4D-MISR: A unified model for low-dose super-resolution imaging via feature fusion

2025-07-14

AI Summary

Radiation damage severely limits atomic-resolution imaging of beam-sensitive materials—such as proteins and 2D materials—in transmission electron microscopy (TEM). Method: This work proposes a unified low-dose 4D-scanning transmission electron microscopy (4D-STEM) super-resolution imaging framework. It introduces multi-view sub-pixel displacement fusion into electron microscopy and designs a dual-path attention neural network to enable robust atomic-scale reconstruction across amorphous, semi-crystalline, and crystalline materials. By synergistically optimizing multi-angle synthetic feature fusion and attention mechanisms, the method significantly enhances spatial information recovery from ultra-low-dose multi-frame datasets. Results: Experiments demonstrate atomic resolution (~1 Å), comparable to ptychography, on representative radiation-sensitive materials, while reducing electron dose by one to two orders of magnitude. This advances the applicability of 4D-STEM for structure–property correlation studies in fragile materials.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

While electron microscopy offers crucial atomic-resolution insights into structure-property relationships, radiation damage severely limits its use on beam-sensitive materials like proteins and 2D materials. To overcome this challenge, we push beyond the electron dose limits of conventional electron microscopy by adapting principles from multi-image super-resolution (MISR) that have been widely used in remote sensing. Our method fuses multiple low-resolution, sub-pixel-shifted views and enhances the reconstruction with a convolutional neural network (CNN) that integrates features from synthetic, multi-angle observations. We developed a dual-path, attention-guided network for 4D-STEM that achieves atomic-scale super-resolution from ultra-low-dose data. This provides robust atomic-scale visualization across amorphous, semi-crystalline, and crystalline beam-sensitive specimens. Systematic evaluations on representative materials demonstrate comparable spatial resolution to conventional ptychography under ultra-low-dose conditions. Our work expands the capabilities of 4D-STEM, offering a new and generalizable method for the structural analysis of radiation-vulnerable materials.

Problem

• Overcoming radiation damage in electron microscopy for beam-sensitive materials
• Achieving atomic-scale super-resolution from ultra-low-dose data
• Providing robust atomic-scale visualization for radiation-vulnerable materials

Innovation

• Fuses multiple low-resolution sub-pixel-shifted views
• Uses CNN with synthetic multi-angle feature integration
• Dual-path attention-guided network for 4D-STEM