Method and system for automatic lung segmentation

• US 7,756,316 B2
• Filed: 12/01/2006
• Issued: 07/13/2010
• Est. Priority Date: 12/05/2005
• Status: Active Grant

• Current Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Odry, Benjamin, Shen, Hong, Qing, Shuping
• Primary Examiner(s): Kim; Charles
• Application Number:
  US11/565,711
• Publication Number:
  US 20070127802A1
• Time in Patent Office: 1,320 Days
• Field of Search: None
• US Class Current: 382/131
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/30061 Lung
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06V 10/457 by analysing connectivity, e.g. edge linking, connected component analysis or slices
• CPC Class Codes: G06V 2201/03 Recognition of patterns in medical or anatomical images

Abstract

Disclosed is a systematic way of automatically segmenting lung regions. To increase the efficiency of a lung segmentation technique, a region-based technique, such as region growing, is performed by a computer on a middle slice of the CT volume. A contour-based technique is then used for a plurality of non-middle slices of the CT volume. This allows the implementation to be multithreaded and results in an improvement in the segmentation algorithm'"'"'s efficiency.

Claims

1. A method of segmenting lungs from a Computerized Tomography (CT) volume comprising a plurality of slices, said method comprising:

using a processor to perform steps comprising;

thresholding said CT volume using a predetermined threshold;

segmenting a middle slice of said CT volume using a region-based technique; and

segmenting a plurality of non-middle slices of said CT volume using a contour-based technique, without using a region-based technique for the non-middle slices.

2. The method of claim 1 further comprising detecting tissues that are not related to said lungs.

3. The method of claim 2 further comprising comparing segmentation results from two consecutive slices.

4. The method of claim 3 further comprising determining if the comparison of said segmentation results contains a region of pixels having a size above a predetermined size threshold and an intensity above a predetermined intensity threshold.

5. The method of claim 4 further comprising removing said region of pixels.

6. The method of claim 1 wherein said segmenting of said middle slice further comprises applying a median filter to said CT volume.

7. The method of claim 1 wherein said segmenting of said middle slice further comprises removing non-body regions from said CT volume.

8. The method of claim 1 wherein said segmenting of said middle slice further comprises locating a body region in said CT volume.

9. The method of claim 1 wherein said segmenting of said middle slice further comprises labeling said lung regions.

10. The method of claim 1 wherein said contour-based technique further comprises at least one of lung border tracing, lung smoothing, and filling lung regions.

11. The method of claim 10 wherein said lung border tracing further comprises setting a starting point and a range to limit searching.

12. The method of claim 11 wherein said lung border tracing further comprises executing a chain-code algorithm.

13. The method of claim 10 wherein said lung smoothing further comprises performing a rolling-ball method.

14. The method of claim 10 wherein said lung smoothing further comprises calculating a curvature of contour points determined by said contour-based technique.

15. The method of claim 14 wherein said curvature of a target point between a first point and a second point is defined as

curvature=abs(θ

2−

θ

1)÷

d

where d is the total length of a path defined by a plurality of segments between said first point to said second point and θ

1 and θ

2are angles defined at least in part by one or more of said segments.

16. An apparatus for segmenting lungs from a Computerized Tomography (CT) volume comprising a plurality of slices, said apparatus comprising:

means for thresholding said CT volume using a predetermined threshold;

means for segmenting a middle slice of said CT volume using a region-based technique; and

means for segmenting a plurality of non-middle slices of said CT volume using a contour-based technique, without using a region-based technique for the non-middle slices.

17. The apparatus of claim 16 wherein said means for segmenting said middle slice further comprises means for applying a median filter to said CT volume.

18. The apparatus of claim 16 wherein said means for segmenting said middle slice further comprises means for removing non-body regions from said CT volume.

19. The apparatus of claim 16 wherein said means for segmenting said middle slice further comprises means for locating a body region in said CT volume.

20. The apparatus of claim 16 wherein said means for segmenting said middle slice further comprises means for labeling said lung regions.

21. The apparatus of claim 16 wherein said contour-based technique further comprises means for at least one of lung border tracing, lung smoothing, and filling lung regions.

22. The apparatus of claim 21 wherein said means for lung border tracing further comprises means for executing a chain-code algorithm.

23. The apparatus of claim 21 wherein said means for lung smoothing further comprises means for performing a rolling-ball method.

24. The apparatus of claim 23 wherein said means for lung smoothing further comprises means for calculating a curvature of contour points determined by said contour-based technique.

25. A non-transitory computer readable medium comprising computer program instructions capable of being executed in a processor and defining the steps comprising:

thresholding a CT volume using a predetermined threshold;

segmenting a middle slice of said CT volume using a region-based technique; and

segmenting a plurality of non-middle slices of said CT volume using a contour-based technique, without using a region-based technique for the non-middle slices.

26. The computer readable medium of claim 25 further comprising the step of detecting tissues that are not related to said lungs.

27. The computer readable medium of claim 25 wherein the step of segmenting said middle slice further comprising the step of applying a median filter to said CT volume.

28. The computer readable medium of claim 25 wherein the step of segmenting said middle slice further comprises the step of removing non-body regions from said CT volume.

29. The computer readable medium of claim 25 wherein the step of segmenting said middle slice further comprises the step of locating a body region in said CT volume.

30. The computer readable medium of claim 25 wherein the step of segmenting said middle slice further comprises the step of labeling said lung regions.

31. The computer readable medium of claim 25 wherein said contour-based technique further comprises at least one of lung border tracing, lung smoothing, and filling lung regions.

32. The computer readable medium of claim 31 wherein said lung smoothing further comprises calculating a curvature of contour points determined by said contour-based technique.