A reusable neural network pipeline for unidirectional fiber segmentation

Fioravante de Siqueira, Alexandre; Ushizima, Daniela M.; van der Walt, Stéfan J.

doi:10.1038/s41597-022-01119-6

Title: A reusable neural network pipeline for unidirectional fiber segmentation

Journal Article · 01 February 2022 · Scientific Data

DOI: https://doi.org/10.1038/s41597-022-01119-6 · OSTI ID:1843311

;

; van der Walt, Stéfan J.

Abstract Fiber-reinforced ceramic-matrix composites are advanced, temperature resistant materials with applications in aerospace engineering. Their analysis involves the detection and separation of fibers, embedded in a fiber bed, from an imaged sample. Currently, this is mostly done using semi-supervised techniques. Here, we present an open, automated computational pipeline to detect fibers from a tomographically reconstructed X-ray volume. We apply our pipeline to a non-trivial dataset by Larson et al . To separate the fibers in these samples, we tested four different architectures of convolutional neural networks. When comparing our neural network approach to a semi-supervised one, we obtained Dice and Matthews coefficients reaching up to 98%, showing that these automated approaches can match human-supervised methods, in some cases separating fibers that human-curated algorithms could not find. The software written for this project is open source, released under a permissive license, and can be freely adapted and re-used in other domains.

View Journal Article

Cite

Export

Save

Research Organization:: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Organization:: Alfred P. Sloan Foundation; Gordon and Betty Moore Foundation; USDOE; USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); USDOE Office of Science (SC), Basic Energy Sciences (BES)

Grant/Contract Number:: AC02-05CH11231

OSTI ID:: 1843311

Journal Information:: Scientific Data, Journal Name: Scientific Data Journal Issue: 1 Vol. 9; ISSN 2052-4463

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United Kingdom

Language:: English

References (39)

