US 12,283,368 B2
Method and device for determining presence of a tumor
Suparna Rayasam, Karnataka (IN)
Assigned to Siemens Healthineers AG, Forchheim (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on May 31, 2022, as Appl. No. 17/829,318.
Claims priority of application No. 21177295 (EP), filed on Jun. 2, 2021.
Prior Publication US 2022/0392618 A1, Dec. 8, 2022
Int. Cl. G16H 30/40 (2018.01); A61B 5/00 (2006.01); G06N 20/00 (2019.01); G06T 7/00 (2017.01); G06T 7/174 (2017.01); G06V 10/75 (2022.01)
CPC G16H 30/40 (2018.01) [A61B 5/004 (2013.01); G06N 20/00 (2019.01); G06T 7/0012 (2013.01); G06T 7/174 (2017.01); G06V 10/751 (2022.01); G06T 2207/30096 (2013.01); G06T 2207/30101 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method of determining a presence of a tumor in a patient, the method comprising:
receiving, by a processing unit, a medical image associated with the patient, wherein the medical image comprises a region of interest associated with the patient;
identifying, by the processing unit, one or more blood vessels associated with the region of interest in the medical image;
determining, by the processing unit, a set of characteristics associated with the one or more blood vessels using a trained machine learning model;
determining, by the trained machine learning model, whether the one or more blood vessels are feeder vessels associated with the tumor based on the set of characteristics associated with the one or more blood vessels; and
detecting, by the processing unit, a tumor region in the region of interest based on the feeder vessels when the one or more blood vessels are the feeder vessels associated with the tumor,
wherein determining whether the one or more blood vessels are the feeder vessels associated with the tumor comprises:
determining one or more radii associated with the one or more blood vessels, respectively, using a trained machine learning model;
determining radii associated with branching vessels originating from the one or more blood vessels, respectively, using the trained machine learning model;
computing one or more cubes of the one or more radii associated with the one or more blood vessels, respectively, and cubes of the radii associated with the branching vessels, respectively, using the trained machine learning model;
determining when a sum of the cubes of the radii associated with the branching vessels equals a sum of the one or more cubes of the one or more radii associated with the one or more blood vessels using the trained machine learning model; and
classifying the one or more blood vessels as the feeder vessels when the sum of the cubes of the radii associated with the branching vessels does not equal the sum of the one or more cubes of the one or more radii associated with the one or more blood vessels using the trained machine learning model.