US 12,444,054 B2
Localization and classification of abnormalities in medical images
Ali Kamen, Skillman, NJ (US); Bin Lou, Princeton Junction, NJ (US); Bibo Shi, Monmouth Junction, NJ (US); Nicolas Von Roden, St Gallen (CH); Berthold Kiefer, Erlangen (DE); Robert Grimm, Nuremberg (DE); Heinrich von Busch, Uttenreuth (DE); Mamadou Diallo, Plainsboro, NJ (US); Tongbai Meng, Ellicott City, MD (US); Dorin Comaniciu, Princeton, NJ (US); David Jean Winkel, Basel (CH); and Xin Yu, Nashville, TN (US)
Assigned to Siemens Healthineers AG, Forchheim (DE)
Filed by Siemens Healthineers AG, Forchheim (DE)
Filed on Feb. 20, 2025, as Appl. No. 19/058,065.
Application 19/058,065 is a continuation of application No. 18/166,128, filed on Feb. 8, 2023.
Application 18/166,128 is a continuation of application No. 17/809,385, filed on Jun. 28, 2022, granted, now 11,610,308, issued on Mar. 21, 2023.
Application 17/809,385 is a continuation of application No. 15/733,778, granted, now 11,403,750, issued on Aug. 2, 2022, previously published as PCT/EP2019/065447, filed on Jun. 13, 2019.
Claims priority of provisional application 62/687,294, filed on Jun. 20, 2018.
Claims priority of provisional application 62/684,337, filed on Jun. 13, 2018.
Prior Publication US 2025/0232445 A1, Jul. 17, 2025
Int. Cl. G06T 7/00 (2017.01); G06F 18/214 (2023.01); G06F 18/2411 (2023.01); G06N 20/00 (2019.01); G06T 7/11 (2017.01); G06V 10/26 (2022.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G06T 7/0014 (2013.01) [G06F 18/214 (2023.01); G06F 18/2411 (2023.01); G06N 20/00 (2019.01); G06T 7/0012 (2013.01); G06T 7/11 (2017.01); G06V 10/26 (2022.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06T 2207/10088 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30096 (2013.01)] 30 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a plurality of input medical images;
localizing a lesion in each of the plurality of input medical images using a trained localization network;
classifying the lesion in each of the plurality of input medical images based on the localizing, using a trained classification network, to generate a classification result for the lesion in each of the plurality of input medical images;
combining the classification results; and
outputting the combined classification results.