Segmentation of nearly isotropic overlapped tracks in photomicrographs using successive erosions as watershed markers Siqueira, Alexandre Fioravante; Nakasuga, Wagner Massayuki; Guedes, Sandro Microscopy Research and Technique, Vol. 82, Issue 10 https://doi.org/10.1002/jemt.23336	journal	July 2019
Evaluating Fiber Detection Models Using Neural Networks Miramontes, Silvia; Ushizima, Daniela M.; Parkinson, Dilworth Y. Advances in Visual Computing: 14th International Symposium on Visual Computing, ISVC 2019, Lake Tahoe, NV, USA, October 7–9, 2019, Proceedings, Part II, p. 541-552 https://doi.org/10.1007/978-3-030-33723-0_44	book	October 2019
U-Net: Convolutional Networks for Biomedical Image Segmentation Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III https://doi.org/10.1007/978-3-319-24574-4_28	book	November 2015
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation Çiçek, Özgün; Abdulkadir, Ahmed; Lienkamp, Soeren S. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016 https://doi.org/10.1007/978-3-319-46723-8_49	conference	January 2016
The Materials Data Facility: Data Services to Advance Materials Science Research Blaiszik, B.; Chard, K.; Pruyne, J. JOM, Vol. 68, Issue 8 https://doi.org/10.1007/s11837-016-2001-3	journal	July 2016
IDEAL: Images Across Domains, Experiments, Algorithms and Learning Ushizima, Daniela M.; Bale, Hrishikesh A.; Bethel, E. Wes JOM, Vol. 68, Issue 11 https://doi.org/10.1007/s11837-016-2098-4	journal	September 2016
Comparison of the predicted and observed secondary structure of T4 phage lysozyme Matthews, B. W. Biochimica et Biophysica Acta (BBA) - Protein Structure, Vol. 405, Issue 2 https://doi.org/10.1016/0005-2795(75)90109-9	journal	October 1975
Topographic distance and watershed lines Meyer, Fernand Signal Processing, Vol. 38, Issue 1 https://doi.org/10.1016/0165-1684(94)90060-4	journal	July 1994
Nonlinear total variation based noise removal algorithms Rudin, Leonid I.; Osher, Stanley; Fatemi, Emad Physica D: Nonlinear Phenomena, Vol. 60, Issue 1-4 https://doi.org/10.1016/0167-2789(92)90242-F	journal	November 1992
Size invariant circle detection Atherton, T. J.; Kerbyson, D. J. Image and Vision Computing, Vol. 17, Issue 11 https://doi.org/10.1016/S0262-8856(98)00160-7	journal	September 1999
In-situ 3D visualization of composite microstructure during polymer-to-ceramic conversion Larson, Natalie M.; Zok, Frank W. Acta Materialia, Vol. 144 https://doi.org/10.1016/j.actamat.2017.10.054	journal	February 2018
Generation of micro-scale finite element models from synchrotron X-ray CT images for multidirectional carbon fibre reinforced composites Sencu, R. M.; Yang, Z.; Wang, Y. C. Composites Part A: Applied Science and Manufacturing, Vol. 91 https://doi.org/10.1016/j.compositesa.2016.09.010	journal	December 2016
Individual fibre segmentation from 3D X-ray computed tomography for characterising the fibre orientation in unidirectional composite materials Emerson, Monica J.; Jespersen, Kristine M.; Dahl, Anders B. Composites Part A: Applied Science and Manufacturing, Vol. 97 https://doi.org/10.1016/j.compositesa.2016.12.028	journal	June 2017
X-ray computed tomography of microstructure evolution during matrix impregnation and curing in unidirectional fiber beds Larson, Natalie M.; Cuellar, Charlene; Zok, Frank W. Composites Part A: Applied Science and Manufacturing, Vol. 117 https://doi.org/10.1016/j.compositesa.2018.11.021	journal	February 2019
A fiber-segmentation algorithm for composites imaged using X-ray microtomography: Development and validation Creveling, Peter J.; Whitacre, William W.; Czabaj, Michael W. Composites Part A: Applied Science and Manufacturing, Vol. 126 https://doi.org/10.1016/j.compositesa.2019.105606	journal	November 2019
Numerical reconstruction of graphite/epoxy composite microstructure based on sub-micron resolution X-ray computed tomography Czabaj, Michael W.; Riccio, Mark L.; Whitacre, William W. Composites Science and Technology, Vol. 105 https://doi.org/10.1016/j.compscitech.2014.10.017	journal	December 2014
Statistical validation of individual fibre segmentation from tomograms and microscopy Emerson, Monica Jane; Dahl, Vedrana Andersen; Conradsen, Knut Composites Science and Technology, Vol. 160 https://doi.org/10.1016/j.compscitech.2018.03.027	journal	May 2018
Recent progress in the development of SiC composites for nuclear fusion applications Koyanagi, T.; Katoh, Y.; Nozawa, T. Journal of Nuclear Materials, Vol. 511 https://doi.org/10.1016/j.jnucmat.2018.06.017	journal	December 2018
Practical, Unified, Motion and Missing Data Treatment in Degraded Video Kokaram, Anil Journal of Mathematical Imaging and Vision, Vol. 20, Issue 1/2 https://doi.org/10.1023/B:JMIV.0000011325.36760.1e	journal	January 2004
Advanced structural ceramics in aerospace propulsion Padture, Nitin P. Nature Materials, Vol. 15, Issue 8 https://doi.org/10.1038/nmat4687	journal	July 2016
Automated defect analysis in electron microscopic images Li, Wei; Field, Kevin G.; Morgan, Dane npj Computational Materials, Vol. 4, Issue 1 https://doi.org/10.1038/s41524-018-0093-8	journal	July 2018
