Determination of optical properties in double integrating sphere measurement by artificial neural network based method
Determination of optical properties in double integrating sphere measurement by artificial neural network based method
复制标题
DOI：
10.1007/s10043-020-00632-6
复制
发表时间：
2021-01
期刊：
影响因子：
1.2
通讯作者：
T. Nishimura;Yusaku Takai;Yu Shimojo;H. Hazama;K. Awazu
中科院分区：
文献类型：
--
作者：
T. Nishimura;Yusaku Takai;Yu Shimojo;H. Hazama;K. Awazu
双积分球测量中的精确反演技术是确定生物组织光学特性的关键。虽然有几个既定的技术，计算时间和复杂的光谱分析需要一些近似的各向异性因子g和折射率n。我们的目的是展示一种基于人工神经网络（ANN）的方法，以确定生物组织的漫反射率R，总透射率T，g和n的吸收和散射系数。使用通过用蒙特卡罗方法在DIS设置中计算光传输而生成的数据集来训练ANN。将测量的randT谱和波长依赖的randn输入计算和。由于简单和快速的计算，基于人工神经网络的方法可以计算的和光谱假设的波长依赖的gandn。训练好的神经网络对和的重建相对误差分别为1.1%和0.95%。在1.1ms内获得每个光学性质光谱（总共662个点）。
An accurate inversion technique in double integrating sphere (DIS) measurement is essential for determining the optical properties of biological tissue. Although there are several established techniques, the computational time and complexity for spectral analysis require some approximations of the anisotropy factorgand refractive indexn. We aim to demonstrate an artificial neural network (ANN) based method to determine the absorptionand scatteringcoefficients of biological tissue from the diffuse reflectanceR, total transmittanceT,g, andn. ANNs were trained using dataset generated by calculating light transport in the DIS setup with a Monte Carlo method. The measuredRandTspectra and the wavelength-dependentgandnwere inputted to calculateand. Due to the simple and fast calculation, the ANN-based method can calculate theandspectra assuming the wavelength dependence ofgandn. The relative errors of reconstruction by the trained networks were 1.1% and 0.95% forand, respectively. Each optical property spectra (total 662 points) was obtained in 1.1 ms. The proposed method can determineandin the DIS measurement assuming wavelength dependentgandn.