DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Convolutional Neural Network for Segmenting Micro-X-ray Computed Tomography Images of Wood Cellular Structures

Abstract

To further enhance the performance of wood products, improved tools are needed to study in situ cellular scale phenomena like mechanical deformations and moisture swelling. Micro-X-ray computed tomography (μXCT) using brilliant synchrotron light sources now has the spatial and temporal resolution for real-time visualization of phenomena in three-dimensional cellular structures. However, the tradeoff for speed includes the loss of intensity contrast between different types of materials within the imaged structure, such as cell wall and air in wood. This loss of contrast prevents traditional histogram-based segmentation methods from being used effectively. A new convolutional neural network (CNN) approach was therefore developed to segment fast μXCT images of wood into cell wall and air volumes. The fast μXCT and segmentation were demonstrated in the study of moisture swelling in loblolly pine (Pinus taeda) earlywood and latewood cellular structures conditioned at 0%, 33%, 75%, and 95% relative humidity (RH). The CNN segmentation results had a mean intersection over union (IoU) metric accuracy of 96%. Initial analysis of the swelling in the latewood revealed cell walls swelled about 25% when conditioned from 0% to 95% RH. Additionally, the widths of ray cell lumina in the transverse plane of latewood could be observed tomore » increase at higher RH. The segmentation method presented here will facilitate future quantitative analyses in in situ μXCT studies of wood and other similar cellular materials.« less

Authors:
ORCiD logo; ; ORCiD logo; ; ; ; ; ; ORCiD logo
Publication Date:
Sponsoring Org.:
USDOE
OSTI Identifier:
1989717
Grant/Contract Number:  
AC02-06CH11357
Resource Type:
Published Article
Journal Name:
Applied Sciences
Additional Journal Information:
Journal Name: Applied Sciences Journal Volume: 13 Journal Issue: 14; Journal ID: ISSN 2076-3417
Publisher:
MDPI AG
Country of Publication:
Switzerland
Language:
English

Citation Formats

Arzola-Villegas, Xavier, Báez, Carlos, Lakes, Roderic, Stone, Donald S., O’Dell, Jane, Shevchenko, Pavel, Xiao, Xianghui, De Carlo, Francesco, and Jakes, Joseph E. Convolutional Neural Network for Segmenting Micro-X-ray Computed Tomography Images of Wood Cellular Structures. Switzerland: N. p., 2023. Web. doi:10.3390/app13148146.
Arzola-Villegas, Xavier, Báez, Carlos, Lakes, Roderic, Stone, Donald S., O’Dell, Jane, Shevchenko, Pavel, Xiao, Xianghui, De Carlo, Francesco, & Jakes, Joseph E. Convolutional Neural Network for Segmenting Micro-X-ray Computed Tomography Images of Wood Cellular Structures. Switzerland. https://doi.org/10.3390/app13148146
Arzola-Villegas, Xavier, Báez, Carlos, Lakes, Roderic, Stone, Donald S., O’Dell, Jane, Shevchenko, Pavel, Xiao, Xianghui, De Carlo, Francesco, and Jakes, Joseph E. Thu . "Convolutional Neural Network for Segmenting Micro-X-ray Computed Tomography Images of Wood Cellular Structures". Switzerland. https://doi.org/10.3390/app13148146.
@article{osti_1989717,
title = {Convolutional Neural Network for Segmenting Micro-X-ray Computed Tomography Images of Wood Cellular Structures},
author = {Arzola-Villegas, Xavier and Báez, Carlos and Lakes, Roderic and Stone, Donald S. and O’Dell, Jane and Shevchenko, Pavel and Xiao, Xianghui and De Carlo, Francesco and Jakes, Joseph E.},
abstractNote = {To further enhance the performance of wood products, improved tools are needed to study in situ cellular scale phenomena like mechanical deformations and moisture swelling. Micro-X-ray computed tomography (μXCT) using brilliant synchrotron light sources now has the spatial and temporal resolution for real-time visualization of phenomena in three-dimensional cellular structures. However, the tradeoff for speed includes the loss of intensity contrast between different types of materials within the imaged structure, such as cell wall and air in wood. This loss of contrast prevents traditional histogram-based segmentation methods from being used effectively. A new convolutional neural network (CNN) approach was therefore developed to segment fast μXCT images of wood into cell wall and air volumes. The fast μXCT and segmentation were demonstrated in the study of moisture swelling in loblolly pine (Pinus taeda) earlywood and latewood cellular structures conditioned at 0%, 33%, 75%, and 95% relative humidity (RH). The CNN segmentation results had a mean intersection over union (IoU) metric accuracy of 96%. Initial analysis of the swelling in the latewood revealed cell walls swelled about 25% when conditioned from 0% to 95% RH. Additionally, the widths of ray cell lumina in the transverse plane of latewood could be observed to increase at higher RH. The segmentation method presented here will facilitate future quantitative analyses in in situ μXCT studies of wood and other similar cellular materials.},
doi = {10.3390/app13148146},
journal = {Applied Sciences},
number = 14,
volume = 13,
place = {Switzerland},
year = {Thu Jul 13 00:00:00 EDT 2023},
month = {Thu Jul 13 00:00:00 EDT 2023}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.3390/app13148146

