Deep-Learning Projector for Optical Diffraction Tomography
F. Yang, T.-a. Pham, H. Gupta, M. Unser, J. Ma
Optics Express, vol. 28, no. 3, pp. 3905-3921, February 3, 2020.
Optical diffraction tomography is an effective tool to estimate the refractive indices of unknown objects. It proceeds by solving an ill-posed inverse problem for which the wave equation governs the scattering events. The solution has traditionally been derived by the minimization of an objective function in which the data-fidelity term encourages measurement consistency while the regularization term enforces prior constraints. In this work, we propose to train a convolutional neural network (CNN) as the projector in a projected-gradient-descent method. We iteratively produce high-quality estimates and ensure measurement consistency, thus keeping the best of CNN-based and regularization-based worlds. Our experiments on two-dimensional-simulated and real data show an improvement over other conventional or deep-learning-based methods. Furthermore, our trained CNN projector is general enough to accommodate various forward models for the handling of multiple-scattering events.
@ARTICLE(http://bigwww.epfl.ch/publications/yang2001.html, AUTHOR="Yang, F. and Pham, T.-a. and Gupta, H. and Unser, M. and Ma, J.", TITLE="Deep-Learning Projector for Optical Diffraction Tomography", JOURNAL="Optics Express", YEAR="2020", volume="28", number="3", pages="3905--3921", month="February 3,", note="")