Patent · US Active

Multi-task learning for chest X-ray abnormality classification

US10691980B1 · kind B1 · utility

12Cited by

0References

18Claims

0Family size

Assignee

Siemens Healthcare Limited · DE

Inventors

Sebastian Guendel · Erlangen, DE
Florin-Cristian Ghesu · Erlangen, DE
Eli Gibson · Plainsboro, US
Sasa Grbic · Plainsboro, US
Bogdan Georgescu · Plainsboro, US
Dorin Comaniciu · Princeton Junction, US

Key dates

Filing date	Sep 16, 2019
Grant date	Jun 23, 2020
Priority date	—
Expiry date	Sep 16, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06V2201/03
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Systems and methods are provided for automatic classification of multiple abnormalities that are visible in chest X-ray images. The systems and methods are based on a deep learning architecture that predicts, in addition to classification scores of abnormalities, lung/heart masks, and the location of certain abnormalities. By training a multi-task network to improve all the results, the network and the resulting abnormality classification is improved. Normalization of the chest X-ray images is also used to improve the accuracy and efficiency of the multi-task network.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.