Sparse volume segmentation for 3D scans
View Patent ↗A computer readable medium is provided embodying instructions executable by a processor to perform a method for sparse volume segmentation for 3D scan of a target. The method including learning prior knowledge, providing volume data comprising the target, selecting a plurality of key contours of the image of the target, building a 3D spare model of the image of the target given the plurality of key contours, segmenting the image of the target given the 3D sparse model, and outputting a segmentation of the image of the target.
1. A non-transitory computer readable medium embodying instructions executable by a processor to perform a method for sparse volume segmentation for 3D scan of a target, the method comprising:
receiving an observation volume;
providing volume data comprising the target;
selecting a plurality of key contours of the volume data;
building a 3D sparse model of the volume data given the plurality of key contours;
determining a volumetric segmentation of a volume data by optimizing an image-based cost function with respect to simultaneously both the set of key contours in a reference space and a transformation which relates a reconstructed model to the observation volume; and
outputting a representation of the volume data based on the segmentation using the 3D sparse model.
2. The method of claim 1 , further comprising parameterizing the key contours in a reduced dimension space.
3. The method of claim 1 , wherein selecting the key contours includes determining key contour indices so that a squared distance between an interpolated volume and the target is minimized.
4. The method of claim 1 , wherein the 3D sparse model includes key indices, the key contours at the key indices, an interpolation operator, and an interpolated volume.
5. The method of claim 4 , wherein determining the volumetric segmentation comprises:
setting a global register of the volume data to the 3D sparse model in a model space;
segmenting the plurality of key contours at the key indices; and
inferring the volumetric segmentation of a portion of the volume data from the plurality of key contours.
6. The method of claim 5 , further comprising adjusting, locally, an interpolated volume to the volume data.
7. The method of claim 1 , wherein the plurality of key contours are 2D contours.
8. A non-transitory computer readable medium embodying instructions executable by a processor to perform a method for sparse volume segmentation for 3D scan of a target, the method comprising:
providing a 3D sparse model of a volume data including the target comprising key indices, key contours at the key indices, an interpolation operator, and an interpolated volume;
setting a global register of the volume data to the 3D sparse model in a model space;
segmenting the plurality of key contours at the key indices;
inferring a segmentation of a portion of the volume data from the plurality of key contours; and
outputting a representation of the volume including the plurality of key contours and the portion of the volume data inferred from the plurality of key contours.
9. The method of claim 8 , further comprising adjusting, locally, an interpolated volume to the volume data.
10. A computer system comprising:
a processor; and
a computer readable medium embodying instructions executable by the processor to perform a method for sparse volume segmentation for 3D scan of a target, the method comprising:
receiving an observation volume;
providing volume data comprising the target;
selecting a plurality of key contours of the volume data;
building a 3D sparse model of the volume data given the plurality of key contours;
determining a volumetric segmentation of a volume data by optimizing an image-based cost function with respect to simultaneously both the set of key contours in a reference space and a transformation which relates a reconstructed model to the observation volume; and
outputting a representation of the volume data based on the segmentation using the 3D sparse model.
11. The system of claim 10 , wherein the 3D sparse model includes key indices, the plurality of 2D key contours at the key indices, an interpolation operator, and an interpolated volume.