Datei im Netzwerk der BAM verfügbar ("Closed Access")
Filtern
Dokumenttyp
- Vortrag (3)
- Zeitschriftenartikel (1)
Sprache
- Englisch (4)
Schlagworte
- Artificial Intelligence (2)
- Automatic Segmentation (2)
- Synthetic Training Data (2)
- XCT (2)
- 3D imaging (1)
- AI (1)
- Automatic segmentation (1)
- CT (1)
- Computed Tomography (1)
- DCNNs (1)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (3)
We propose a novel iterative segmentation algorithm (i.S.Sy.Da.T.A: Iterative Segmentation Synthetic Data Training Algorithm) employing Deep Convolutional Neural Networks and synthetic training data for X-ray tomographic reconstructions of complex microstructures. In our method, we reinforce the synthetic training data with experimental XCT datasets that were automatically segmented in the previous iteration. This strategy produces better segmentations in successive iterations. We test our algorithm with experimental XCT re constructions of a 6-phase Al-Si Matrix Composite reinforced with ceramic fibers and particles. We perform the analysis in 3D with a special network architecture that demonstrates good generalization with synthetic training data. We show that our iterative algorithm returns better segmentations compared to the standard single training approach. More specifically, phases possessing similar attenuation coefficients can be better segmented: for Al2O3 fibers, SiC particles, and Intermetallics, we see an increase of the Dice score with respect to the classic approach: from 0.49 to 0.54, from 0.66 to 0.72, and from 0.55 to 0.66 respectively. Furthermore, the overall Dice score increases from 0.77 to 0.79. The methods presented in this work are also applicable to other materials and imaging techniques.
Irrespective of the experimental care used to acquire Computed Tomography Data, certain artifacts might still exist such as: Noise, Blurring, Ring Artifacts etc. To tackle this problem, a complete multi-level framework employing AI (Deep Artificial Neural Nets), targeting specific artifacts individually, is presented. The goal is to render the data suitable for subsequent unproblematic segmentation without any loss of information, compared to manual conditioning with traditional filters.
The strategy can therefore be used to acquire faster CT data (e.g. in-situ investigations) and ensure legacy with existing data obtained, perhaps, on older instruments.
We employ in-house generated synthetic Al-Si matrix composite XCT data for training deep convolutional neural networks for XCT data conditioning and automatic segmentation. We propose an in-house multilevel deep conditioning framework capable of rectifying noise and blur in corrupted XCT data sequentially. Furthermore, for automatic segmentation, we utilize a special in-house network coupled with a novel iterative segmentation algorithm capable of generalized learning from synthetic data. We report a consistent SSIM efficiency of 92%, 99%, and 95% for the combined denoising/deblurring, standalone denoising, and standalone deblurring, respectively. The overall segmentation precision was over 85% according to the Dice coefficient. We used experimental XCT data from various scans of Al-Si matrix composites reinforced with ceramic particles and fibers.