Save / Share:

Works referenced in this record:

Hysteretic swelling of wood at cellular scale probed by phase-contrast X-ray tomography
journal, January 2011

  • Derome, Dominique; Griffa, Michele; Koebel, Matthias
  • Journal of Structural Biology, Vol. 173, Issue 1
  • DOI: 10.1016/j.jsb.2010.08.011

An Analysis of Histogram-Based Thresholding Algorithms
journal, November 1993


Real-time streaming tomographic reconstruction with on-demand data capturing and 3D zooming to regions of interest
journal, April 2022

  • Nikitin, Viktor; Tekawade, Aniket; Duchkov, Anton
  • Journal of Synchrotron Radiation, Vol. 29, Issue 3
  • DOI: 10.1107/S1600577522003095

Automatic measurement of sister chromatid exchange frequency.
journal, July 1977

  • Zack, G. W.; Rogers, W. E.; Latt, S. A.
  • Journal of Histochemistry & Cytochemistry, Vol. 25, Issue 7
  • DOI: 10.1177/25.7.70454

Operations Useful for Similarity-Invariant Pattern Recognition
journal, April 1962


Minimum error thresholding
journal, January 1986


U-Net-Based Medical Image Segmentation
journal, April 2022

  • Yin, Xiao-Xia; Sun, Le; Fu, Yuhan
  • Journal of Healthcare Engineering, Vol. 2022
  • DOI: 10.1155/2022/4189781

A Review of Convolutional Neural Networks
conference, February 2020

  • Ajit, Arohan; Acharya, Koustav; Samanta, Abhishek
  • 2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE)
  • DOI: 10.1109/ic-ETITE47903.2020.049

tomoRecon: High-speed tomography reconstruction on workstations using multi-threading
conference, October 2012

  • Rivers, Mark L.
  • SPIE Optical Engineering + Applications, SPIE Proceedings
  • DOI: 10.1117/12.930022

3D micro-scale deformations of wood in bending: Synchrotron radiation μCT data analyzed with digital volume correlation
journal, December 2008


Recent progress in semantic image segmentation
journal, June 2018


Image thresholding by minimizing the measures of fuzziness
journal, January 1995


The Distribution of the Flora in the Alpine Zone.1
journal, February 1912


Structural Performance Characterization of Mass Plywood Panels
journal, October 2021


NIH Image to ImageJ: 25 years of image analysis
journal, June 2012

  • Schneider, Caroline A.; Rasband, Wayne S.; Eliceiri, Kevin W.
  • Nature Methods, Vol. 9, Issue 7
  • DOI: 10.1038/nmeth.2089

A new method for gray-level picture thresholding using the entropy of the histogram
journal, March 1985

  • Kapur, J. N.; Sahoo, P. K.; Wong, A. K. C.
  • Computer Vision, Graphics, and Image Processing, Vol. 29, Issue 3
  • DOI: 10.1016/0734-189X(85)90125-2

Picture Thresholding Using an Iterative Selection Method
journal, January 1978

  • Ridler, T. W.; Calvard, S.
  • IEEE Transactions on Systems, Man, and Cybernetics, Vol. 8, Issue 8, p. 630-632
  • DOI: 10.1109/TSMC.1978.4310039

