Insight into 3D micro-CT data: exploring segmentation algorithms through performance metrics
Abstract
Three-dimensional (3D) micro-tomography (µ-CT) has proven to be an important imaging modality in industry and scientific domains. Understanding the properties of material structure and behavior has produced many scientific advances. An important component of the 3D µ-CT pipeline is image partitioning (or image segmentation), a step that is used to separate various phases or components in an image. Image partitioning schemes require specific rules for different scientific fields, but a common strategy consists of devising metrics to quantify performance and accuracy. The present article proposes a set of protocols to systematically analyze and compare the results of unsupervised classification methods used for segmentation of synchrotron-based data. Additionally, the proposed dataflow for Materials Segmentation and Metrics (MSM) provides 3D micro-tomography image segmentation algorithms, such as statistical region merging (SRM), k-means algorithm and parallel Markov random field (PMRF), while offering different metrics to evaluate segmentation quality, confidence and conformity with standards. Both experimental and synthetic data are assessed, illustrating quantitative results through the MSM dashboard, which can return sample information such as media porosity and permeability. The main contributions of this work are: (i) to deliver tools to improve material design and quality control; (ii) to provide datasets for benchmarking and reproducibility;more »
- Authors:
-
[1];
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Univ. of California, Berkeley, CA (United States)
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Advanced Light Source (ALS)
- Univ. of California, Santa Barbara, CA (United States)
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); US Office of Naval Research (ONR)
- OSTI Identifier:
- 1764517
- Grant/Contract Number:
- AC02-05CH11231; N00014-13-1-0860
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of Synchrotron Radiation (Online)
- Additional Journal Information:
- Journal Name: Journal of Synchrotron Radiation (Online); Journal Volume: 24; Journal Issue: 5; Journal ID: ISSN 1600-5775
- Publisher:
- International Union of Crystallography
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; unsupervised segmentation; micro-tomography; ceramic matrix composites; image analysis
Citation Formats
Perciano, Talita, Ushizima, Daniela, Krishnan, Harinarayan, Parkinson, Dilworth, Larson, Natalie, Pelt, Daniël M., Bethel, Wes, Zok, Frank, and Sethian, James. Insight into 3D micro-CT data: exploring segmentation algorithms through performance metrics. United States: N. p., 2017.
Web. doi:10.1107/s1600577517010955.
Perciano, Talita, Ushizima, Daniela, Krishnan, Harinarayan, Parkinson, Dilworth, Larson, Natalie, Pelt, Daniël M., Bethel, Wes, Zok, Frank, & Sethian, James. Insight into 3D micro-CT data: exploring segmentation algorithms through performance metrics. United States. https://doi.org/10.1107/s1600577517010955
Perciano, Talita, Ushizima, Daniela, Krishnan, Harinarayan, Parkinson, Dilworth, Larson, Natalie, Pelt, Daniël M., Bethel, Wes, Zok, Frank, and Sethian, James. Wed .
"Insight into 3D micro-CT data: exploring segmentation algorithms through performance metrics". United States. https://doi.org/10.1107/s1600577517010955. https://www.osti.gov/servlets/purl/1764517.
@article{osti_1764517,
title = {Insight into 3D micro-CT data: exploring segmentation algorithms through performance metrics},
author = {Perciano, Talita and Ushizima, Daniela and Krishnan, Harinarayan and Parkinson, Dilworth and Larson, Natalie and Pelt, Daniël M. and Bethel, Wes and Zok, Frank and Sethian, James},
abstractNote = {Three-dimensional (3D) micro-tomography (µ-CT) has proven to be an important imaging modality in industry and scientific domains. Understanding the properties of material structure and behavior has produced many scientific advances. An important component of the 3D µ-CT pipeline is image partitioning (or image segmentation), a step that is used to separate various phases or components in an image. Image partitioning schemes require specific rules for different scientific fields, but a common strategy consists of devising metrics to quantify performance and accuracy. The present article proposes a set of protocols to systematically analyze and compare the results of unsupervised classification methods used for segmentation of synchrotron-based data. Additionally, the proposed dataflow for Materials Segmentation and Metrics (MSM) provides 3D micro-tomography image segmentation algorithms, such as statistical region merging (SRM), k-means algorithm and parallel Markov random field (PMRF), while offering different metrics to evaluate segmentation quality, confidence and conformity with standards. Both experimental and synthetic data are assessed, illustrating quantitative results through the MSM dashboard, which can return sample information such as media porosity and permeability. The main contributions of this work are: (i) to deliver tools to improve material design and quality control; (ii) to provide datasets for benchmarking and reproducibility; (iii) to yield good practices in the absence of standards or ground-truth for ceramic composite analysis.},
doi = {10.1107/s1600577517010955},
journal = {Journal of Synchrotron Radiation (Online)},
number = 5,
volume = 24,
place = {United States},
year = {Wed Aug 23 00:00:00 EDT 2017},
month = {Wed Aug 23 00:00:00 EDT 2017}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Influence of segmentation on micro-CT images of trabecular bone: SEGMENTATION OF MICRO-CT IMAGES OF TRABECULAR BONE
journal, August 2014
- Tassani, S.; Korfiatis, V.; Matsopoulos, G. K.
