Abstract

Accurate measurement of the optical properties of biological tissue is very important for optical diagnosis and therapeutics. An artificial neural network (ANN)-based inverse reconstruction method is introduced to determine the optical properties of turbid media, which is based on the reflectance (R) and transmittance (T) of a thin sample measured by a double-integrating-spheres system. The accuracy and robustness of the method has been validated, and the results show that the root mean square errors (RMSEs) of the absorption coefficient \mu a and scattering coefficient \mu' s reconstruction are less than 0.01 cm^-1 and 0.02 cm^-1, respectively. The algorithm is not only very accurate in the case of a lower albedo (~0.33), but also very robust to the noise of R and T especially for the \mu' s reconstruction.

© 2010 Chinese Optics Letters

Efficient construction of robust artificial neural networks for accurate determination of superficial sample optical properties

Yu-Wen Chen and Sheng-Hao Tseng
Biomed. Opt. Express 6(3) 747-760 (2015)

Multiple polynomial regression method for determination of biomedical optical properties from integrating sphere measurements

Jan S. Dam, Torben Dalgaard, Paul Erik Fabricius, and Stefan Andersson-Engels
Appl. Opt. 39(7) 1202-1209 (2000)

Double-integrating-sphere system for measuring the optical properties of tissue

John W. Pickering, Scott A. Prahl, Niek van Wieringen, Johan F. Beek, Henricus J. C. M. Sterenborg, and Martin J. C. van Gemert
Appl. Opt. 32(4) 399-410 (1993)

Inverse hybrid technique for determining the optical properties of turbid media from integrating-sphere measurements

I. V. Yaroslavsky, A. N. Yaroslavsky, T. Goldbach, and H.-J. Schwarzmaier
Appl. Opt. 35(34) 6797-6809 (1996)

Accuracy of retrieving optical properties from liquid tissue phantoms using a single integrating sphere

Vinoin Devpaul Vincely and Karthik Vishwanath
Appl. Opt. 61(2) 375-385 (2022)