Abstract
Time-of-flight secondary ion mass spectrometry (TOF–SIMS) is a useful and versatile tool for surface analysis, enabling detailed compositional information to be obtained for the surfaces of diverse samples. Furthermore, in the case of two- or three-dimensional imaging, the measurement sensitivity in the higher molecular weight range can be improved by using a cluster ion source, thus further enriching the TOF–SIMS information. Therefore, appropriate analytical methods are required to interpret this TOF–SIMS data. This study explored the capabilities of a sparse autoencoder, a feature extraction method based on artificial neural networks, to process TOF–SIMS image data. The sparse autoencoder was applied to TOF–SIMS images of human skin keratinocytes to extract the distribution of endogenous intercellular lipids and externally penetrated drugs. The results were compared with those obtained using principal component analysis (PCA) and multivariate curve resolution (MCR), which are conventionally used for extracting features from TOF–SIMS data. This confirmed that the sparse autoencoder matches, and often betters, the feature extraction performance of conventional methods, while also offering greater flexibility.
Graphical abstract
Similar content being viewed by others
Data availability
The raw data of this study are available on request with proper reason from the corresponding author, Kazuhiro Matsuda.
Code availability
Not applicable.
References
Douglas MA, Chen PJ. Quantitative trace metal analysis of silicon surface by ToF-SIMS. Surf Interface Anal. 1998;26(13):984–94.
Zanderigo F, Ferrari S, Queirolo G, Pello C, Borgini M. Quantitative TOF-SIMS analysis of metal contamination on silicon wafers. Mat Sci Eng B-Solid. 2000;73(1):173–7.
Auditore A, Samperi F, Puglisi C, Licciardello A. ToF-SIMS investigation of the thermally induced processes at the surface of polyester based polymer blends. Compos Sci Technol. 2003;63(8):1213–9.
Oran U, Ünveren E, Wirth T, Unger WES. Poly-dimethyl-siloxane (PDMS) contamination of polystyrene (PS) oligomers samples: a comparison of time-of-flight static secondary ion mass spectrometry (TOF-SSIMS) and X-ray photoelectron spectroscopy (XPS) results. Appl Surf Sci. 2004;227(1–4):318–24.
Belu AM, Graham DJ, Castner DG. Time-of-flight secondary ion mass spectrometry: techniques and applications for the characterization of biomaterial surfaces. Biomaterials. 2003;24(21):3635–53.
Kessler L, Legeay G, Coudreuse A, Bertrand P, Poleunus C, Vanden Eynde X, Mandes K, Marchetti P, Pinget M, Belcourt A. Surface treatment of polycarbonate films aimed at biomedical application. J Biomater Sci, Polym Ed. 2003;14(10):1135–53.
Kingshott P, Andersson G, McArthur SL, Griesser HJ. Surface modification and chemical surface analysis of biomaterials. Curr Opin Chem Biol. 2011;15(5):667–76.
Benabdellah F, Seyer A, Quinton L, Touboul D, Brunelle A, Laprevote O. Mass spectrometry imaging of rat brain sections: nanomolar sensitivity with MALDI versus nanometer resolution by TOF-SIMS. Anal Bioanal Chem. 2010;396(1):151–62.
Brunelle A, Touboul D, Laprevote O. Biological tissue imaging with time-of-flight secondary ion mass spectrometry and cluster ion sources. J Mass Spectrom. 2005;40(8):985–99.
Kim JH, Kim JH, Ahn BJ, Park JH, Shon HK, Yu YS, Moon DW, Lee TG, Kim KW. Label-free calcium imaging in ischemic retinal tissue by TOF-SIMS. Biophys J. 2008;94(10):4095–102.
Kojima T, Yamada H, Yamamoto T, Matsushita Y, Fukushima K. Dyeing regions of oxidative hair dyes in human hair investigated by nanoscale secondary ion mass spectrometry. Colloids Surf B Biointerfaces. 2013;106:140–4.
