A new image-reconstruction approach to optical computed tomography based on BP neural network

Qiong Wu; Zhiyu Qian

doi:10.1117/12.725453

11 January 2007 A new image-reconstruction approach to optical computed tomography based on BP neural network

Qiong Wu, Zhiyu Qian

Proceedings Volume 6279, 27th International Congress on High-Speed Photography and Photonics; 62792T (2007) https://doi.org/10.1117/12.725453
Event: 27th International congress on High-Speed Photography and Photonics, 2006, Xi'an, China

Abstract

A new image reconstruction approach to optical computed tomography is proposed in which a BP neural network is used to express the nonlinear relation between the change of optical properties inside the biology tissue and photons distributing change around the surface. A modeling and simulation tool named Femlab and finite element method has been tested wherein the forward model on a basis of the diffusion equation. Based on the forward problem, a BP neural network was established to solve the inverse problem. Thus, the position and its corresponding optical properties of tissue change could be recognized by the network. New approach was suitable for clinical application for its fast reconstruct characteristic.

Citation Download Citation

Qiong Wu and Zhiyu Qian "A new image-reconstruction approach to optical computed tomography based on BP neural network", Proc. SPIE 6279, 27th International Congress on High-Speed Photography and Photonics, 62792T (11 January 2007); https://doi.org/10.1117/12.725453

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available