What question did this study set out to answer?

This research aims to develop an automated deep learning framework to accurately determine the 3D shapes of nanoparticles from 2D high-resolution images.

May 28, 2026npj Computational Materials0 citationsOpen Access

Unlocking 3D nanoparticle shapes from 2D high-resolution transmission electron microscopy images: a deep learning approach

RMRomain MoreauCentre National de la Recherche Scientifique HAHakim AmaraCentre National de la Recherche Scientifique MMMaxime MoreaudIFP Énergies nouvelles

Key Points

This research aims to develop an automated deep learning framework to accurately determine the 3D shapes of nanoparticles from 2D high-resolution images.
Developed a deep learning model trained on simulated HRTEM images of gold nanoparticles ranging from 4 to 8 nm.
Constructed atomistic models of nanoparticles on amorphous carbon, simulating random orientations and using multislice method for imaging.
Conducted systematic evaluations on factors like structure, resolution, and orientation affecting model performance.
The deep learning model shows significantly improved accuracy in predicting 3D nanoparticle shapes from 2D images.
Validation conducted on both simulated and real HRTEM datasets confirms the robustness of the model.
Different physical and numerical factors were found to critically influence the model's predictive capabilities.

Abstract

Abstract The analysis of high-resolution transmission electron microscopy (HRTEM) images with atomic resolution remains limited due to the lack of automated methods capable of processing a statistically significant number of nano-objects. In particular, the accurate characterization of nanoparticle (NP) morphology at the nanoscale remains a major challenge. To address this issue, we have developed a deep learning (DL) framework trained on a dataset of simulated HRTEM images of gold NPs nanoparticles adopting a face-centred cubic structure and ranging in size from 4 to 8 nm, labeled according to their 3D shape. The dataset is generated by constructing atomistic models of NPs deposited on amorphous carbon and subjected to random rotations in order to account for all possible orientations observed in experimental samples. HRTEM images are then simulated using the multislice method, to mimic experimental acquisition of an aberration-corrected transmission electron microscope. A systematic study is carried out to evaluate the impact of different key physical and numerical quantities (amorphous carbon structure, image resolution, focusing conditions, NP size and orientation) on the predictive performance of the DL model. Finally, a robust and accurate framework is developped and proposed for inferring 3D gold NP morphologies from 2D HRTEM images, validated on both simulated and experimental datasets.

问 AI

Bookmark

View Full Paper