Automated Grain Boundary Detection for Bright-Field Transmission Electron Microscopy Images via U-Net
Microscopy and Microanalysis · 21.12.2023 · 29 (6) · 1968-1979
DOI: 10.1093/micmic/ozad115 ↗Kurz gefasst
Fachartikel in der Zeitschrift Microscopy and Microanalysis, online erschienen am 15.11.2023. Verfasst von Matthew J Patrick und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Physics and Applied Mathematics, Columbia University, 200 S.W. Mudd Building, 500 W. 120 Street, New York, NY 10027, USA. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Quantification of microstructures is crucial for understanding processing–structure and structure–property relationships in polycrystalline materials. Delineating grain boundaries in bright-field transmission electron micrographs, however, is challenging due to complex diffraction contrast in images. Conventional edge detection algorithms are inadequate; instead, manual tracing is usually required. This study demonstrates the first successful machine learning approach for grain boundary detection in bright-field transmission electron micrographs. The proposed methodology uses a U-Net convolutional neural network trained on carefully constructed data from bright-field images and hand tracings available from prior studies, combined with targeted postprocessing algorithms to preserve fine features of interest. The image processing pipeline accurately estimates grain boundary positions, avoiding segmentation in regions with intragrain contrast and identifying low-contrast boundaries. Our approach is validated by directly comparing microstructural markers (i.e., grain centroids) identified in U-Net predictions with those identified in hand tracings; furthermore, the grain size distributions obtained from the two techniques show notable overlap when compared using t-test, Kolmogorov–Smirnov test, and Cramér–von Mises test. The technique is then successfully applied to interpret new microstructures having different image characteristics from the training data, with preliminary results from platinum and palladium microstructures presented, highlighting the versatility of our approach for grain boundary identification in bright-field micrographs.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Applied Physics and Applied Mathematics, Columbia University, 200 S.W. Mudd Building, 500 W. 120 Street, New York, NY 10027, USA.
- Department of Physics, University of Illinois, 1110 W. Green Street, Urbana, IL 61801, USA.
- Department of Mechanical Engineering, Columbia University, 210 S.W. Mudd Building, 500 W. 120 Street, New York, NY 10027, USA.
- Department of Physics, Barnard College, 504A Altschul Hall, 3009 Broadway, New York, NY 10027, USA.
- Department of Mathematics and Computer Science, Duquesne University, 440 College Hall, 1100 Locust Street, Pittsburgh, PA 15282, USA.
- Department of Materials Science and Engineering, Lehigh University, Whitaker Lab 244, 5 E. Packer Avenue, Bethlehem, PA 18015, USA.
ORCID-Profile: Matthew J Patrick, James K Eckstein, Javier R Lopez, Silvia Toderas, Sarah A Asher, Sylvia I Whang, Stacey Levine, Jeffrey M Rickman, Katayun Barmak
Zitieren
APA
Patrick, M. J., Eckstein, J. K., Lopez, J. R., Toderas, S., Asher, S. A., Whang, S. I., Levine, S., Rickman, J. M., & Barmak, K. (2023). Automated Grain Boundary Detection for Bright-Field Transmission Electron Microscopy Images via U-Net. Microscopy and Microanalysis, 29(6), 1968-1979. https://doi.org/10.1093/micmic/ozad115
Vancouver
Patrick MJ, Eckstein JK, Lopez JR, Toderas S, Asher SA, Whang SI, et al. Automated Grain Boundary Detection for Bright-Field Transmission Electron Microscopy Images via U-Net. Microscopy and Microanalysis. 2023;29(6):1968-1979. doi:10.1093/micmic/ozad115
BibTeX
@article{Patrick2023,
author = {Patrick, Matthew J and Eckstein, James K and Lopez, Javier R and Toderas, Silvia and Asher, Sarah A and Whang, Sylvia I and Levine, Stacey and Rickman, Jeffrey M and Barmak, Katayun},
title = {Automated Grain Boundary Detection for Bright-Field Transmission Electron Microscopy Images via U-Net},
journal = {Microscopy and Microanalysis},
year = {2023},
volume = {29},
number = {6},
pages = {1968--1979},
doi = {10.1093/micmic/ozad115}
}
EUVIMED