Constrained training of artificial neural networks using labelled medical data of mixed quality

US12148201B2 · kind B2 · utility

Assignee

• KONINIKLIJKE PHILIPS N.V. · NL

Inventors

• SVEN KROENKE · Hamburg, DE
• Jens Von Berg · Hamburg, DE
• Daniel Bystrov · Hamburg, DE
• Bernd Lundt · Hamburg, DE
• Nataly Wieberneit · Hamburg, DE
• Stewart Young · Hamburg, DE

Key dates

• Filing date: Nov 9, 2020
• Grant date: Nov 19, 2024
• Expiry date: Nov 18, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V2201/03
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

The invention relates to a method (100) for supervised training of an artificial neural network for medical image analysis. The method comprises acquiring (SI) first and second sets of training samples, wherein the training samples comprise feature vectors and associated predetermined labels, the feature vectors being indicative of medical images and the labels pertaining to anatomy detection, to semantic segmentation of medical images, to classification of medical images, to computer-aided diagnosis, to detection and/or localization of biomarkers or to quality assessment of medical images. The accuracy of predetermined labels may be better for the second set of training samples than for the first set of training samples. The neural network is trained (S3) by reducing a cost function, which comprises a first and a second part. The first part of the cost function depends on the first set of training samples, and the second part of the cost function depends on a first subset of training samples, the first subset being a subset of the second set of training samples. In addition, the second part of the cost function depends on an upper bound for the average prediction performance of th…