US 12,475,569 B2
Methods and systems for segmenting images
Matthias Lenga, Mainz (DE); Christian Buerger, Hamburg (DE); and Steffen Renisch, Hamburg (DE)
Assigned to KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
Appl. No. 17/770,307
Filed by KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
PCT Filed Oct. 22, 2020, PCT No. PCT/EP2020/079679
§ 371(c)(1), (2) Date Apr. 20, 2022,
PCT Pub. No. WO2021/078823, PCT Pub. Date Apr. 29, 2021.
Claims priority of application No. 19204772 (EP), filed on Oct. 23, 2019.
Prior Publication US 2022/0398740 A1, Dec. 15, 2022
Int. Cl. G06T 7/149 (2017.01); G06T 7/50 (2017.01); G06V 10/46 (2022.01); G06V 10/82 (2022.01)
CPC G06T 7/149 (2017.01) [G06T 7/50 (2017.01); G06V 10/46 (2022.01); G06V 10/82 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A method of segmenting a feature in an image, the method comprising:
providing an image product, related in whole or in part to the image, to a model trained using a machine learning process, wherein the model has been trained to predict an indication of a shape descriptor based on training data comprising: example image products and corresponding ground truth shape descriptors for the example image products;
receiving from the model an indication of a shape descriptor for the feature in the image, based on the image product;
using the indicated shape descriptor in a model based segmentation (MBS) to initialize the MBS and segment the feature; and
using a mesh of a target structure that is adapted in an iterative fashion to features in the image.