Deep-learning-based quality filtering of mechanically exfoliated 2D crystals Saito, Yu; Shin, Kento; Terayama, Kei npj Computational Materials, Vol. 5, Issue 1 https://doi.org/10.1038/s41524-019-0262-4	journal	December 2019
Understanding important features of deep learning models for segmentation of high-resolution transmission electron microscopy images Horwath, James P.; Zakharov, Dmitri N.; Mégret, Rémi npj Computational Materials, Vol. 6, Issue 1 https://doi.org/10.1038/s41524-020-00363-x	journal	July 2020
Data augmentation in microscopic images for material data mining Ma, Boyuan; Wei, Xiaoyan; Liu, Chuni npj Computational Materials, Vol. 6, Issue 1 https://doi.org/10.1038/s41524-020-00392-6	journal	August 2020
3D convolutional neural networks-based segmentation to acquire quantitative criteria of the nucleus during mouse embryogenesis Tokuoka, Yuta; Yamada, Takahiro G.; Mashiko, Daisuke npj Systems Biology and Applications, Vol. 6, Issue 1 https://doi.org/10.1038/s41540-020-00152-8	journal	October 2020
Semantic segmentation of microscopic neuroanatomical data by combining topological priors with encoder–decoder deep networks Banerjee, Samik; Magee, Lucas; Wang, Dingkang Nature Machine Intelligence, Vol. 2, Issue 10 https://doi.org/10.1038/s42256-020-0227-9	journal	September 2020
Gradient-based learning applied to document recognition Lecun, Y.; Bottou, L.; Bengio, Y. Proceedings of the IEEE, Vol. 86, Issue 11 https://doi.org/10.1109/5.726791	journal	January 1998
The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation Jegou, Simon; Drozdzal, Michal; Vazquez, David 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) https://doi.org/10.1109/CVPRW.2017.156	conference	July 2017
Matplotlib: A 2D Graphics Environment Hunter, John D. Computing in Science & Engineering, Vol. 9, Issue 3 https://doi.org/10.1109/MCSE.2007.55	journal	January 2007
Real-time digital image enhancement Woods, R. E.; Gonzalez, R. C. Proceedings of the IEEE, Vol. 69, Issue 5 https://doi.org/10.1109/PROC.1981.12031	journal	January 1981
Large-Scale Fiber Tracking Through Sparsely Sampled Image Sequences of Composite Materials Zhou, Youjie; Yu, Hongkai; Simmons, Jeff IEEE Transactions on Image Processing, Vol. 25, Issue 10 https://doi.org/10.1109/TIP.2016.2598640	journal	October 2016
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Ren, Shaoqing; He, Kaiming; Girshick, Ross IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, Issue 6 https://doi.org/10.1109/TPAMI.2016.2577031	journal	June 2017
A Threshold Selection Method from Gray-Level Histograms Otsu, Nobuyuki IEEE Transactions on Systems, Man, and Cybernetics, Vol. 9, Issue 1 https://doi.org/10.1109/TSMC.1979.4310076	journal	January 1979
Anomaly detection of microstructural defects in continuous fiber reinforced composites Bricker, Stephen; Simmons, J. P.; Przybyla, Craig IS&T/SPIE Electronic Imaging, SPIE Proceedings https://doi.org/10.1117/12.2079679	conference	March 2015
Fully automated segmentation of the temporal bone from micro-CT using deep learning Nikan, Soodeh; Agrawal, Sumit K.; Ladak, Hanif M. Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging https://doi.org/10.1117/12.2549609	conference	March 2020
Ex-situ XCT dataset for "X-ray computed tomography of microstructure evolution during matrix impregnation and curing in unidirectional fiber beds" Larson, Natalie M.; Zok, Frank W. Materials Data Facility https://doi.org/10.18126/M2QM0Z	dataset	January 2019
Measures of the Amount of Ecologic Association Between Species Dice, Lee R. Ecology, Vol. 26, Issue 3 https://doi.org/10.2307/1932409	journal	July 1945
A Comparative Study of Hough Transform Methods for Circle Finding Yuen, H. K.; Princen, J.; Dlingworth, J. Procedings of the Alvey Vision Conference 1989 https://doi.org/10.5244/C.3.29	conference	January 1989
Data from: A reusable pipeline for large-scale fiber segmentation on unidirectional fiber beds using fully convolutional neural networks Fioravante De Siqueira, Alexandre; Van Der Walt, Stéfan; Mayumi Ushizima, Daniela Dryad https://doi.org/10.6078/D1069R	dataset	January 2021

Similar Records

A machine learning pipeline for membrane segmentation of cryo-electron tomograms

Journal Article · 2022 · Journal of Computational Science · OSTI ID:1974768

Zhou, Li; Yang, Chao; Gao, Weiguo; +3 more

High-Throughput Field Plant Phenotyping: A Self-Supervised Sequential CNN Method to Segment Overlapping Plants

Journal Article · 2023 · Plant Phenomics · OSTI ID:2421574

Guo, Xingche; Qiu, Yumou; Nettleton, Dan; +1 more

Semi-supervised graph neural networks for pileup noise removal

Journal Article · 2023 · European Physical Journal. C, Particles and Fields (Online) · OSTI ID:1922868

Li, Tianchun; Liu, Shikun; Feng, Yongbin; +4 more

Related Subjects

79 ASTRONOMY AND ASTROPHYSICS
computational methods
scientific data
software

Title: A reusable neural network pipeline for unidirectional fiber segmentation

Citation Formats

References (39)

Similar Records

Related Subjects