Using a modified double deep image prior for crosstalk mitigation in multislice ptychography

TL;DR

This paper introduces a modified double deep image prior (DDIP) approach to effectively reduce crosstalk artifacts in multislice ptychography, enhancing image quality without additional experimental data.

Contribution

The paper presents a novel modified DDIP architecture specifically designed for crosstalk mitigation in multislice ptychography, demonstrating its effectiveness on experimental data.

Findings

DDIP effectively reduces crosstalk artifacts.

The method eliminates the need for supplementary experimental data.

Improves multislice ptychography image reconstruction quality.

Abstract

Multislice ptychography is a high-resolution microscopy technique used to image multiple separate axial planes using a single illumination direction. However, multislice ptychography reconstructions are often degraded by crosstalk, where some features on one plane erroneously contribute to the reconstructed image of another plane. Here, we demonstrate the use of a modified "double deep image prior" (DDIP) architecture in mitigating crosstalk artifacts in multislice ptychography. Utilizing the tendency of generative neural networks to produce natural images, a modified DDIP method yielded good results on experimental data. For one of the datasets, we show that using DDIP could remove the need of using additional experimental data, such as from x-ray fluorescence, to suppress the crosstalk. Our method may help x-ray multislice ptychography work for more general experimental scenarios.