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.

Date of Patent:
Aug. 15, 2017

Filed:

Feb. 26, 2016
Applicant:

Siemens Healthcare Gmbh, Erlangen, DE;

Inventors:

Bogdan Georgescu, Plainsboro, NJ (US);

Yefeng Zheng, Princeton Junction, NJ (US);

Hien Nguyen, Princeton, NJ (US);

Vivek Kumar Singh, Monmouth Junction, NJ (US);

Dorin Comaniciu, Princeton Junction, NJ (US);

David Liu, Franklin Park, NJ (US);

Assignee:

Siemens Healthcare GmbH, Erlangen, DE;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
A61B 5/00 (2006.01); G06T 7/00 (2017.01); G06K 9/46 (2006.01); G06K 9/62 (2006.01); G06T 7/73 (2017.01); A61B 6/00 (2006.01); A61B 8/08 (2006.01); A61B 8/00 (2006.01); A61B 5/055 (2006.01);
U.S. Cl.
CPC ...
A61B 5/7267 (2013.01); A61B 6/5217 (2013.01); A61B 8/5223 (2013.01); G06K 9/4628 (2013.01); G06K 9/6255 (2013.01); G06T 7/0012 (2013.01); G06T 7/73 (2017.01); A61B 5/055 (2013.01); A61B 6/503 (2013.01); A61B 6/507 (2013.01); A61B 6/563 (2013.01); A61B 8/0883 (2013.01); A61B 8/0891 (2013.01); A61B 8/565 (2013.01); G06K 2209/051 (2013.01); G06T 2200/04 (2013.01); G06T 2207/10072 (2013.01); G06T 2207/10132 (2013.01); G06T 2207/20016 (2013.01); G06T 2207/20024 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30048 (2013.01); G06T 2207/30101 (2013.01);
Abstract

A method and system for anatomical object detection using marginal space deep neural networks is disclosed. The pose parameter space for an anatomical object is divided into a series of marginal search spaces with increasing dimensionality. A respective sparse deep neural network is trained for each of the marginal search spaces, resulting in a series of trained sparse deep neural networks. Each of the trained sparse deep neural networks is trained by injecting sparsity into a deep neural network by removing filter weights of the deep neural network.


Find Patent Forward Citations

Loading…