AI-enabled Lorentz microscopy for quantitative imaging of nanoscale magnetic spin textures

TL;DR

This paper introduces an AI-based method for quantitative magnetic imaging at the nanoscale using Lorentz microscopy, significantly improving accuracy and noise robustness in phase retrieval from single images.

Contribution

It presents a novel AI-enabled phase-retrieval technique combining a generative deep image prior with a forward model, enabling real-time, quantitative magnetic imaging from minimal data.

Findings

Higher accuracy in phase retrieval compared to existing methods

Robustness to noise in experimental conditions

Ability to distinguish sample heterogeneities from magnetic contrast

Abstract

The manipulation and control of nanoscale magnetic spin textures is of rising interest as they are potential foundational units in next-generation computing paradigms. Achieving this requires a quantitative understanding of the spin texture behavior under external stimuli using in situ experiments. Lorentz transmission electron microscopy (LTEM) enables real-space imaging of spin textures at the nanoscale, but quantitative characterization of in situ data is extremely challenging. Here, we present an AI-enabled phase-retrieval method based on integrating a generative deep image prior with an image formation forward model for LTEM. Our approach uses a single out-of-focus image for phase retrieval and achieves significantly higher accuracy and robustness to noise compared to existing methods. Furthermore, our method is capable of isolating sample heterogeneities from magnetic contrast, as shown by application to simulated and experimental data. This approach allows quantitative phase reconstruction of in situ data and can also enable near real-time quantitative magnetic imaging.