Received: 7 July 2017 Revised: 6 October 2017 Accepted: 12 October 2017 DOI: 10.1002/cem.2973 SPECIAL ISSUE ARTICLE Integrating spatial, morphological, and textural information for improved cell type differentiation using Raman microscopy Sascha D. Krauß 1 Hesham K. Yosef 1 Tatjana Lechtonen 1 Hendrik Jütte 2 Andrea Tannapfel 2 Heiko U. Käfferlein 3 Thomas Brüning 3 Florian Roghmann 4 Joachim Noldus 4 Samir F. El-Mashtoly 1 Klaus Gerwert 1 Axel Mosig 1 1 Department of Biophysics, Ruhr-University Bochum, 44780 Bochum, Germany 2 Institute of Pathology, Bergmannsheil Hospital, Ruhr-University Bochum, 44789 Bochum, Germany 3 Institute for Prevention and Occupational Medicine of the German Social Accident Insurance, Institute of the Ruhr-University Bochum (IPA), 44789 Bochum, Germany 4 Department of Urology, Marien Hospital Herne, Ruhr-University Bochum, 44625 Herne, Germany Correspondence Axel Mosig, Department of Biophysics, Ruhr-University Bochum, 44780 Bochum, Germany. Email: axel.mosig@bph.rub.de; axel.mosig@bph.ruhr-uni-bochum.de Funding information Protein Research Unit Ruhr within Europe (PURE) ; Ministry of Innovation, Science and Research (MIWF) of North-Rhine Westphalia, Germany; European Regional Development Fund Abstract Raman microscopy is a well-established tool for distinguishing different cell types in cell biological or cytopathological applications, since it can provide maps that show the specific distribution of biochemical components in the cell, with high lateral and spatial resolution. Currently, established data analysis approaches for differentiating cells of different types mostly rely on conventional chemometrics approaches, which tend to not systematically utilise the advan- tages provided by Raman microscopic data sets. To address this, we propose 2 approaches that explicitly exploit the large number of spectra as well as the mor- phological and textural information that are available in Raman microscopic data sets. Spatial bagging as our first approach is based on a statistical analysis of majority vote over classification results obtained from individual pixel spec- tra. Based on the Condorcet's Jury Theorem, this approach raises the accuracy of a relatively weak classifier for individual spectra to nearly perfect accuracy at the level of characterising whole cells. Our second approach extracts morpho- logical and textural (morpho-textural) features from Raman microscopic images to differentiate cell types. While using few wavenumbers of the Raman spec- trum only, our results indicate on a quantitative basis that Raman microscopic images carry more morphological and textural information than haematoxylin and eosin (H&E) stained images as the current gold standard in cytopathol- ogy. Our 2 approaches promise improved protocols for the fast acquisition of Raman imaging data, for instance, for the morphological analysis of coherent anti-Stokes Raman spectroscopy microscopic imaging data or for improving the accuracy of fibre optical probe systems by resampling spectra and utilising spatial bagging. KEYWORDS cytopathology, morphological classification, Raman microscopy, supervised learning, spatial bag- ging 1 INTRODUCTION Raman microscopy provides a label-free approach to characterise cellular samples at high spatial and lateral resolu- tion, where the pixel spectra of a Raman microscopic image are both highly location specific and representative of the Journal of Chemometrics. 2018;32:e2973. wileyonlinelibrary.com/journal/cem Copyright © 2017 John Wiley & Sons, Ltd. 1 of 11 https://doi.org/10.1002/cem.2973