US 12,340,509 B2
Systems and methods for automated digital image content extraction and analysis
Russell H. Amundson, Merion Station, PA (US); Saurabh Bhargava, Eden Prairie, MN (US); Rama Krishna Singh, Greater Noida (IN); Ravi Pande, Noida (IN); Vishwakant Gupta, Noida (IN); Destiny L. Babjack, Bethel Park, PA (US); Gaurav Mantri, Gurugram (IN); Abhinav Agrawal, Gulabpura (IN); and Sapeksh Suman, Greater Noida West (IN)
Assigned to UnitedHealth Group Incorporated, Minnetonka, MN (US)
Filed by UnitedHealth Group Incorporated, Minnetonka, MN (US)
Filed on Mar. 4, 2021, as Appl. No. 17/191,963.
Application 17/191,963 is a continuation of application No. 17/191,921, filed on Mar. 4, 2021, granted, now 11,869,189.
Claims priority of provisional application 62/991,686, filed on Mar. 19, 2020.
Prior Publication US 2021/0295504 A1, Sep. 23, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/00 (2017.01); G06F 18/2137 (2023.01); G06F 18/24 (2023.01); G06T 3/60 (2024.01); G06T 7/11 (2017.01); G06T 7/33 (2017.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06V 10/764 (2022.01); G06V 10/77 (2022.01); G16H 30/40 (2018.01); G16H 40/67 (2018.01)
CPC G06T 7/0014 (2013.01) [G06F 18/21375 (2023.01); G06F 18/24 (2023.01); G06T 3/60 (2013.01); G06T 7/0012 (2013.01); G06T 7/11 (2017.01); G06T 7/337 (2017.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06V 10/764 (2022.01); G06V 10/7715 (2022.01); G16H 30/40 (2018.01); G16H 40/67 (2018.01); G06T 2207/10024 (2013.01); G06T 2207/20024 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30004 (2013.01); G06T 2207/30012 (2013.01); G06T 2207/30068 (2013.01); G06T 2207/30088 (2013.01); G06T 2207/30096 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A system comprising:
memory; and one or more processors communicatively coupled to the memory, the one or more processors configured to:
receive an image comprising image content and associated metadata for a patient;
identify diagnosis criteria comprising at least one feature identification model;
apply the at least one feature identification model to the image content to identify a first feature and a second feature specified by the identified diagnosis criteria within the image content;
determine orientation information of the first feature and the second feature within the image content;
determine a positioning of the first feature and the second feature;
determine a location of the first feature relative to the second feature within the image content based at least in part on the orientation information of the first feature and the second feature and the positioning of the first feature and the second feature; and
determine a diagnosis for the patient based at least in part on the diagnosis criteria and the location of the first feature relative to the second feature.