US 12,131,525 B2
Multi-task deep learning method for a neural network for automatic pathology detection
Alexandra Groth, Hamburg (DE); Axel Saalbach, Hamburg (DE); Ivo Matteo Baltruschat, Hamburg (DE); Jens Von Berg, Hamburg (DE); and Michael Grass, Buchholz In Der Nordheide (NL)
Assigned to KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
Appl. No. 17/620,142
Filed by KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
PCT Filed Jun. 25, 2020, PCT No. PCT/EP2020/067821
§ 371(c)(1), (2) Date Dec. 17, 2021,
PCT Pub. No. WO2020/260459, PCT Pub. Date Dec. 30, 2020.
Claims priority of application No. 19183052 (EP), filed on Jun. 27, 2019.
Prior Publication US 2022/0319160 A1, Oct. 6, 2022
Int. Cl. G06V 10/00 (2022.01); G06T 7/00 (2017.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 10/96 (2022.01); G06V 20/70 (2022.01)
CPC G06V 10/82 (2022.01) [G06T 7/0012 (2013.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/96 (2022.01); G06V 20/70 (2022.01); G06T 2207/10081 (2013.01); G06T 2207/10124 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06V 2201/03 (2022.01)] 10 Claims
OG exemplary drawing
 
1. A multi-task deep learning method for a neural network for automatic pathology detection, comprising:
receiving first image data for a first image recognition task;
receiving second image data for a second image recognition task, wherein the first image data is of a first datatype, and the second image data is of a second datatype being different from the first datatype;
labeling the first image data;
synthesizing the second image data into the first datatype and/or first dimension;
labeling the synthesized second image data; and
training the neural network based on the received first image data, the received second image data, the labeled first image data and the synthesized labeled second image data;
wherein the first image recognition task and the second image recognition task relate to a same anatomic region where the respective image data is taken from and/or relate to a same pathology to be recognized in the respective image data.