Training deep neural networks to reconstruct nanoporous structures from FIB tomography images using synthetic training data

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.

Subjects

electron microscopy

synthetic training data

3D reconstruction

semantic segmentation

SEM simulation

3D CNN

2D CNN with adjacent slices

machine learning

MLE@TUHH

DDC Class

600: Technik

Funding(s)

SFB 986: Teilprojekt B09 - Mikrostrukturbasierte Klassifizierung und mechanische Analyse nanoporöser Metalle durch maschinelles Lernen

Lizenz

http://rightsstatements.org/vocab/InC/1.0/

Name

fmats-09-837006-g007.tif

Size

2.16 MB

Format

TIFF

Name

fmats-09-837006-g003.tif

Size

1.25 MB

Format

TIFF

Name

fmats-09-837006-g008.tif

Size

141.52 KB

Format

TIFF

Name

DataSheet1.pdf

Size

2.76 MB

Format

Adobe PDF

Name

fmats-09-837006.pdf

Size

3.92 MB

Format

Adobe PDF

Name

fmats-09-837006-g002.tif

Size

819.71 KB

Format

TIFF

Name

fmats-09-837006-g001.tif

Size

1.15 MB

Format

TIFF

Name

fmats-09-837006-g006.tif

Size

1.1 MB

Format

TIFF

Name

fmats-09-837006-g005.tif

Size

184.39 KB

Format

TIFF

Name

fmats-09-837006-g004.tif

Size

1.6 MB

Format

TIFF

Options

Training deep neural networks to reconstruct nanoporous structures from FIB tomography images using synthetic training data