US 12,136,209 B2
Orientation detection for 2D vessel segmentation for angio-FFR
Christian Haase, Hamburg (DE); Michael Grass, Buchholz in der Nordheide (DE); Martijn Anne Van Lavieren, Utrecht (NL); Cornelis Willem Johannes Immanuel Spoel, Helmond (NL); Romane Isabelle Marie-Bernard Gauriau, Paris (FR); Holger Schmitt, Luetjensee (DE); and Javier Olivan Bescos, Eindhoven (NL)
Assigned to KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
Appl. No. 17/288,357
Filed by KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
PCT Filed Oct. 25, 2019, PCT No. PCT/EP2019/079118
§ 371(c)(1), (2) Date Apr. 23, 2021,
PCT Pub. No. WO2020/084101, PCT Pub. Date Apr. 30, 2020.
Claims priority of application No. 18290125 (EP), filed on Oct. 26, 2018.
Prior Publication US 2021/0383539 A1, Dec. 9, 2021
Int. Cl. G06K 9/00 (2022.01); G06T 7/00 (2017.01)
CPC G06T 7/0012 (2013.01) [G06T 2207/10116 (2013.01); G06T 2207/20101 (2013.01); G06T 2207/30101 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus for assessing a vessel of interest of a patient, the apparatus comprising:
a processor in communication with memory, the processor configured to:
receive segmentation data to perform a vessel segmentation of the vessel of interest in at least one diagnostic image, the segmentation data defining a segmentation starting position and a segmentation ending position to segment the vessel of interest,
derive at least one vessel parameter for the vessel segmentation based on the segmentation data, and
classify the at least one vessel parameter to obtain an indication of a vessel segmentation orientation of the vessel segmentation, the vessel segmentation orientation indicating a blood flow direction between the segmentation starting position and the segmentation ending position,
wherein the classification is based on a classifier derived from a dataset correlating a set of known vessel segmentation orientations with a set of corresponding values of the at least one vessel parameter.