Publication in OSA Continuum

Efficient and flexible approach to ptychography using an optimization framework based on automatic differentiation

Ptychography is a lensless imaging method that allows for wavefront sensing and phase-sensitive microscopy from a set of diffraction patterns.  Recently, it has been shown that the optimization task in ptychography can be achieved via automatic differentiation (AD). We propose an open-access AD-based framework implemented with TensorFlow, a popular machine learning library. Using simulations, we show that our AD-based framework performs comparably to a state-of-the-art implementation of the momentum-accelerated ptychographic iterative engine (mPIE) in terms of reconstruction speed and quality. AD-based approaches provide great flexibility, as we demonstrate by setting the reconstruction distance as a trainable parameter. Additionally, we experimentally demonstrate that our framework faithfully reconstructs a biological specimen.
The presented results are important for establishing optimization frameworks based on AD as viable methods within the field of coherent diffraction imaging and ptychography. Moreover, we can expect AD-based techniques to further improve thanks to the fast-paced progress in machine-learning toolboxes like TensorFlow and in computer hardware like application-specific integrated circuits (e.g., tensor processing units).


Efficient and flexible approach to ptychography using an optimization framework based on automatic differentiation
J. Seifert, D. Bouchet, L. Loetgering and A.P. Mosk, OSA Continuum 4 (1), 121-128 (2021). DOI: 10.1364/OSAC.411174