Structure contouring, such as for segmentation or radiation treatment planning, using a 3D paint brush combined with an edge-detection algorithm
Techniques for contouring of a region of interest based on imaging parameters of spatial imaging data and guided by user input of locations in the spatial imaging data, which may be used for segmentation or radiation treatment planning. An approach of combining a new paint brush tool with an edge-detection algorithm to correct for both the jagged contours and the painting routine not being executed often enough. By using an edge-detection algorithm, the user does not need to focus as much attention on moving the mouse accurately because the system will find the true organ boundary (e.g., using the image gradient) automatically, which may also lead to more time savings.
1. A computer-implemented method of contouring of a region of interest based on imaging parameters of 3D spatial imaging data and guided by user input of locations in the spatial imaging data, the method comprising:
representing a paint brush shape for the contouring as a surface mesh including a plurality of rays and having a center located at a position of a cursor controlled by the user;
within the surface mesh, detecting structure edges for a boundary of the region of interest via an edge detection algorithm using the imaging parameters of the 3D spatial imaging data and along the plurality of rays;
smoothing the paint brush shape via a mesh smoothing algorithm; and
painting the boundary in the 3D spatial imaging data for display to the user, including:
painting the boundary in a current image slice; and
painting the boundary only in images slices in one direction from the current image slice, wherein the 3D spatial imaging data includes a plurality of image slices.
2. The method of claim 1 , wherein smoothing the paint brush shape via the mesh smoothing algorithm includes:
determining a total energy problem; and
processing the total energy problem to determine a solution to the total energy problem.
3. The method of claim 2 , wherein processing the total energy problem to determine the solution to the total energy problem includes:
determining a derivative of a total energy equation; and
minimizing the total energy equation.
4. The method of claim 2 , wherein determining the total energy problem includes:
determining an external energy contribution for the plurality of rays of the surface mesh; and
determining an internal energy contribution for edges of the surface mesh.
5. The method of claim 4 , comprising:
adjusting a smoothness of the mesh smoothing by applying a weighting factor to the determined internal energy contribution or the determined external energy contribution.
6. The method of claim 1 , wherein smoothing the paint brush shape via a mesh smoothing algorithm includes:
constraining the detected structure edges.
7. The method of claim 1 , comprising:
adjusting a sensitivity of the edge detection algorithm, wherein the sensitivity is based on a difference in image voxel gray values.
8. A non-transitory computer-readable storage device configured to include instructions that, when executed by a machine, cause the machine to perform operations comprising:
representing a paint brush shape for contouring as a surface mesh including a plurality of rays and having a center located at a position of a cursor controlled by a user;
within the surface mesh, detecting structure edges for a boundary of a region of interest via an edge detection algorithm using imaging parameters of spatial imaging data and along the plurality of rays;
smoothing the paint brush shape via a mesh smoothing algorithm; and
painting the boundary in the spatial imaging data for display to the user, including:
painting the boundary in a current image slice; and
painting the boundary only in images slices in one direction from the current image slice, wherein the spatial imaging data includes a plurality of image slices.
9. The computer-readable storage device of claim 8 , wherein smoothing the paint brush shape via the mesh smoothing algorithm comprises:
determining a total energy problem; and
processing the total energy problem to determine a solution to the total energy problem.
10. The computer-readable storage device of claim 9 , wherein processing the total energy problem to determine the solution to the total energy problem comprises:
determining a derivative of a total energy equation; and
minimizing the total energy equation.
11. The computer-readable storage device of claim 9 , wherein determining the total energy problem comprises:
determining an external energy contribution for the plurality of rays of the surface mesh; and
determining an internal energy contribution for edges of the surface mesh.
12. The computer-readable storage device of claim 11 , wherein the operations comprise:
adjusting a smoothness of the mesh smoothing by applying a weighting factor to the determined internal energy contribution.
