Branch extension method for airway segmentation
View Patent ↗A branch extension method and system for segmenting airways in 3D image data is disclosed. An initial airway segmentation is obtained from the 3D image data. Terminal branches of segmented airways of the initial airway segmentation are identified. The segmentation of the terminal branches is then extended. The segmentation of the terminal branches can be extended using various segmentation techniques. This method can use complex segmentation techniques to extend the terminal branches without having a large impact to the overall speed of the segmentation.
1. A method comprising:
obtaining 3D image data including segmented airways having a plurality of branches;
identifying, by a processor, one or more of the plurality of branches of the segmented airways as terminal branches; and
extending, by a processor, the segmentation of the identified terminal branches.
2. The method of claim 1 , wherein said step of identifying one or more of the plurality of branches of the segmented airways as terminal branches comprises:
generating a distance map of said segmented airways from the trachea; and
identifying locally maximal regions on said distance map as terminal branches.
3. The method of claim 1 , wherein said step of identifying terminal branches of the segmented airways comprises:
generating a tree model of the segmented airways; and
determining the terminal branches of the segmented airways based on the tree model.
4. The method of claim 1 , wherein said step of extending the segmentation of the identified terminal branches comprises:
extending the segmentation of the terminal branches using adaptive region growing segmentation.
5. The method of claim 1 , wherein said step of extending the segmentation of the identified terminal branches comprises:
extending the segmentation of the terminal branches using differential adaptive region growing segmentation.
6. The method of claim 1 , wherein said step of extending the segmentation of the identified terminal branches comprises:
extending the segmentation of the terminal branches using fuzzy connectedness segmentation.
7. The method of claim 1 , wherein said step of extending the segmentation of the identified terminal branches comprises:
extending the segmentation of the terminal branches via branch tracking at the identified terminal branches.
8. The method of claim 1 , wherein said step of obtaining 3D image data including segmented airways comprises:
receiving 3D image data; and
segmenting airways in the 3D image data.
9. A method comprising:
segmenting, by a processor, airways in 3D image data using a first segmentation technique, wherein the segmented airways resulting from the first segmentation technique have a plurality of branches;
identifying, by a processor, one or more of the plurality of branches of the segmented airways resulting from said first segmentation technique as terminal branches; and
extending, by a processor, the identified terminal branches by performing segmentation at the terminal branches using a second segmentation technique.
10. An apparatus comprising:
means for obtaining 3D image data including segmented airways having a plurality of branches;
means for identifying one or more of the plurality of branches of the segmented airways as terminal branches; and
means for extending the segmentation of the identified terminal branches.
11. The apparatus of claim 10 , wherein said means for identifying one or more of the plurality of branches of the segmented airways as terminal branches comprises:
means for generating a distance map of said segmented airways from the trachea; and
means for identifying locally maximal regions on said distance map as terminal branches.
12. The apparatus of claim 10 , wherein said means for identifying terminal branches of the segmented airways comprises:
means for generating a tree model of the segmented airways; and
means for determining the terminal branches of the segmented airways based on the tree model.
13. The apparatus of claim 10 , wherein said means for extending the segmentation of the identified terminal branches comprises:
means for performing adaptive region growing segmentation at the identified terminal branches.
14. The apparatus of claim 10 , wherein said means for extending the segmentation of the identified terminal branches comprises:
means for performing differential adaptive region growing segmentation at the identified terminal branches.
15. The apparatus of claim 10 , wherein said means for extending the segmentation of the identified terminal branches comprises:
means for performing fuzzy connectedness segmentation at the identified terminal branches.
16. The apparatus of claim 10 , wherein said means for extending the segmentation of the identified terminal branches comprises:
means for performing branch tracking at the identified terminal branches.
17. The apparatus of claim 10 , wherein said means for obtaining 3D image data including segmented airways comprises:
means for receiving 3D image data; and
means for segmenting airways in the 3D image data.
18. An apparatus comprising:
means for segmenting airways in 3D image data using a first segmentation technique, wherein the segmented airways resulting from the first segmentation technique have a plurality of branches;
means for identifying one or more of the plurality of branches of the segmented airways resulting from said first segmentation technique as terminal branches; and
means for extending the identified terminal branches by performing segmentation at the terminal branches using a second segmentation technique.
19. A non-transitory computer readable medium storing computer program instructions, said computer program instructions defining the steps comprising:
identifying one or more of a plurality of branches of segmented airways in 3D image data including an airway segmentation as terminal branches; and
extending the segmentation of the identified terminal branches.
20. The computer readable medium of claim 19 , wherein the computer program instructions defining the step of identifying one or more of a plurality of branches of the segmented airways in 3D image data including an airway segmentation as terminal branches comprise computer program instructions defining the steps of:
generating a distance map of said segmented airways from the trachea; and
identifying locally maximal regions on said distance map as terminal branches.
21. The computer readable medium of claim 19 , wherein the computer program instructions defining the step of identifying terminal branches of the segmented airways comprise computer program instructions defining the steps of:
generating a tree model of the segmented airways; and
determining the terminal branches of the segmented airways based on the tree model.
22. The computer readable medium of claim 19 , wherein the computer program instructions defining the step of extending the segmentation of the identified terminal branches comprise computer program instructions comprising the step of:
extending the segmentation of the terminal branches using adaptive region growing segmentation.
23. The computer readable medium of claim 19 , wherein the computer program instructions defining the step of extending the segmentation of the identified terminal branches comprise computer program instructions comprising the step of:
extending the segmentation of the terminal branches using differential adaptive region growing segmentation.
24. The computer readable medium of claim 19 , wherein the computer program instructions defining the step of extending the segmentation of the identified terminal branches comprise computer program instructions comprising the step of:
extending the segmentation of the terminal branches using fuzzy connectedness segmentation.
25. The computer readable medium of claim 19 , wherein the computer program instructions defining the step of extending the segmentation of the identified terminal branches comprise computer program instructions comprising the step of:
extending the segmentation of the terminal branches via branch tracking at the identified terminal branches.
26. A non-transitory computer readable medium storing computer program instructions, said computer program instructions defining the steps comprising:
segmenting airways in 3D image data using a first segmentation technique, wherein the segmented airways resulting from the first segmentation technique have a plurality of branches;
identifying one or more of the plurality of branches of the segmented airways resulting from said first segmentation technique as terminal branches; and
extending the identified terminal branches by performing segmentation at the terminal branches using a second segmentation technique.