US 11,715,210 B2
Method for generating a 3D physical model of a patient specific anatomic feature from 2D medical images
Niall Haslam, Belfast (GB); Lorenzo Trojan, Belfast (GB); and Daniel Crawford, Belfast (GB)
Assigned to Axial Medical Printing Limited, Belfast (GB)
Filed by Axial Medical Printing Limited, Belfast (GB)
Filed on Jan. 4, 2023, as Appl. No. 18/150,112.
Application 18/150,112 is a continuation of application No. 17/656,189, filed on Mar. 23, 2022, granted, now 11,551,420, issued on Jan. 10, 2023.
Application 17/656,189 is a continuation of application No. 17/491,183, filed on Sep. 30, 2021, granted, now 11,288,865, issued on Mar. 29, 2022.
Application 17/491,183 is a continuation of application No. 17/115,102, filed on Dec. 8, 2020, granted, now 11,138,790, issued on Oct. 5, 2021.
Application 17/115,102 is a continuation of application No. 16/341,554, granted, now 11,497,557, issued on Nov. 15, 2022, previously published as PCT/GB2017/053125, filed on Oct. 16, 2017.
Claims priority of application No. 1617507 (GB), filed on Oct. 14, 2016.
Prior Publication US 2023/0141276 A1, May 11, 2023
Int. Cl. G06K 9/00 (2022.01); G06T 7/11 (2017.01); G06T 17/20 (2006.01); G06T 7/00 (2017.01); G16H 30/40 (2018.01); G16H 50/70 (2018.01); G16H 50/50 (2018.01); G06F 18/24 (2023.01); G06V 10/26 (2022.01)
CPC G06T 7/11 (2017.01) [G06F 18/24 (2023.01); G06T 7/0014 (2013.01); G06T 17/20 (2013.01); G06V 10/26 (2022.01); G16H 30/40 (2018.01); G16H 50/50 (2018.01); G16H 50/70 (2018.01); G06T 2200/08 (2013.01); G06T 2207/30004 (2013.01); G06V 2201/03 (2022.01)] 30 Claims
OG exemplary drawing
 
1. A method for defining a patient specific anatomical features from 2D medical images, the method comprising:
receiving, by a server, 2D medical images of a patient comprising one or more patient specific anatomical features and background information;
automatically processing, by the server, the 2D medical images using a segmentation algorithm to classify each pixel of the 2D medical images;
using, by the server, an anatomical feature identification algorithm to probabilistically match the classified pixels of the 2D medical images against a database of medical image anatomical features and generate a score for the classified pixels indicative of a likelihood that the classified pixel was classified correctly; and
generating, by the server, a dataset comprising the classification and the score for each pixel of the one or more patient specific anatomical features of the 2D medical images of the patient for defining the patient specific anatomical feature.