US 12,111,373 B2
Determination of a further processing location in magnetic resonance imaging
Karsten Sommer, Hamburg (DE); and Michael Gunter Helle, Hamburg (DE)
Assigned to Koninklijke Philips N.V., Eindhoven (NL)
Appl. No. 17/294,698
Filed by KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
PCT Filed Nov. 19, 2019, PCT No. PCT/EP2019/081797
§ 371(c)(1), (2) Date May 18, 2021,
PCT Pub. No. WO2020/104455, PCT Pub. Date May 28, 2020.
Claims priority of application No. 18207254 (EP), filed on Nov. 20, 2018.
Prior Publication US 2022/0012876 A1, Jan. 13, 2022
Int. Cl. G01R 33/54 (2006.01); G01R 33/56 (2006.01); G01R 33/563 (2006.01); G06N 3/045 (2023.01); G06N 3/084 (2023.01); G06T 7/00 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G01R 33/543 (2013.01) [G01R 33/546 (2013.01); G01R 33/5608 (2013.01); G01R 33/56308 (2013.01); G01R 33/56366 (2013.01); G06T 7/0012 (2013.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06T 2207/10096 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20101 (2013.01); G06T 2207/30016 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of training a neural network configured for providing a further processing location, the method comprising:
providing a labeled medical image, wherein the labeled medical image comprises a plurality of labels indicating a plurality of truth processing locations, respectively;
inputting the labeled medical image into the neural network to obtain a most likely trial processing location as an output of the neural network;
determining a closest truth processing location of the plurality of truth processing locations for the most likely trial processing location, wherein the closest truth processing location is a closest of the plurality of truth processing locations to the output of the neural network;
calculating an error vector using the closest truth processing location and the most likely trial processing location, wherein the error vector is a position change between the closest truth processing location and the most likely trial processing location, wherein the error vector is calculated only using the closest truth processing location and the most likely trial processing location; and
training the neural network using the error vector.