An official website of the United States government
Abstract Automated, reliable, and objective microstructure inference from micrographs is essential for a comprehensive understanding of process-microstructure-property relations and tailored materials development. However, such inference, with the increasing complexity of microstructures, requires advanced segmentation methodologies. While deep learning offers new opportunities, an intuition about the required data quality/quantity and a methodological guideline for microstructure quantification is still missing. This, along with deep learning’s seemingly intransparent decision-making process, hampers its breakthrough in this field. We apply a multidisciplinary deep learning approach, devoting equal attention to specimen preparation and imaging, and train distinct U-Net architectures with 30–50 micrographs of different imaging modalities and electron backscatter diffraction-informed annotations. On the challenging task of lath-bainite segmentation in complex-phase steel, we achieve accuracies of 90% rivaling expert segmentations. Further, we discuss the impact of image context, pre-training with domain-extrinsic data, and data augmentation. Network visualization techniques demonstrate plausible model decisions based on grain boundary morphology.
more »
« less
High Throughput Quantitative Metallography for Complex Microstructures Using Deep Learning: A Case Study in Ultrahigh Carbon Steel
Abstract We apply a deep convolutional neural network segmentation model to enable novel automated microstructure segmentation applications for complex microstructures typically evaluated manually and subjectively. We explore two microstructure segmentation tasks in an openly available ultrahigh carbon steel microstructure dataset: segmenting cementite particles in the spheroidized matrix, and segmenting larger fields of view featuring grain boundary carbide, spheroidized particle matrix, particle-free grain boundary denuded zone, and Widmanstätten cementite. We also demonstrate how to combine these data-driven microstructure segmentation models to obtain empirical cementite particle size and denuded zone width distributions from more complex micrographs containing multiple microconstituents. The full annotated dataset is available on materialsdata.nist.gov.
more »
« less
- PAR ID:
- 10101198
- Date Published:
- Journal Name:
- Microscopy and Microanalysis
- Volume:
- 25
- Issue:
- 1
- ISSN:
- 1431-9276
- Page Range / eLocation ID:
- 21 to 29
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This dataset contain the results of 426 anisotropic grain growth simulations in 2D. Every microstructure was stored as an 800x800 label matrix, where the label in a given pixel indicates the grain orientation at that point from the accompanying list of initial orientations (represented as quaternions) assigned to each grain.more » « less
-
Nanostructured materials, whose characteristic microstructure size is under 100 nm, can be either single-phasenanocrystalline materials or multi-phase nanocomposite materials. Nanocrystalline materials can also be treated asnanocomposites with grain interior as matrix and grain boundary as secondary phase. The strengthening models ofnanostructured materials resemble those strengthening models of conventional composite structures, but havesubstantial deviations from conventional strengthening mechanisms due to their distinctive nanoscale structure andthe complex hierarchy of their nanoscale microstructure. This paper reviewed the current progress in developmentsof strengthening models for nanostructured materials with emphasis on single-phase nanocrystalline and multiphasenanocomposite materials, which would help guide the design of new nanostructured materials and othersimilar nanoscale composite structures. Furthermore, practical large scale industrial applications of high strengthnanostructured materials require these materials to possess decent formability, ductility or other functionalproperties to satisfy both structural and multifunctional applications. Therefore, the latest developments of novelnanostructured materials are discussed to highlight their potential of overcoming the strength ductility trade-off andstrength-conductivity trade-off by various approaches. Their complex and distinctive nanoscale microstructuresuggests the potential challenges and opportunities in developing new strengthening models for designing futureadvanced nanostructured materials with unprecedented properties.more » « less
-
Precision in segmenting cardiac MR images is critical for accurately diagnosing cardiovascular diseases. Several deep learning models have been shown useful in segmenting the structure of the heart, such as atrium, ventricle and myocardium, in cardiac MR images. Given the diverse image quality in cardiac MRI scans from various clinical settings, it is currently uncertain how different levels of noise affect the precision of deep learning image segmentation. This uncertainty could potentially lead to bias in subsequent diagnoses. The goal of this study is to examine the effects of noise in cardiac MRI segmentation using deep learning. We employed the Automated Cardiac Diagnosis Challenge MRI dataset and augmented it with varying degrees of Rician noise during model training to test the model’s capability in segmenting heart structures. Three models, including TransUnet, SwinUnet, and Unet, were compared by calculating the SNR-Dice relations to evaluate the models’ noise resilience. Results show that the TransUnet model, which combines CNN and Transformer architectures, demonstrated superior noise resilience. Noise augmentation during model training improved the models’ noise resilience for segmentation. The findings under-score the critical role of deep learning models in adequately handling diverse noise conditions for the segmentation of heart structures in cardiac images.more » « less
-
Accurate medical imaging segmentation is critical for precise and effective medi- cal interventions. However, despite the success of convolutional neural networks (CNNs) in medical image segmentation, they still face challenges in handling fine-scale features and variations in image scales. These challenges are particularly evident in complex and challenging segmentation tasks, such as the BraTS multi- label brain tumor segmentation challenge. In this task, accurately segmenting the various tumor sub-components, which vary significantly in size and shape, remains a significant challenge, with even state-of-the-art methods producing substantial errors. Therefore, we propose two architectures, FMG-Net and W-Net, that incor- porate the principles of geometric multigrid methods for solving linear systems of equations into CNNs to address these challenges. Our experiments on the BraTS 2020 dataset demonstrate that both FMG-Net and W-Net outperform the widely used U-Net architecture regarding tumor subcomponent segmentation accuracy and training efficiency. These findings highlight the potential of incorporating the principles of multigrid methods into CNNs to improve the accuracy and efficiency of medical imaging segmentation.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1017/S1431927618015635
