Bone segmentation from image data
AssigneeKoninklijke Philips N.V.
InventorsLiran Goshen, Asher Gringauz
Life of this patent
Estimating the term…
Abstract
A method for segmenting bone in spectral image data is described herein. The spectral image data includes at least a first set of image data corresponding to a first energy and second set of image data corresponding to a second different energy. The method includes obtaining the spectral image data. The method further includes extracting a set of features for each voxel in spectral image data. The method further includes determining, for each voxel, a probability that each voxel represents bone structure based on the set of features. The method further includes extracting bone structure from the spectral image data based on the probabilities.
Claims17
A method for segmenting bone in spectral image data, which includes at least a first set of image data corresponding to a first energy and second set of image data corresponding to a second different energy, the method comprising:
- obtaining the spectral image data;
- extracting a set of features for each voxel in spectral image data, wherein the set of features are based on local spectral data and a structure represented in an adjacent voxel;
- determining, for each voxel, a probability that each voxel represents bone structure based on the set of features;
- and
- extracting bone structure from the spectral image data based on the probabilities.
A computing system, comprising:
- computer readable storage medium that stores a bone segmentation algorithm;
- and
- a computer processor that executes the bone segmentation algorithm, which causes the computer processor to:
- extract bone structure from spectral image data based on a probability that each voxel in the spectral image data represents bone structure;
- de-noise the spectral image data;
- extract a set of features for each voxel in de-noised spectral image data, wherein the set features are based on local spectral data and a structure represented in an adjacent voxel;
- determines, for each voxel, the probability based on the set of features;
- and
- extract the bone structure from the spectral image data based on the probabilities.
A computer readable storage medium encoded with one or more computer executable instructions, which, when executed by a processor of a computing system, causes the processor to:
- obtain spectral image data, wherein the spectral image data includes at least a first set of image data corresponding to a first energy and second set of image data corresponding to a second different energy;
- de-noise the spectral image data;
- extract a set of features for each voxel in de-noised spectral image data, wherein the set of features are based on local spectral data and a structure represented in an adjacent voxel;
- determine, for each voxel, a probability that each voxel represents bone structure based on the set of features;
- extract bone structure from the spectral image data based on the probabilities;
- and
- visually refine the extracted bone.
Dependencies are inferred from the claim text.