Method for segmenting medical images and detecting surface anomalies in anatomical structures
First Claim
1. A method for segmenting an anatomical structure represented in a three-dimensional data set, the method comprising:
- starting from a point in the three dimensional data set, growing a region in the anatomical structure by modifying coordinates of a voxel in the region to find a next generation voxel, examining a characteristic of the next generation voxel, and adding the next generation voxel to the region when the characteristic of the voxel is within a threshold; and
growing the region with successive generations of voxels along a path in the three dimensional data set using a path length limit to limit the number of generations of voxel growth from the starting point.
2 Assignments
0 Petitions
Accused Products
Abstract
A region growing method segments three-dimensional image data of an anatomical structure using a tortuous path length limit to constrain voxel growth. The path length limit constrains the number of successive generations of voxel growth from a seed point to prevent leakage of voxels outside the boundary of the anatomical structure. Once segmented, a process for detecting surface anomalies performs a curvature analysis on a computer model of the surface of the structure. This process detects surface anomalies automatically by traversing the vertices in the surface model, computing partial derivatives of the surface at the vertices, and computing curvature characteristics from the partial derivatives. To identify possible anomalies, the process compares the curvature characteristics with predetermined curvature characteristics of anomalies and classifies the vertices. The process further refines potential anomalies by segmenting neighboring vertices that are classified as being part of an anomaly using curvature characteristics. Finally, the process colorizes the anomalies and computes a camera position and direction for each one to assist the user in viewing 2D renderings of the computer model.
-
Citations
16 Claims
-
1. A method for segmenting an anatomical structure represented in a three-dimensional data set, the method comprising:
-
starting from a point in the three dimensional data set, growing a region in the anatomical structure by modifying coordinates of a voxel in the region to find a next generation voxel, examining a characteristic of the next generation voxel, and adding the next generation voxel to the region when the characteristic of the voxel is within a threshold; and
growing the region with successive generations of voxels along a path in the three dimensional data set using a path length limit to limit the number of generations of voxel growth from the starting point. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15)
using directional criteria as a constraint in modifying coordinates of a voxel in the region to identify a voxel in the next generation of the region, where the directional criteria controls growth in selected directions according to a predetermined rate for the selected directions.
-
-
7. The method of claim 6 wherein the predetermined rate is achieved by expanding coordinates of a voxel in the region in a selected direction at a different rate than a rate at which other directions are expanded such that voxel growth proceeds more quickly in the selected direction.
-
8. The method of claim 6 wherein the directional criteria comprises a ratio of relative rates of growth in different directions from faces of a voxel.
-
9. The method of claim 1 further including:
-
creating a 3D surface model approximating points on a surface of the structure from the voxels identified as being part of the region; and
rendering the 3D surface model from a selected camera position to create a two-dimensional image representing the structure as viewed from the selected camera position.
-
-
10. The method of claim 9 wherein the step of creating the 3D surface model includes:
-
using the voxels in the region, identifying adjacent voxels that share a vertex, assigning the intensities of the neighboring voxels to a corresponding vertex, adding the vertex to a 3D array, and repeating the identifying, assigning and adding steps for subsequent groups of adjacent voxels to create the 3D array;
identifying a surface passing through the 3D array that satisfies an isosurface threshold using the intensities assigned to the vertices in the 3D array; and
triangulating the surface to create a surface model comprising an array of triangles.
-
-
11. The method of claim 10 further including:
-
traversing the surface model to identify surface anomalies that have a predetermined curvature; and
flagging the surface anomalies to enable a user to view each of the surface anomalies selectively as 2D image renderings of the surface model from camera positions directed at the surface anomalies.
-
-
12. The method of claim 11 wherein the structure represents a wall of a bronchus captured from a scan of a human patient, and the surface anomalies represent lesions detected on the wall during the traversing step.
-
13. The method of claim 11 further including:
-
fitting a curve to selected vertices in the surface model;
computing an extent of curvature of the fitted curve to evaluate whether the surface at the selected vertices has a predetermined curvature;
when the surface at the selected vertices has the predetermined curvature, recording a location of the selected vertices as a surface anomaly.
-
-
14. The method of claim 11 further including:
in a 3D rendering application, successively repositioning the camera position in the direction of a different surface anomaly to guide a user to the surface anomalies in selected 2D image renderings of the surface model.
-
15. A computer readable medium having instructions for performing the steps of claim 1.
-
16. In a method of constraining voxel growth in a computer model of an anatomical structure, the method including analyzing successive voxels along a path to determine whether the successive voxels satisfy a predetermined constraint indicating that the voxels are part of the structure, an improvement comprising:
establishing a path length limit, tracking the path length to each voxel, and discontinuing further voxel growth when the path length limit is reached.
Specification