A novel iterative algorithm to improve segmentations with deep convolutional neural networks trained with synthetic X-ray computed tomography data (i.S.Sy.Da.T.A)
- 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, SiCWe 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.…
Autor*innen: | Athanasios Tsamos, Sergei Evsevleev, R. Fioresi, F. Faglioni, Giovanni BrunoORCiD |
---|---|
Dokumenttyp: | Zeitschriftenartikel |
Veröffentlichungsform: | Verlagsliteratur |
Sprache: | Englisch |
Titel des übergeordneten Werkes (Englisch): | Computational Materials Science |
Jahr der Erstveröffentlichung: | 2023 |
Organisationseinheit der BAM: | 8 Zerstörungsfreie Prüfung |
8 Zerstörungsfreie Prüfung / 8.5 Röntgenbildgebung | |
Verlag: | Elsevier B.V. |
Jahrgang/Band: | 223 |
Aufsatznummer: | 112112 |
Erste Seite: | 1 |
Letzte Seite: | 8 |
DDC-Klassifikation: | Naturwissenschaften und Mathematik / Chemie / Analytische Chemie |
Freie Schlagwörter: | 3D imaging; Automatic segmentation; Deep convolutional neural network (DCNN); Dice score; Metal matrix composites (MMC); Modified U-net architectures; Multi-phase materials |
Themenfelder/Aktivitätsfelder der BAM: | Chemie und Prozesstechnik |
DOI: | 10.1016/j.commatsci.2023.112112 |
ISSN: | 0927-0256 |
Verfügbarkeit des Dokuments: | Datei im Netzwerk der BAM verfügbar ("Closed Access") |
Datum der Freischaltung: | 17.05.2023 |
Referierte Publikation: | Ja |
Datum der Eintragung als referierte Publikation: | 23.10.2023 |