|Title:||Training deep neural networks to reconstruct nanoporous structures from FIB tomography images using synthetic training data||Language:||English||Authors:||Sardhara, Trushal
Aydin, Roland C.
Cyron, Christian J.
|Keywords:||Electron microscopy;Synthetic training data;3D reconstruction;Semantic segmentation;SEM simulation;3D CNN;2D CNN with adjacent slices;Machine learning||Issue Date:||2-Feb-2022||Is supplement to:||10.3389/fmats.2022.837006||Abstract (english):||
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 sample is degraded by layer-wise milling. After each layer, the current surface is imaged by a scanning electron microscope (SEM), providing a consecutive series of cross-sections of the three-dimensional material sample. Especially for nanoporous materials, the reconstruction of the 3D microstructure of the material, from the information collected during FIB tomography, is impaired by the so-called 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 training data in the form of FIB-SEM images generated by Monte Carlo simulations. 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 processing a group of adjacent slices as input data as well as 3D CNN perform best and can enhance the segmentation performance significantly.
|URI:||http://hdl.handle.net/11420/11060.2||DOI:||10.15480/336.3932.2||Institute:||Kontinuums- und Werkstoffmechanik M-15
Betriebseinheit Elektronenmikroskopie M-26
Werkstoffphysik und -technologie M-22
|Document Type:||Dataset||Project:||SFB 986: Teilprojekt B09 - Mikrostrukturbasierte Klassifizierung und mechanische Analyse nanoporöser Metalle durch maschinelles Lernen||Funded by:||Deutsche Forschungsgemeinschaft (DFG)||License:||CC BY 4.0 (Attribution)|
|Appears in Collections:||Research Data TUHH|
Show full item record
Files in This Item:
checked on May 27, 2022
checked on May 27, 2022
Note about this record
Cite this record
|2||doi:10.15480/336.3932.2||2022-02-08 14:11:21.026||# 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|
This item is licensed under a Creative Commons License