US 12,148,166 B2
Updating boundary segmentations
Karim Amer, Cairo (EG); Noha El-Zehiry, Plainsboro, NJ (US); Gareth Funka-Lea, Princeton, NJ (US); and Athira Jane Jacob, Plainsboro, NJ (US)
Assigned to Siemens Healthineers AG, Forchheim (DE)
Appl. No. 17/635,105
Filed by Siemens Healthcare GmbH, Erlangen (DE)
PCT Filed Mar. 6, 2020, PCT No. PCT/EP2020/056041
§ 371(c)(1), (2) Date Feb. 14, 2022,
PCT Pub. No. WO2021/032325, PCT Pub. Date Feb. 25, 2021.
Claims priority of provisional application 62/887,743, filed on Aug. 16, 2019.
Prior Publication US 2022/0301177 A1, Sep. 22, 2022
Int. Cl. G06T 7/00 (2017.01); G06T 7/12 (2017.01)
CPC G06T 7/12 (2017.01) [G06T 7/0012 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/30048 (2013.01); G06T 2207/30168 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A computer-implemented method for updating a boundary segmentation, the method comprising:
receiving image data and an original boundary segmentation comprising a plurality of boundary points;
detecting a plurality of edges in the image data to generate an edge map;
computing a confidence for a boundary point in the original boundary segmentation, the confidence based on a distance between the boundary point and an edge point associated with at least one of the plurality of edges of the edge map;
determining a classification of the boundary point based on the computed confidence;
generating an updated boundary segmentation based on the classification of the boundary point, wherein generating comprises:
analyzing the boundary point to determine a group of boundary points representative of a connected component of the boundary segmentation;
determining at least one characteristic of the connected component;
refining the classification of the group of boundary points based on the at least one characteristic of the connected component; and
outputting the updated boundary segmentation.