13. The computer-readable storage device of claim 8 , wherein smoothing the paint brush shape via a mesh smoothing algorithm includes:
constraining the detected structure edges.
14. The computer-readable storage device of claim 8 , wherein the operations comprise:
adjusting a sensitivity of the edge detection algorithm, wherein the sensitivity is based on a difference in image voxel gray values.
15. A computer-implemented method of contouring of a region of interest based on imaging parameters of spatial imaging data and guided by user input of locations in the spatial imaging data, the method comprising:
representing a paint brush shape for contouring as a surface mesh including a plurality of rays and having a center located at a position of a cursor controlled by a user;
within the surface mesh, detecting structure edges for a boundary of the region of interest via an edge detection algorithm using the imaging parameters of the spatial imaging data and along the plurality of rays;
smoothing the paint brush shape via a mesh smoothing algorithm; and
painting the boundary in the spatial imaging data for display to the user, including:
painting the boundary in a current image slice; and
painting the boundary only in a user-selected number of images slices in one direction from the current image slice, wherein the spatial imaging data includes a plurality of image slices.
16. The method of claim 15 , wherein smoothing the paint brush shape via the mesh smoothing algorithm includes:
determining a total energy problem; and
processing the total energy problem to determine a solution to the total energy problem.
17. The method of claim 16 , wherein processing the total energy problem to determine the solution to the total energy problem includes:
determining a derivative of a total energy equation; and
minimizing the total energy equation.
18. The method of claim 16 , wherein determining the total energy problem includes:
determining an external energy contribution for the plurality of rays of the surface mesh; and
determining an internal energy contribution for edges of the surface mesh.
19. The method of claim 18 , comprising:
adjusting a smoothness of the mesh smoothing by applying a weighting factor to the determined internal energy contribution or the determined external energy contribution.
20. The method of claim 15 , wherein smoothing the paint brush shape via a mesh smoothing algorithm includes:
constraining the detected structure edges.
21. The method of claim 15 , comprising:
adjusting a sensitivity of the edge detection algorithm, wherein the sensitivity is based on a difference in image voxel gray values.
22. A non-transitory computer-readable storage device configured to include instructions that, when executed by a machine, cause the machine to perform operations comprising:
representing a paint brush shape for contouring as a surface mesh including a plurality of rays and having a center located at a position of a cursor controlled by a user;
within the surface mesh, detecting structure edges for a boundary of a region of interest via an edge detection algorithm using imaging parameters of spatial imaging data and along the plurality of rays;
smoothing the paint brush shape via a mesh smoothing algorithm; and
painting the boundary in the spatial imaging data for display to the user, including:
painting the boundary in a current image slice; and
painting the boundary only in a user-selected number of images slices in one direction from the current image slice, wherein the spatial imaging data includes a plurality of image slices.
23. The computer-readable storage device of claim 22 , wherein smoothing the paint brush shape via the mesh smoothing algorithm comprises:
determining a total energy problem; and
processing the total energy problem to determine a solution to the total energy problem.
24. The computer-readable storage device of claim 23 , wherein processing the total energy problem to determine the solution to the total energy problem comprises:
determining a derivative of a total energy equation; and
minimizing the total energy equation.
25. The computer-readable storage device of claim 23 , wherein determining the total energy problem comprises:
determining an external energy contribution for the plurality of rays of the surface mesh; and
determining an internal energy contribution for edges of the surface mesh.
26. The computer-readable storage device of claim 25 , wherein the operations comprise:
adjusting a smoothness of the mesh smoothing by applying a weighting factor to the determined internal energy contribution.
27. The computer-readable storage device of claim 22 , wherein smoothing the paint brush shape via a mesh smoothing algorithm includes:
constraining the detected structure edges.
28. The computer-readable storage device of claim 22 , wherein the operations comprise:
adjusting a sensitivity of the edge detection algorithm, wherein the sensitivity is based on a difference in image voxel gray values.