US 12,148,201 B2
Constrained training of artificial neural networks using labelled medical data of mixed quality
Sven Kroenke, Hamburg (DE); Jens Von Berg, Hamburg (DE); Daniel Bystrov, Hamburg (DE); Bernd Lundt, Hamburg (DE); Nataly Wieberneit, Hamburg (DE); and Stewart Young, Hamburg (DE)
Assigned to KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
Appl. No. 17/776,083
Filed by KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
PCT Filed Nov. 9, 2020, PCT No. PCT/EP2020/081434
§ 371(c)(1), (2) Date May 11, 2022,
PCT Pub. No. WO2021/094238, PCT Pub. Date May 20, 2021.
Claims priority of application No. 19209033 (EP), filed on Nov. 14, 2019.
Prior Publication US 2022/0392198 A1, Dec. 8, 2022
Int. Cl. G06V 10/774 (2022.01); G06T 7/00 (2017.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G16H 30/40 (2018.01)
CPC G06V 10/774 (2022.01) [G06T 7/0012 (2013.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G16H 30/40 (2018.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06V 2201/03 (2022.01)] 14 Claims
OG exemplary drawing
 
1. A computer-implemented method for supervised training of an artificial neural network for a medical image analysis, the method comprising:
acquiring first and second sets of training samples;
acquiring an upper bound for an average prediction performance of the neural network for a first subset of the second set of training samples; and
training the neural network by reducing a cost function,
wherein the training samples comprise feature vectors and associated predetermined labels, the feature vectors being indicative of medical images and the labels pertaining to at least one of anatomy detection, semantic segmentation of medical images, classification of medical images, computer-aided diagnosis, detection and/or localization of biomarkers, and quality assessment of medical images;
wherein the cost function comprises a first part and a second part;
wherein the first part of the cost function depends on the first set of training samples;
wherein the second part of the cost function depends on the first subset of training samples and the upper bound for the average prediction performance of the neural network for the first subset of training samples, and
wherein the second part of the cost function is configured to prevent the upper bound from exceeding the average prediction performance for the first subset of training samples.