US 12,094,112 B2
Coronary lumen and reference wall segmentation for automatic assessment of coronary artery disease
Mehmet Akif Gulsun, Princeton, NJ (US); Puneet Sharma, Princeton Junction, NJ (US); Diana Ioana Stoian, Brasov (RO); and Max Schöbinger, Hirschaid (DE)
Assigned to Siemens Healthineers AG, Forchheim (DE)
Filed by SIEMENS HEALTHINEERS AG, Forccheim (DE)
Filed on Jan. 27, 2022, as Appl. No. 17/649,067.
Prior Publication US 2023/0237648 A1, Jul. 27, 2023
Int. Cl. G06T 7/00 (2017.01); G06T 7/10 (2017.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); A61B 6/00 (2006.01); A61B 6/50 (2024.01)
CPC G06T 7/0012 (2013.01) [G06T 7/10 (2017.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); A61B 6/504 (2013.01); A61B 6/5217 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30048 (2013.01); G06T 2207/30096 (2013.01); G06T 2207/30101 (2013.01)] 23 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving one or more input medical images of a vessel of a patient;
performing a plurality of vessel assessment tasks for assessing the vessel using a machine learning based model trained using multi-task learning based on shared features extracted from the one or more input medical images, the plurality of vessel assessment tasks comprising segmentation of reference walls of the vessel from the one or more input medical images and segmentation of lumen of the vessel from the one or more input medical images, wherein the machine learning based model is trained for the segmentation of the reference wall of the vessel and the segmentation of the lumen of the vessel based on regularization for consistency between results of the segmentation of the reference walls of the vessel and results of the segmentation of the lumen of the vessel in regions without anomalies or lesions; and
outputting results of the plurality of vessel assessment tasks.