| People | Locations | Statistics |
|---|---|---|
| Naji, M. |
| |
| Motta, Antonella |
| |
| Aletan, Dirar |
| |
| Mohamed, Tarek |
| |
| Ertürk, Emre |
| |
| Taccardi, Nicola |
| |
| Kononenko, Denys |
| |
| Petrov, R. H. | Madrid |
|
| Alshaaer, Mazen | Brussels |
|
| Bih, L. |
| |
| Casati, R. |
| |
| Muller, Hermance |
| |
| Kočí, Jan | Prague |
|
| Šuljagić, Marija |
| |
| Kalteremidou, Kalliopi-Artemi | Brussels |
|
| Azam, Siraj |
| |
| Ospanova, Alyiya |
| |
| Blanpain, Bart |
| |
| Ali, M. A. |
| |
| Popa, V. |
| |
| Rančić, M. |
| |
| Ollier, Nadège |
| |
| Azevedo, Nuno Monteiro |
| |
| Landes, Michael |
| |
| Rignanese, Gian-Marco |
|
Lomholdt, William Bang
Technical University of Denmark
in Cooperation with on an Cooperation-Score of 37%
Topics
Publications (6/6 displayed)
- 2024Interpretability of high-resolution transmission electron microscopy imagescitations
- 2024Interpretability of high-resolution transmission electron microscopy imagescitations
- 2024Beam induced heating in electron microscopy modeled with machine learning interatomic potentialscitations
- 2023Quantifying noise limitations of neural network segmentations in high-resolution transmission electron microscopycitations
- 2023Quantifying noise limitations of neural network segmentations in high-resolution transmission electron microscopycitations
- 2021Electron beam effects in high-resolution transmission electron microscopy investigations of catalytic nanoparticles
Places of action
| Organizations | Location | People |
|---|
article
Quantifying noise limitations of neural network segmentations in high-resolution transmission electron microscopy
Abstract
Motivated by the need for low electron dose transmission electron microscopy imaging, we report the optimal frame dose (<i>i.e</i>. e<sup>−</sup>/Å<sup>2</sup>) range for object detection and segmentation tasks with neural networks. The MSD-net architecture shows promising abilities over the industry standard U-net architecture in generalising to frame doses below the range included in the training set, for both simulated and experimental images. It also presents a heightened ability to learn from lower dose images. The MSD-net displays mild visibility of a Au nanoparticle at 20–30 e<sup>−</sup>/Å<sup>2</sup>, and converges at 200 e<sup>−</sup>/Å<sup>2</sup> where a full segmentation of the nanoparticle is achieved. Between 30 and 200 e<sup>−</sup>/Å<sup>2</sup> object detection applications are still possible. This work also highlights the importance of modelling the modulation transfer function when training with simulated images for applications on images acquired with scintillator based detectors such as the Gatan Oneview camera. A parametric form of the modulation transfer function is applied with varying ranges of parameters, and the effects on low electron dose segmentation is presented.