- Journal of Microscopy, Vol. 256, Issue 2
Statistical region merging
journal, November 2004
- Nock, R.; Nielsen, F.
- IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, Issue 11
Contour Detection and Hierarchical Image Segmentation
journal, May 2011
- Arbeláez, P.; Maire, M.; Fowlkes, C.
- IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33, Issue 5
Real-time quantitative imaging of failure events in materials under load at temperatures above 1,600 °C
journal, December 2012
- Bale, Hrishikesh A.; Haboub, Abdel; MacDowell, Alastair A.
- Nature Materials, Vol. 12, Issue 1
Augmented Topological Descriptors of Pore Networks for Material Science
journal, December 2012
- Ushizima, Daniela; Morozov, Dmitriy; Weber, Gunther H.
- IEEE Transactions on Visualization and Computer Graphics, Vol. 18, Issue 12
A Parallel EM Algorithm for Model-Based Clustering Applied to the Exploration of Large Spatio-Temporal Data
journal, November 2013
- Chen, Wei-chen; Ostrouchov, George; Pugmire, David
- Technometrics, Vol. 55, Issue 4
XDesign : an open-source software package for designing X-ray imaging phantoms and experiments
journal, February 2017
- Ching, Daniel J.; Gürsoy, Dogˇa
- Journal of Synchrotron Radiation, Vol. 24, Issue 2
Techniques in helical scanning, dynamic imaging and image segmentation for improved quantitative analysis with X-ray micro-CT
journal, April 2014
- Sheppard, Adrian; Latham, Shane; Middleton, Jill
- Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms, Vol. 324
PITRE : software for phase-sensitive X-ray image processing and tomography reconstruction
journal, August 2012
- Chen, Rong-Chang; Dreossi, Diego; Mancini, Lucia
- Journal of Synchrotron Radiation, Vol. 19, Issue 5
Fast computation of morphological operations with arbitrary structuring elements
journal, December 1996
- Van Droogenbroeck, Marc; Talbot, Hugues
- Pattern Recognition Letters, Vol. 17, Issue 14
Automated segmentation of micro-CT images of bone formation in calcium phosphate scaffolds
journal, January 2012
- Polak, Samantha J.; Candido, Salvatore; Levengood, Sheeny K. Lan
- Computerized Medical Imaging and Graphics, Vol. 36, Issue 1
Voronoi diagrams---a survey of a fundamental geometric data structure
journal, September 1991
- Aurenhammer, Franz
- ACM Computing Surveys, Vol. 23, Issue 3
Image processing pipeline for synchrotron-radiation-based tomographic microscopy
journal, May 2010
- Hintermüller, C.; Marone, F.; Isenegger, A.
- Journal of Synchrotron Radiation, Vol. 17, Issue 4
Spatially and Intensity Adaptive Morphology
journal, November 2012
- Pinoli, J-C; Debayle, J.
- IEEE Journal of Selected Topics in Signal Processing, Vol. 6, Issue 7
On the longitudinal permeability of aligned fiber arrays
journal, June 2014
- Shou, Dahua; Ye, Lin; Fan, Jintu
- Journal of Composite Materials, Vol. 49, Issue 14
The ASTRA Toolbox: A platform for advanced algorithm development in electron tomography
journal, October 2015
- van Aarle, Wim; Palenstijn, Willem Jan; De Beenhouwer, Jan
- Ultramicroscopy, Vol. 157
Fiji: an open-source platform for biological-image analysis
journal, June 2012
- Schindelin, Johannes; Arganda-Carreras, Ignacio; Frise, Erwin
- Nature Methods, Vol. 9, Issue 7
Statistical segmentation and porosity quantification of 3D x-ray microtomography
conference, September 2011
- Ushizima, Daniela; Parkinson, Dilworth; Nico, Peter
- SPIE Optical Engineering + Applications, SPIE Proceedings
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