Options
Training deep neural networks to reconstruct nanoporous structures from FIB tomography images using synthetic training data
Citation Link: https://doi.org/10.15480/336.3932.2
Type
Dataset
Date Issued
2022-02-02
Creator
Language
English
Abstract
This dataset contains simulated FIB tomography data of nanoporous/hierarchical nanoporous gold, synthetic FIB-SEM images of hierarchical nanoporous gold and segmentation results of real hierarchical nanoporous gold dataset.
Abstract of the paper:
Focused ion beam (FIB) tomography is a destructive technique used to collect three-dimensional (3D) structural information at a resolution of a few nanometers. For FIB tomography, a material is eroded in a layer-wise manner. After the erosion of each layer (whose thickness ranges on the nanometer scale), the current material surface is imaged by a scanning electron microscope. Especially for nanoporous materials, the reconstruction of the 3D microstructure of the material, from the information collected during FIB tomography, is impaired by the shine-through effect. This effect prevents a unique mapping between voxel intensity values and material phase (e.g., solid or void). It often substantially reduces the accuracy of conventional methods for image segmentation. Here we demonstrate how machine learning can be used to tackle this problem. A bottleneck in doing so is the availability of sufficient training data. To overcome this problem, we present a novel approach to generate synthetic FIB-SEM images using Monte Carlo simulations, which can be used as training data for machine learning. Based on this approach, we compare the performance of different machine learning architectures for segmenting FIB tomography data of nanoporous materials. We demonstrate that two-dimensional (2D) convolutional neural network (CNN) architectures with a group of adjacent slices as input data as well as 3D CNN perform best and can improve the segmentation performance by more than 100%.
Abstract of the paper:
Focused ion beam (FIB) tomography is a destructive technique used to collect three-dimensional (3D) structural information at a resolution of a few nanometers. For FIB tomography, a material is eroded in a layer-wise manner. After the erosion of each layer (whose thickness ranges on the nanometer scale), the current material surface is imaged by a scanning electron microscope. Especially for nanoporous materials, the reconstruction of the 3D microstructure of the material, from the information collected during FIB tomography, is impaired by the shine-through effect. This effect prevents a unique mapping between voxel intensity values and material phase (e.g., solid or void). It often substantially reduces the accuracy of conventional methods for image segmentation. Here we demonstrate how machine learning can be used to tackle this problem. A bottleneck in doing so is the availability of sufficient training data. To overcome this problem, we present a novel approach to generate synthetic FIB-SEM images using Monte Carlo simulations, which can be used as training data for machine learning. Based on this approach, we compare the performance of different machine learning architectures for segmenting FIB tomography data of nanoporous materials. We demonstrate that two-dimensional (2D) convolutional neural network (CNN) architectures with a group of adjacent slices as input data as well as 3D CNN perform best and can improve the segmentation performance by more than 100%.
Subjects
Electron microscopy
Synthetic training data
3D reconstruction
Semantic segmentation
SEM simulation
3D CNN
2D CNN with adjacent slices
Machine learning
DDC Class
620: Ingenieurwissenschaften
Funding Organisations
Deutsche Forschungsgemeinschaft (DFG)
No Thumbnail Available
Name
Paper Data.zip
Size
484.6 MB
Format
ZIP
Loading...
Name
Supplementary Material.pdf
Size
2.76 MB
Format
Adobe PDF
Loading...
Name
readme.pdf
Size
87.15 KB
Format
Adobe PDF
Version History
You are currently viewing version 2 of the item.
Now showing1 - 2 of 2
Version | Date | Summary |
---|---|---|
2 * | 2022-02-08 14:11:21 | # Changelog
All notable changes to this dataset are as follows.
- Added simulated dataset along with their virtual initial structures
- Updated supplementary material content
- Added new data table and segmentation results for synthetic test data |
1 | 2021-12-15 11:44:18 |
* Selected version