IDiyas

For the Inventor, By the Inventor

The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Patent No.:

US 10606982 B1

PDFFull Text
Date of Patent:
Mar. 31, 2020

Filed:

Sep. 06, 2017

Iterative semi-automatic annotation for workload reduction in medical image labeling

Applicant:

International Business Machines Corporation, Armonk, NY (US);

Inventors:

Yufan Guo, San Jose, CA (US);

Yaniv Gur, San Jose, CA (US);

Mehdi Moradi, San Jose, CA (US);

Assignee:

Other;

Attorneys:

Erik Huestis

Stephen Kenny

Foley Hoag

Primary Examiner:

Jose L Couso

Int. Cl.
CPC ...
G06K 9/00 (2006.01); G06F 19/00 (2018.01); G06K 9/62 (2006.01); G06F 17/24 (2006.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G06F 17/27 (2006.01); G06F 3/0482 (2013.01); G06N 5/00 (2006.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); G06N 3/04 (2006.01);
U.S. Cl.
CPC ...
G06F 19/321 (2013.01); G06F 17/241 (2013.01); G06F 17/2785 (2013.01); G06K 9/6253 (2013.01); G06K 9/6263 (2013.01); G06K 9/6267 (2013.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G06F 3/0482 (2013.01); G06N 3/04 (2013.01); G06N 5/003 (2013.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01);
Abstract

Semi-automatic annotation of medical images is provided. In various embodiments, a classifier is applied to each of a first plurality of medical images to generate a label and an associated confidence value for each of the first plurality of medical images. The classifier is pre-trained using a manually labeled set of medical images. Those of the first plurality of medical images having an associated confidence value below a predetermined threshold are selected. The selected medical images are provided to a user. Updated labels are received from the user for the selected medical images. The classifier is retrained using the first plurality of medical images, with the updated labels for the selected medical images and the generated labels for medical images not selected.

Find Patent Forward Citations

Loading…