US 12,236,604 B2
Method for providing airway information
Dominik Neumann, Erlangen (DE); Puyang Wang, Baltimore, MD (US); Anna Boehm, Stuttgart (DE); Sasa Grbic, Plainsboro, NJ (US); Zhoubing Xu, Plainsboro, NJ (US); and Siqi Liu, Princeton, NJ (US)
Assigned to SIEMENS HEALTHINEERS AG, Forchheim (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on Feb. 17, 2021, as Appl. No. 17/177,286.
Claims priority of application No. 20160072 (EP), filed on Feb. 28, 2020.
Prior Publication US 2021/0272287 A1, Sep. 2, 2021
Int. Cl. G06T 7/00 (2017.01); G06T 7/11 (2017.01); G16H 30/00 (2018.01); G16H 50/20 (2018.01)
CPC G06T 7/11 (2017.01) [G16H 30/00 (2018.01); G16H 50/20 (2018.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30061 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for providing at least one quantitative airway information, comprising:
determining whether a proposed airway segment is curved;
in response to determining that the proposed airway segment is curved, subdividing the proposed airway segment into one or more segments and adding the one or more segments to a plurality of airway segments of an airway centerline tree;
in response to the proposed airway segment not being curved, adding the proposed airway segment to the plurality of airway segments;
determining first medical image data of an airway segment, the airway segment being selected from the plurality of airway segments;
applying a first trained function to the first medical image data, to generate output data, the output data including a mask of a wall of the airway segment;
determining the at least one quantitative airway information of the airway segment based on the output data; and
providing the at least one quantitative airway information, wherein
the airway segment is a portion of the airway centerline tree that is not curved,
the first medical image data is a slice that is extracted from second medical image data, the slice being orthogonal to the airway segment such that the slice includes a cross-section of the airway segment, and
the first medical image data is determined based on the airway centerline tree and the second medical image data.