Automated correlative segmentation of large Transmission X-ray Microscopy (TXM) tomograms using deep learning

Abstract A unique correlative approach for automated segmentation of large 3D nanotomography datasets obtained using Transmission X-ray Microscopy (TXM) in an Al-Cu alloy has been introduced. Automated segmentation using a Convolutional Neural Network (CNN) architecture based on a deep learning approach was employed. This extremely versatile technique is capable of emulating the manual segmentation process effectively. Coupling this technique with post-scanning SEM imaging ensured precise estimation of 3D morphological parameters from nanotomography. The segmentation process as well as subsequent analysis was expedited by several orders of magnitude. Quantitative comparison between segmentation performed manually and using the CNN architecture established the accuracy of this automated technique. Its ability to robustly process ultra-large volumes of data in relatively small time frames can exponentially accelerate tomographic data analysis, possibly opening up novel avenues for performing 4D characterization experiments with finer time steps.

[1]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  S. Wilkins,et al.  Phase-contrast imaging using polychromatic hard X-rays , 1996, Nature.

[3]  A. Takeuchi,et al.  State of 3-D micro-damage in hydrogen redistributed regions of precharged high strength aluminium alloy , 2016 .

[4]  G. D. Preston Age-hardening of copper-aluminium alloys , 1940 .

[5]  S. Goldstein,et al.  Beam hardening artifacts in micro-computed tomography scanning can be reduced by X-ray beam filtration and the resulting images can be used to accurately measure BMD. , 2009, Bone.

[6]  Kevin W Eliceiri,et al.  NIH Image to ImageJ: 25 years of image analysis , 2012, Nature Methods.

[7]  B. Muddle,et al.  The Effect of Precipitate Shape and Orientation on Dispersion Strengthening in High Strength Aluminium Alloys , 1996 .

[8]  Jean-Michel Morel,et al.  A non-local algorithm for image denoising , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Joan Vila-Comamala,et al.  High-efficiency Fresnel zone plates for hard X-rays by 100 keV e-beam lithography and electroplating , 2011, Journal of synchrotron radiation.

[10]  Christopher M Wolverton,et al.  Multiscale modeling of θ′ precipitation in Al–Cu binary alloys , 2004 .

[11]  Robert F. Singer,et al.  The investigation of morphometric parameters of aluminium foams using micro-computed tomography , 2002 .

[12]  K. Uesugi,et al.  Direct measurement procedure for three-dimensional local crack driving force using synchrotron X-ray microtomography , 2008 .

[13]  Jeff Gelb,et al.  The Ascent of 3D X-ray Microscopy in the Laboratory , 2013, Microscopy Today.

[14]  H. Aaronson,et al.  Mechanisms of formation of θ and dissolution of θ′ precipitates in an Al-4% Cu alloy , 1966 .

[15]  K.,et al.  Quantitative assessment of microstructure and its effects on compression behavior of aluminum foams via high-resolution synchrotron X-ray tomography , 2006 .

[16]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[17]  Xianghui Xiao,et al.  Damage evolution in SiC particle reinforced Al alloy matrix composites by X-ray synchrotron tomography , 2010 .

[18]  F. De Carlo,et al.  Probing Novel Microstructural Evolution Mechanisms in Aluminum Alloys Using 4D Nanoscale Characterization , 2017, Advanced materials.

[19]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[20]  A. Takeuchi,et al.  Three-dimensional observation of nanoscopic precipitates in an aluminum alloy by microtomography with Fresnel zone plate optics , 2006 .

[21]  Stefan Holban,et al.  Segmentation of bone structure in X-ray images using convolutional neural network , 2013 .

[22]  C. Laird,et al.  Kinetics of growth of platelike precipitates , 1974 .

[23]  P. Cloetens,et al.  Advances in synchrotron radiation microtomography , 2006 .

[24]  Stéphane Roux,et al.  Crack closure and stress intensity factor measurements in nodular graphite cast iron using three-dimensional correlation of laboratory X-ray microtomography images , 2009 .

[25]  A. Guinier Structure of Age-Hardened Aluminium-Copper Alloys , 1938, Nature.

[26]  Tony Lanzirotti,et al.  Scientific data exchange: a schema for HDF5-based storage of raw and analyzed data. , 2014, Journal of synchrotron radiation.

[27]  F. Carlo,et al.  Microstructural evolution and deformation behavior of Al-Cu alloys: A Transmission X-ray Microscopy (TXM) and micropillar compression study , 2018 .

[28]  Charudatta Phatak,et al.  A convolutional neural network approach to calibrating the rotation axis for X-ray computed tomography. , 2017, Journal of synchrotron radiation.

[29]  R. Ritchie,et al.  Real-time Quantitative Imaging of Failure Events in Materials under Load at Temperatures above 1,600 , 2012 .

[30]  Ian Sinclair,et al.  A 3D measurement procedure for internal local crack driving forces via synchrotron X-ray microtomography , 2004 .

[31]  E. Maire,et al.  Characterization of the morphology of cellular ceramics by 3D image processing of X-ray tomography , 2007 .

[32]  K. Fezzaa,et al.  Nanoscale 3D imaging at the Advanced Photon Source , 2016 .

[33]  P. Withers,et al.  Quantitative X-ray tomography , 2014 .

[34]  B. Niemann,et al.  X-ray microscopy with synchrotron radiation. , 1976, Applied optics.

[35]  Jason J. Williams,et al.  Development of a lab-scale, high-resolution, tube-generated X-ray computed-tomography system for three-dimensional (3D) materials characterization , 2014 .

[36]  Francesco De Carlo,et al.  TomoPy: a framework for the analysis of synchrotron tomographic data , 2014, Journal of synchrotron radiation.

[37]  William A. Barrett,et al.  Interactive Segmentation with Intelligent Scissors , 1998, Graph. Model. Image Process..

[38]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[39]  M. Suéry,et al.  In situ and real-time 3-D microtomography investigation of dendritic solidification in an Al-10 wt.% Cu alloy , 2009 .