Mains J, Wilson CG, Urquhart A. ToF-SIMS analysis of dexamethasone distribution in the isolated perfused eye. Invest Ophthalmol Vis Sci. 2011;52(11):8413–9.
Sjövall P, Rossmeisl M, Hanrieder J, Kuda O, Kopecky J, Bryhn M. Dietary uptake of omega-3 fatty acids in mouse tissue studied by time-of-flight secondary ion mass spectrometry (TOF-SIMS). Anal Bioanal Chem. 2015;407(17):5101–11.
Fletcher JS. Latest applications of 3D ToF-SIMS bio-imaging. Biointerphases. 2015;10(1):018902.
Passarelli MK, Winograd N. Characterizing in situ glycerophospholipids with SIMS and MALDI methodologies. Surf Interface Anal. 2011;43(1–2):269–71.
Weibel DE, Lockyer N, Vickerman JC. C60 cluster ion bombardment of organic surfaces. Appl Surf Sci. 2004;231–232:146–52.
Angerer TB, Velickovic D, Nicora CD, Kyle JE, Graham DJ, Anderton C, Gamble LJ. Exploiting the semidestructive nature of gas cluster ion beam time-of-flight secondary ion mass spectrometry imaging for simultaneous localization and confident LIPID ANNOTATIONS. Anal Chem. 2019;91(23):15073–80.
Fujii M, Nakagawa S, Matsuda K, Man N, Seki T, Aoki T, Matsuo J. Study on the detection limits of a new argon gas cluster ion beam secondary ion mass spectrometry apparatus using lipid compound samples. Rapid Commun Mass Spectrom. 2014;28(8):917–20.
Mohammadi AS, Phan NT, Fletcher JS, Ewing AG. Intact lipid imaging of mouse brain samples: MALDI, nanoparticle-laser desorption ionization, and 40 keV argon cluster secondary ion mass spectrometry. Anal Bioanal Chem. 2016;408(24):6857–68.
Dimovska Nilsson K, Karagianni A, Kaya I, Henricsson M, Fletcher JS. (CO2)n+, (H2O)n+, and (H2O)n+ (CO2) gas cluster ion beam secondary ion mass spectrometry: analysis of lipid extracts, cells, and Alzheimer’s model mouse brain tissue. Anal Bioanal Chem. 2021;413(16):4181–94.
Razo IB, Sheraz S, Henderson A, Lockyer NP, Vickerman JC. Mass spectrometric imaging of brain tissue by time-of-flight secondary ion mass spectrometry - how do polyatomic primary beams C60+, Ar2000+, water-doped Ar2000+ and (H2O)6000+ compare? Rapid Commun Mass Spectrom. 2015;29(20):1851–62.
Lee JLS, Gilmore IS, Fletcher IW, Seah MP. Multivariate image analysis strategies for ToF-SIMS images with topography. Surf Interface Anal. 2009;41(8):653–65.
Wagner MS, Castner DG. Characterization of adsorbed protein films by time-of-flight secondary ion mass spectrometry with principal component analysis. Langmuir. 2001;17(15):4649–60.
Wagner MS, Graham DJ, Castner DG. Simplifying the interpretation of ToF-SIMS spectra and images using careful application of multivariate analysis. Appl Surf Sci. 2006;252(19):6575–81.
Aoyagi S, Matsuzaki T, Takahashi M, Sakurai Y, Kudo M. Evaluation of reagent effect on skin using time-of-flight secondary ion mass spectrometry and multivariate curve resolution. Surf Interface Anal. 2012;44(6):772–5.
Lai H, Liu Q, Deng J, Wen S, Liu Z. Surface chemistry study of Cu-Pb sulfide ore using ToF-SIMS and multivariate analysis. Appl Surf Sci. 2020;518.
