Adaptive Regularization for Three-dimensional Optical Diffraction Tomography

Thanh-An Pham (1, 2) , Emmanuel Soubies (3, 4, 5) , Ahmed Ayoub (2) , Demetri Psaltis (2) , Michael Unser (1, 2)

1 Biomedical Imaging Group [Lausanne]
2 EPFL - Ecole Polytechnique Fédérale de Lausanne
3 CNRS - Centre National de la Recherche Scientifique
4 IRIT-SC - Signal et Communications
5 UT - Université de Toulouse

Optical diffraction tomography (ODT) allows one to quantitatively measure the distribution of the refractive index of the sample. It relies on the resolution of an inverse scattering problem. Due to the limited range of views as well as optical aberrations and speckle noise, the quality of ODT reconstructions is usually better in lateral planes than in the axial direction. In this work, we propose an adaptive regularization to mitigate this issue. We first learn a dictionary from the lateral planes of an initial reconstruction that is obtained with a total-variation regularization. This dictionary is then used to enhance both the lateral and axial planes within a final reconstruction step. The proposed pipeline is validated on real data using an accurate nonlinear forward model. Comparisons with standard reconstructions are provided to show the benefit of the proposed framework. Index Terms-plug-and-play, nonlinear inverse problems, dictionary learning, computational imaging.

Mots clés: nonlinear inverse problems; computational imaging; dictionary learning; plug-and-play

Domaines: Traitement des images [eess.IV]; Traitement du signal et de l'image [eess.SP]; Optique / photonique

Thanh-An Pham, Emmanuel Soubies, Ahmed Ayoub, Demetri Psaltis, Michael Unser. Adaptive Regularization for Three-dimensional Optical Diffraction Tomography. , 2020 IEEE 16th International Symposium on Biomedical Imaging (ISBI), Apr 2020, Iowa City, United States. ⟨10.1109/ISBI45749.2020.9098523⟩. ⟨hal-02444659⟩