US 12,142,365 B2
Method for registration of image data and for provision of corresponding trained facilities, apparatus for doing so and corresponding computer program product
Christian Kaethner, Forchheim (DE); and Alois Regensburger, Poxdorf (DE)
Assigned to Siemens Healthineers AG, Forchheim (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on Dec. 9, 2020, as Appl. No. 17/116,190.
Claims priority of application No. 10 2019 219 246.7 (DE), filed on Dec. 10, 2019.
Prior Publication US 2021/0174523 A1, Jun. 10, 2021
Int. Cl. G16H 30/40 (2018.01); G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06T 7/00 (2017.01); G06T 7/11 (2017.01); G06T 7/33 (2017.01); G06V 10/26 (2022.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01); G16H 50/20 (2018.01)
CPC G16H 30/40 (2018.01) [G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06T 7/0012 (2013.01); G06T 7/11 (2017.01); G06T 7/337 (2017.01); G06V 10/26 (2022.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/803 (2022.01); G06V 10/82 (2022.01); G16H 50/20 (2018.01); G06T 2207/10081 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30101 (2013.01); G06V 2201/03 (2022.01)] 22 Claims
OG exemplary drawing
 
1. A method for registration of a patient's preoperative image data with the patient's intra-operative image data, the method comprising:
training a first machine-learning facility to identify predetermined anatomical landmarks present in preoperative image data;
training a second machine-learning facility to identify in intra-operative image data the predetermined anatomical landmarks identified by the first machine learning facility, whereby an overfitting of the second machine-learning facility is performed on the predetermined anatomical landmarks, wherein the intra-operative image data is of a lower resolution or includes an inferior contrast ratio than the preoperative image data;
identifying one or more predetermined anatomical landmarks in the patient's preoperative image data by the first machine-learning facility;
identifying the one or more predetermined anatomical landmarks in the patient's intra-operative image data by the second machine-learning facility; and
registering the patient's preoperative image data with the patient's intra-operative image data with an aid of the identified one or more predetermined anatomical landmarks by the first machine-learning facility and the second machine-learning facility, wherein the patient's intra-operative image data is of a lower resolution or includes an inferior contrast ratio than the patient's preoperative image data.