TEM Software Publications Library

This work demonstrates live analysis of 4D-STEM data by integrating LiberTEM with the ARINA detector platform. The approach enables immediate feedback during acquisition, helping researchers evaluate experiments as data is collected.

This paper explores how machine learning enables automated experimentation in scanning transmission electron microscopy. The framework supports real-time decision-making, adaptive measurements, and closed-loop microscope operation.

This chapter introduces machine learning concepts and practical implementations using the scikit-learn library. It provides guidance for building, training, and evaluating predictive models in Python.

This paper applies machine-learning methods to classify obfuscated ransomware families. The framework improves cybersecurity analysis by identifying malware variants from complex behavioral patterns.

PyEBSDIndex accelerates electron backscatter diffraction pattern indexing using graphics processing units. The software improves computational efficiency and enables rapid analysis of large EBSD datasets.

This paper presents Pyxem, a Python toolkit built for processing and interpreting 4D-STEM experiments. The package supports diffraction analysis, structural mapping, visualization, and scalable handling of multidimensional microscopy measurements.

This study applies deep learning segmentation and modelling techniques to quantitative analysis of 3D electron microscopy datasets. The workflow improves object identification, measurement accuracy, and biological structure characterization.

SimpliPyTEM delivers an accessible library and graphical application for TEM image and video processing. The software automates routine enhancement tasks, enabling faster conversion of raw acquisitions into publication-ready outputs.

SimpliPyTEM provides an open-source Python toolkit for analyzing electron microscopy images and in-situ videos. The package streamlines common processing tasks and helps researchers build reproducible workflows.

This work reviews scanning transmission X-ray microscopy (STXM) as a technique for high-resolution chemical and structural imaging. The method enables detailed characterization of materials through X-ray absorption contrast.

The study applies synchrotron X-ray nano-tomography and multimodal analysis to investigate interactions between metals and molten salts. Advanced imaging provides three-dimensional insight into corrosion processes and material evolution.

TomoFlows introduces preprocessing workflows for cryo-electron tomography datasets. The framework streamlines data preparation steps and promotes consistent handling of large tomography experiments.

TomoTwin applies machine learning and structural data mining to localize macromolecules within cryo-electron tomograms. The approach enables generalized particle identification without extensive manual annotation.

The authors combine active learning and meta-learning strategies to accelerate autonomous electron microscopy. The methodology helps instruments identify informative experiments and adapt quickly to new samples.

This paper discusses key factors affecting measurement accuracy, reproducibility, and calibration in 4D-STEM. The recommendations support reliable quantitative analysis across diverse experimental settings.

AtomAI introduces a deep learning framework for electron and scanning probe microscopy data analysis. The package enables automated feature discovery, segmentation, prediction, and scientific interpretation using modern AI techniques.

AutoDisk introduces an automated workflow for diffraction analysis and strain mapping in 4D-STEM experiments. The software reduces manual intervention while improving consistency and throughput for structural measurements.

This work demonstrates automated TEM lamella preparation through remote CAD-to-SEM image alignment. The approach enhances efficiency, accuracy, and scalability in semiconductor failure analysis workflows.

The authors explore correlative multimodal microscopy by integrating atomic force microscopy within an SEM environment. The combined technique provides complementary topographical and microstructural information for materials characterization.

This study applies deep learning and object-tracking methods to monitor nanoparticle evolution in environmental TEM experiments. The approach enables automated analysis of large image datasets generated during dynamic observations.