Patent · US Active

Method and system for approximating deep neural networks for anatomical object detection

US9633306B2 · kind B2 · utility

57Cited by

2References

33Claims

0Family size

Assignee

Siemens Healthcare Limited · DE

Inventors

David Liu · San Francisco, US
Nathan Lay · Plainsboro, US
Shaohua Kevin Zhou · Plainsboro, US
Jan Kretschmer · Nürnberg, DE
Hien Nguyen · Ngọc Lặc, VN
Vivek Singh · Monmouth Junction, US
Yefeng Zheng
Bogdan Georgescu · Plainsboro, US
Dorin Comaniciu · Princeton Junction, US

Key dates

Filing date	May 7, 2015
Grant date	Apr 25, 2017
Priority date	—
Expiry date	Jun 16, 2035

Classification

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

Abstract

A method and system for approximating a deep neural network for anatomical object detection is discloses. A deep neural network is trained to detect an anatomical object in medical images. An approximation of the trained deep neural network is calculated that reduces the computational complexity of the trained deep neural network. The anatomical object is detected in an input medical image of a patient using the approximation of the trained deep neural network.

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