Automated Grain Boundary Detection for Bright-Field Transmission Electron Microscopy Images via U-Net.

Autor: Patrick MJ; Department of Applied Physics and Applied Mathematics, Columbia University, 200 S.W. Mudd Building, 500 W. 120 Street, New York, NY 10027, USA., Eckstein JK; Department of Physics, University of Illinois, 1110 W. Green Street, Urbana, IL 61801, USA., Lopez JR; Department of Mechanical Engineering, Columbia University, 210 S.W. Mudd Building, 500 W. 120 Street, New York, NY 10027, USA., Toderas S; Department of Applied Physics and Applied Mathematics, Columbia University, 200 S.W. Mudd Building, 500 W. 120 Street, New York, NY 10027, USA., Asher SA; Department of Applied Physics and Applied Mathematics, Columbia University, 200 S.W. Mudd Building, 500 W. 120 Street, New York, NY 10027, USA., Whang SI; Department of Physics, Barnard College, 504A Altschul Hall, 3009 Broadway, New York, NY 10027, USA., Levine S; Department of Mathematics and Computer Science, Duquesne University, 440 College Hall, 1100 Locust Street, Pittsburgh, PA 15282, USA., Rickman JM; Department of Materials Science and Engineering, Lehigh University, Whitaker Lab 244, 5 E. Packer Avenue, Bethlehem, PA 18015, USA., Barmak K; Department of Applied Physics and Applied Mathematics, Columbia University, 200 S.W. Mudd Building, 500 W. 120 Street, New York, NY 10027, USA.
Jazyk: angličtina
Zdroj: Microscopy and microanalysis : the official journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada [Microsc Microanal] 2023 Dec 21; Vol. 29 (6), pp. 1968-1979.
DOI: 10.1093/micmic/ozad115
Abstrakt: 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.
Competing Interests: Conflict of Interest The authors declare that they have no competing interest.
(© The Author(s) 2023. Published by Oxford University Press on behalf of the Microscopy Society of America.)
Databáze: MEDLINE