Open AccessInverse dynamical photon scattering (IDPS): an artificial neural network based algorithm for three-dimensional quantitative imaging in optical microscopy
Author(s) -
Xiaoming Jiang,
Wouter Van den Broek,
Christoph T. Koch
Publication year - 2016
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.24.007006
Subject(s) - inverse problem , inverse scattering problem , optics , artificial neural network , computer science , regularization (linguistics) , microscopy , image processing , algorithm , inverse , artificial intelligence , physics , scattering , mathematics , image (mathematics) , mathematical analysis , geometry
Inverse dynamical photon scattering (IDPS), an artificial neural network based algorithm for three-dimensional quantitative imaging in optical microscopy, is introduced. Because the inverse problem entails numerical minimization of an explicit error metric, it becomes possible to freely choose a more robust metric, to introduce regularization of the solution, and to retrieve unknown experimental settings or microscope values, while the starting guess is simply set to zero. The regularization is accomplished through an alternate directions augmented Lagrangian approach, implemented on a graphics processing unit. These improvements are demonstrated on open source experimental data, retrieving three-dimensional amplitude and phase for a thick specimen.