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

TL;DR

This paper introduces an open-access, flexible ptychography reconstruction framework using automatic differentiation in TensorFlow, achieving comparable results to existing methods and enabling novel parameter optimization, validated through simulations and biological experiments.

Contribution

It presents a new AD-based ptychography framework that is flexible, open-source, and capable of optimizing parameters like reconstruction distance, with validation on simulations and biological samples.

Findings

Framework performs comparably to state-of-the-art methods in speed and quality.

Demonstrates flexibility by optimizing reconstruction distance as a trainable parameter.

Successfully reconstructs biological specimens experimentally.

Abstract

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). Here, 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. Lastly, we experimentally demonstrate that our framework faithfully reconstructs a biological specimen.