Development of the Self Optimising Kohonen Index Network (SKiNET) for Raman Spectroscopy Based Detection of Anatomical Eye Tissue

Raman spectroscopy shows promise as a tool for timely diagnostics via in-vivo spectroscopy of the eye, for a number of ophthalmic diseases. By measuring the inelastic scattering of light, Raman spectroscopy is able to reveal detailed chemical characteristics, but is an inherently weak effect resulting in noisy complex signal, which is often difficult to analyse. Here, we embraced that noise to develop the self-optimising Kohonen index network (SKiNET), and provide a generic framework for multivariate analysis that simultaneously provides dimensionality reduction, feature extraction and multi-class classification as part of a seamless interface. The method was tested by classification of anatomical ex-vivo eye tissue segments from porcine eyes, yielding an accuracy >93% across 5 tissue types. Unlike traditional packages, the method performs data analysis directly in the web browser through modern web and cloud technologies as an open source extendable web app. The unprecedented accuracy and clarity of the SKiNET methodology has the potential to revolutionise the use of Raman spectroscopy for in-vivo applications.

[1]  Alexey Pomerantsev,et al.  Multiclass partial least squares discriminant analysis: Taking the right way-A critical tutorial , 2018, Journal of Chemometrics.

[2]  Martin Grootveld,et al.  Self Organising Maps for variable selection: Application to human saliva analysed by nuclear magnetic resonance spectroscopy to investigate the effect of an oral healthcare product , 2009 .

[3]  Anastasios Bezerianos,et al.  The Supervised Network Self-Organizing Map for Classification of Large Data Sets , 2002, Applied Intelligence.

[4]  Karen Esmonde-White,et al.  focal point review , 2012 .

[5]  A. Talari,et al.  Raman Spectroscopy of Biological Tissues , 2007 .

[6]  John Creasey,et al.  The Blind Spot , 1940, Nature.

[7]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[8]  Peter Hildebrandt,et al.  Theory of Infrared Absorption and Raman Spectroscopy , 2008 .

[9]  Holly J. Butler,et al.  Using Raman spectroscopy to characterize biological materials , 2016, Nature Protocols.

[10]  Margarita Osadchy,et al.  Deep Convolutional Neural Networks for Raman Spectrum Recognition: A Unified Solution , 2017, The Analyst.

[11]  Richard G Brereton,et al.  Self organising maps for visualising and modelling , 2012, Chemistry Central Journal.

[12]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[13]  F.H.M. Jongsma,et al.  Raman Spectroscopy in Ophthalmology: From Experimental Tool to Applications In Vivo , 2001, Lasers in Medical Science.

[14]  R. S. Krishnan,et al.  Raman effect: History of the discovery , 1981 .

[15]  Lori M. Bruce,et al.  Why principal component analysis is not an appropriate feature extraction method for hyperspectral data , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[16]  M Motamedi,et al.  Noninvasive assessment of the hydration gradient across the cornea using confocal Raman spectroscopy. , 1998, Investigative ophthalmology & visual science.

[17]  Klaus Klaushofer,et al.  Raman analysis of proteoglycans simultaneously in bone and cartilage , 2014 .

[18]  Ronei J. Poppi,et al.  Discrimination between authentic and counterfeit banknotes using Raman spectroscopy and PLS-DA with uncertainty estimation , 2013 .

[19]  Chia-Yu Chang,et al.  Essential fatty acids and human brain. , 2009, Acta neurologica Taiwanica.

[20]  Sarah E Bohndiek,et al.  Raman micro-spectroscopy for accurate identification of primary human bronchial epithelial cells , 2018, Scientific Reports.

[21]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[22]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[23]  R. Brereton,et al.  Supervised self organizing maps for classification and determination of potentially discriminatory variables: illustrated by application to nuclear magnetic resonance metabolomic profiling. , 2010, Analytical chemistry.

[24]  Y. Ozaki,et al.  Raman spectroscopic study of age-related structural changes in the lens proteins of an intact mouse lens. , 1983, Biochemistry.

[25]  Oxana Ye. Rodionova,et al.  Multiclass partial least squares discriminant analysis: Taking the right way—A critical tutorial , 2018 .

[26]  Holly J. Butler,et al.  Aluminium foil as a potential substrate for ATR-FTIR, transflection FTIR or Raman spectrochemical analysis of biological specimens , 2016 .

[27]  B A Tozer,et al.  The calculation of maximum permissible exposure levels for laser radiation , 1979 .

[28]  P. Bernstein,et al.  Resonant Raman detection of macular pigment levels in the living human retina. , 2001, Optics letters.

[29]  Paul S. Bernstein,et al.  Macular carotenoid levels of normal subjects and age-related maculopathy patients in a Japanese population. , 2008, Ophthalmology.

[30]  Christopher. Simons,et al.  Machine learning with Python , 2017 .

[31]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[32]  John Elliot,et al.  HISTORY of the Discovery , 2013 .

[33]  P. Larkin,et al.  IR and Raman Spectra-Structure Correlations , 2011 .

[34]  Jianji Pan,et al.  Rapid detection of nasopharyngeal cancer using Raman spectroscopy and multivariate statistical analysis. , 2015, Molecular and clinical oncology.

[35]  R. Brereton,et al.  Partial least squares discriminant analysis: taking the magic away , 2014 .