined by a user input or the computer-based segmentation algorithm.

3. The method of claim 1, wherein the computer-based segmentation algorithm is a semi-automatic or automatic segmentation algorithm.

4. The method of claim 1, wherein the image is acquired by using one of a CT, MR, positron emission tomography (PET), fluoroscopic, ultrasound, x-ray or hybrid imaging technique, or scanning or digital image recording technique.

5. The method of claim 1, wherein the first point is determined by a user input or the computer-based segmentation algorithm.

6. The method of claim 1, wherein the second point determined by a user input or the computer-based segmentation algorithm.

7. The method of claim 1, wherein the consistency is determined by an overlap ratio between the first segmentation result and the second segmentation result.

8. The method of claim 7, further comprising:

outputting a result of the consistency determination.

9. The method of claim 8, wherein when the result of the consistency determination is output, the method further comprises:

converting the overlap ratio into a color representation.

10. A system for validating an image segmentation algorithm, comprising:

a memory device for storing a program;

a processor in communication with the memory device, the processor operative with the program to;

determine a region of interest in an image;

segment the image from a first point in the region of interest by using a computer-based segmentation algorithm to obtain a first segmentation result;

segment the image from a second point in the region of interest by using the computer-based segmentation algorithm to obtain a second segmentation result; and

compare the first segmentation result with the second segmentation result to determine a consistency of the computer-based segmentation algorithm.

11. The system of claim 10, wherein the region of interest is determined by a user input or the computer-based segmentation algorithm.

12. The system of claim 10, wherein the computer-based segmentation algorithm is a semi-automatic or automatic segmentation algorithm.

13. The system of claim 10, wherein the image is acquired by using one of a CT, MR, positron emission tomography (PET), fluoroscopic, ultrasound, x-ray or hybrid imaging device, or digital camera or flatbed scanner.

14. The system of claim 10, wherein the first point is determined by a user input or the computer-based segmentation algorithm.

15. The system of claim 10, wherein the second point determined by a user input or the computer-based segmentation algorithm.

16. The system of claim 10, wherein the consistency is determined by an overlap ratio between the first segmentation result and the second segmentation result.

17. The system of claim 16, wherein the processor is further operative with the program code to:

output a result of the consistency determination.

18. The system of claim 17, wherein when the result of the consistency determination is output the processor is further operative with the program code to:

convert the overlap ratio into a color representation.

19. A method for determining consistency between initial points in a region of interest in an image, comprising:

(a) segmenting the image from a first initial point in the region of interest by using a computer-based segmentation algorithm to obtain a first segmentation result;

(b) segmenting the image from a new initial point in the region of interest by using the computer-based segmentation algorithm to obtain a new segmentation result;

(c) determining the consistency of the computer-based segmentation algorithm by comparing the first segmentation result with the new segmentation result; and

(d) repeating steps (b) and (c) until all points in the region of interest have been used as the new initial point to start the computer-based segmentation algorithm.

20. The method of claim 19, wherein the region of interest is determined by a user input or the computer-based segmentation algorithm.

21. The method of claim 19, wherein the computer-based segmentation algorithm is a semi-automatic or automatic segmentation algorithm.

22. The method of claim 19, wherein the image is acquired by using one of a CT, MR, positron emission tomography (PET), fluoroscopic, ultrasound, x-ray or hybrid imaging technique, or scanning or digital image recording technique.

23. The method of claim 19, wherein the first initial point is determined by a user input or the computer-based segmentation algorithm.

24. The method of claim 19, wherein the new initial point is a point in the region of interest that has not been used as an initial point to start the computer-based segmentation algorithm.

25. The method of claim 19, wherein the consistency is determined by an overlap ratio between the first segmentation result and the new segmentation result.

26. The method of claim 26, further comprising:

outputting a result of the consistency determination.

28. The method of claim 26, wherein the overlap ratio indicates the consistency between the first initial point and the new initial point.

27. The method of claim 27, wherein when the result of the consistency determination is output, the method further comprises:

converting the overlap ratio into a color representation.