A comprehensive evaluation of axial gas permeability in wood using XCT imaging
journal, December 2022


Minimum cross entropy thresholding
journal, April 1993


TomoPy: a framework for the analysis of synchrotron tomographic data
journal, August 2014

  • Gürsoy, Dogˇa; De Carlo, Francesco; Xiao, Xianghui
  • Journal of Synchrotron Radiation, Vol. 21, Issue 5
  • DOI: 10.1107/S1600577514013939

Learning representations by back-propagating errors
journal, October 1986

  • Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J.
  • Nature, Vol. 323, Issue 6088
  • DOI: 10.1038/323533a0

Phase segmentation of uncured prepreg X-Ray CT micrographs
journal, October 2021


Not Just Lumber—Using Wood in the Sustainable Future of Materials, Chemicals, and Fuels
journal, July 2016


Image Segmentation Using Multilevel Thresholding: A Research Review
journal, August 2019

  • Pare, S.; Kumar, A.; Singh, G. K.
  • Iranian Journal of Science and Technology, Transactions of Electrical Engineering, Vol. 44, Issue 1
  • DOI: 10.1007/s40998-019-00251-1

Utilization of Information Measure as a Means of Image Thresholding
journal, September 1994


Quasi-real-time x-ray microtomography system at the Advanced Photon Source
conference, September 1999

  • Wang, Yuxin; De Carlo, Francesco; Foster, Ian
  • SPIE's International Symposium on Optical Science, Engineering, and Instrumentation, SPIE Proceedings
  • DOI: 10.1117/12.363735

The Analysis of cell Images*
journal, January 1966


X-ray methods to observe and quantify adhesive penetration into wood
journal, August 2018

  • Jakes, Joseph E.; Frihart, Charles R.; Hunt, Christopher G.
  • Journal of Materials Science, Vol. 54, Issue 1
  • DOI: 10.1007/s10853-018-2783-5

Cellular Solids
book, January 2014


X-ray computed tomography of wood-adhesive bondlines: attenuation and phase-contrast effects
journal, July 2015

  • Paris, Jesse L.; Kamke, Frederick A.; Xiao, Xianghui
  • Wood Science and Technology, Vol. 49, Issue 6
  • DOI: 10.1007/s00226-015-0750-8

Stripe and ring artifact removal with combined wavelet—Fourier filtering
journal, January 2009

  • Münch, Beat; Trtik, Pavel; Marone, Federica
  • Optics Express, Vol. 17, Issue 10
  • DOI: 10.1364/OE.17.008567

Reconstruction of CT Images Using Iterative Least-Squares Methods with Nonnegative Constraint
journal, March 2019

  • Kohno, Hiromasa; Tanji, Yuichi; Fujimoto, Ken'ichi
  • Journal of Signal Processing, Vol. 23, Issue 2
  • DOI: 10.2299/jsp.23.41

Hysteresis in swelling and in sorption of wood tissue
journal, June 2013

  • Patera, Alessandra; Derome, Dominique; Griffa, Michele
  • Journal of Structural Biology, Vol. 182, Issue 3
  • DOI: 10.1016/j.jsb.2013.03.003

Methodology for comparing wood adhesive bond load transfer using digital volume correlation
journal, September 2018


Moment-preserving thresolding: A new approach
journal, March 1985


Humidity fixed points of binary saturated aqueous solutions
journal, January 1977

  • Greenspan, Lewis
  • Journal of Research of the National Bureau of Standards Section A: Physics and Chemistry, Vol. 81A, Issue 1
  • DOI: 10.6028/jres.081A.011

Quantitative wood–adhesive penetration with X-ray computed tomography
journal, September 2015


Cross laminated timber (CLT): overview and development
journal, January 2016

  • Brandner, R.; Flatscher, G.; Ringhofer, A.
  • European Journal of Wood and Wood Products, Vol. 74, Issue 3
  • DOI: 10.1007/s00107-015-0999-5

Wood Moisture-Induced Swelling at the Cellular Scale—Ab Intra
journal, November 2019

  • Arzola-Villegas, Xavier; Lakes, Roderic; Plaza, Nayomi Z.
  • Forests, Vol. 10, Issue 11
  • DOI: 10.3390/f10110996

A Threshold Selection Method from Gray-Level Histograms
journal, January 1979