Almuqhim F, Saeed F. ASD-SAENet: a sparse autoencoder, and deep-neural network model for detecting autism spectrum disorder (ASD) using fMRI data. Front Comput Neurosci. 2021;15:654315.
Aslam MA, Xue C, Chen Y, Zhang A, Liu M, Wang K, Cui D. Breath analysis based early gastric cancer classification from deep stacked sparse autoencoder neural network. Sci Rep. 2021;11(1):4014.
Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science. 2006;313(5786):504–7.
Kawashima T, Aoki T, Taniike Y, Aoyagi S. Examination of beauty ingredient distribution in the human skin by time-of-flight secondary ion mass spectrometry. Biointerphases. 2020;15(3):031013.
Thomas SA, Race AM, Steven RT, Gilmore IS, Bunch J. Dimensionality reduction of mass spectrometry imaging data using autoencoders. Proceedings of the 2016 IEEE Symposium Series on Computational Intelligence (SSCI). 2016.
Matsuda K, Aoyagi S. Time-of-flight secondary ion mass spectrometry analysis of hair samples using unsupervised artificial neural network. Biointerphases. 2020;15(2):021013.
Starr NJ, Abdul Hamid K, Wibawa J, Marlow I, Bell M, Perez-Garcia L, Barrett DA, Scurr DJ. Enhanced vitamin C skin permeation from supramolecular hydrogels, illustrated using in situ ToF-SIMS 3D chemical profiling. Int J Pharm. 2019;563:21–9.
Cizinauskas V, Elie N, Brunelle A, Briedis V. Fatty acids penetration into human skin ex vivo: a TOF-SIMS analysis approach. Biointerphases. 2017;12(1):011003.
Holmes AM, Scurr DJ, Heylings JR, Wan KW, Moss GP. Dendrimer pre-treatment enhances the skin permeation of chlorhexidine digluconate: characterisation by in vitro percutaneous absorption studies and time-of-flight secondary ion mass spectrometry. Eur J Pharm Sci. 2017;104:90–101.
Sjövall P, Skedung L, Gregoire S, Biganska O, Clément F, Luengo GS. Imaging the distribution of skin lipids and topically applied compounds in human skin using mass spectrometry. Sci Rep. 2018;8(1):16683.
Starr NJ, Johnson DJ, Wibawa J, Marlow I, Bell M, Barrett DA, Scurr DJ. Age-related changes to human stratum corneum lipids detected using time-of-flight secondary ion mass spectrometry following in vivo sampling. Anal Chem. 2016;88(8):4400–8.
Chollet F, et al. Keras 2015 [Available from: https://keras.io. Accessed 15 Sep 2021.
Géron A. Hand’s-on machine learning with Scikit-Learn, Keras, & Tensorflow. 2nd ed. Sebastpol CA: O’ Reilly Media, Inc.; 2019.
Kingma DP, Ba JL. Adam: A method for stochastic optimization. 3rd International Conference for Learning Representations (ICLR) 2015; San Diego: arXiv preprint; 2014.
Author information
Authors and Affiliations
Contributions
Kazuhiro Matsuda was responsible for writing (original draft), investigation, data acquisition (sample preparation and TOF–SIMS measurements), data processing, and data visualization.
Satoka Aoyagi was responsible for supervision, methodology, and writing (review and editing).
Corresponding author
Ethics declarations
Ethics approval
The evaluation of this study was based on the Declaration of Helsinki and conducted under approval of the ethics committee of Toray research center Inc.
Consent to participate
Written informed consent was obtained from the provider of skin corneocytes for publication of this study.
Consent for publication
Consent for publication was obtained from the provider of skin corneocytes by written form.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Matsuda, K., Aoyagi, S. Sparse autoencoder–based feature extraction from TOF–SIMS image data of human skin structures. Anal Bioanal Chem 414, 1177–1186 (2022). https://doi.org/10.1007/s00216-021-03744-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00216-021-03744-3