Raman spectroscopic grading of astrocytoma tissues: using soft reference information

Gliomas are the most frequent primary brain tumours. During neurosurgical treatment, locating the exact tumour border is often difficult. This study assesses grading of astrocytomas based on Raman spectroscopy for a future application in intra-surgical guidance. Our predictive classification models distinguish the surgically relevant classes “normal tissue” and “low” and “high grade astrocytoma” in Raman maps of moist bulk samples (80 patients) acquired with a fibre-optic probe. We introduce partial class memberships as a strategy to utilize borderline cases for classification. Borderline cases supply the most valuable training and test data for our application. They are (a) examples of the sought boundary and (b) the cases for which new diagnostics are needed. Besides, the number of suitable training samples increases considerably: soft logistic regression (LR) utilizes 85% more spectra and 50% more patients than linear discriminant analysis (LDA). The predictive soft LR models achieve ca. 85, 67 and 84% (normal, low and high grade) sensitivity and specificity. We discuss the different heuristics of LR and LDA in the light of borderline samples. While we focus on prediction, the spectroscopic interpretation of the predictive models agrees with previous descriptive studies. Unsaturated lipids are used to differentiate between normal and tumour tissues, while the total lipid content prominently contributes to the determination of the tumour grade. The high-wavenumber region above 2,800 cm−1 alone did not allow successful grading. We give a proof of concept for Raman spectroscopic grading of moist astrocytoma tissues and propose to include borderline samples into classifier training and testing.

[1]  Kurt Varmuza,et al.  Pattern recognition in chemistry , 1980 .

[2]  Charles E McCulloch,et al.  Relaxing the rule of ten events per variable in logistic and Cox regression. , 2007, American journal of epidemiology.

[3]  Airton Abrahão Martin,et al.  Role of cervicitis in the Raman-based optical diagnosis of cervical intraepithelial neoplasia. , 2008, Journal of biomedical optics.

[4]  D. Louis WHO classification of tumours of the central nervous system , 2007 .

[5]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[6]  Khek Yu Ho,et al.  Near-infrared Raman spectroscopy for gastric precancer diagnosis , 2009 .

[7]  Gerwin J Puppels,et al.  Fiber-optic probes for in vivo Raman spectroscopy in the high-wavenumber region. , 2005, Analytical chemistry.

[8]  C. J. Huberty,et al.  Applied Discriminant Analysis , 1994 .

[9]  Webster K. Cavenee,et al.  Erratum: The 2007 WHO classification of tumours of the central nervous system (Acta Neuropathol (2007) vol. 114 (97-109)) , 2007 .

[10]  Claudia Beleites,et al.  Variance reduction in estimating classification error using sparse datasets , 2005 .

[11]  Brian D. Ripley,et al.  Modern applied statistics with S, 4th Edition , 2002, Statistics and computing.

[12]  G. Socrates,et al.  Infrared and Raman characteristic group frequencies : tables and charts , 2001 .

[13]  Anita Mahadevan-Jansen,et al.  Comparison of autofluorescence, diffuse reflectance, and Raman spectroscopy for breast tissue discrimination. , 2008, Journal of biomedical optics.

[14]  Christoph Krafft,et al.  Methodology for fiber-optic Raman mapping and FTIR imaging of metastases in mouse brains , 2007, Analytical and bioanalytical chemistry.

[15]  M. Barker,et al.  Partial least squares for discrimination , 2003 .

[16]  R. Salzer,et al.  Raman spectroscopic imaging for in vivo detection of cerebral brain metastases , 2010, Analytical and bioanalytical chemistry.

[17]  J. Concato,et al.  A simulation study of the number of events per variable in logistic regression analysis. , 1996, Journal of clinical epidemiology.

[18]  Christoph Krafft,et al.  Near infrared Raman spectroscopic mapping of native brain tissue and intracranial tumors. , 2005, The Analyst.

[19]  F. Abdul-Karim,et al.  Interobserver reproducibility among neuropathologists and surgical pathologists in fibrillary astrocytoma grading , 2000, Journal of the Neurological Sciences.

[20]  Jürgen Popp,et al.  Discriminating isogenic cancer cells and identifying altered unsaturated fatty acid content as associated with metastasis status, using k-means clustering and partial least squares-discriminant analysis of Raman maps. , 2010, Analytical chemistry.

[21]  Caterina Giannini,et al.  Panel Review of Anaplastic Oligodendroglioma From European Organization for Research and Treatment of Cancer Trial 26951: Assessment of Consensus in Diagnosis, Influence of 1p/19q Loss, and Correlations With Outcome , 2007, Journal of neuropathology and experimental neurology.

[22]  T C Bakker Schut,et al.  Tissue characterization using high wave number Raman spectroscopy. , 2005, Journal of biomedical optics.

[23]  J. Raizer,et al.  Low-grade gliomas: management issues , 2007, Expert review of anticancer therapy.

[24]  Anita Mahadevan-Jansen,et al.  A Probability-Based Spectroscopic Diagnostic Algorithm for Simultaneous Discrimination of Brain Tumor and Tumor Margins from Normal Brain Tissue , 2007, Applied spectroscopy.

[25]  Max Diem,et al.  Vibrational Spectroscopy for Medical Diagnosis , 2008 .

[26]  S. Vandenberg Current Diagnostic Concepts of Astrocytic Tumors , 1992, Journal of neuropathology and experimental neurology.

[27]  K. Aldape,et al.  Diagnostic, treatment, and demographic factors influencing survival in a population-based study of adult glioma patients in the San Francisco Bay Area. , 2006, Neuro-oncology.

[28]  Anita Mahadevan-Jansen,et al.  Multiclass discrimination of cervical precancers using Raman spectroscopy. , 2009, Journal of Raman spectroscopy : JRS.

[29]  Giles M. Foody,et al.  Status of land cover classification accuracy assessment , 2002 .

[30]  M. Manfait,et al.  Ex vivo and in vivo diagnosis of C6 glioblastoma development by Raman spectroscopy coupled to a microprobe , 2010, Analytical and bioanalytical chemistry.

[31]  Christoph Krafft,et al.  Disease recognition by infrared and Raman spectroscopy , 2009, Journal of biophotonics.

[32]  Christoph Krafft,et al.  Analysis of human brain tissue, brain tumors and tumor cells by infrared spectroscopic mapping. , 2004, The Analyst.

[33]  C. Kendall,et al.  Vibrational spectroscopy: a clinical tool for cancer diagnostics. , 2009, The Analyst.

[34]  William N. Venables,et al.  Modern Applied Statistics with S , 2010 .

[35]  Tom Fearn,et al.  Characterising the performance of qualitative analytical methods: Statistics and terminology , 2005 .

[36]  Valerii Fedorov,et al.  Consequences of dichotomization , 2009, Pharmaceutical statistics.

[37]  M. Teh,et al.  Near‐infrared Raman spectroscopy for early diagnosis and typing of adenocarcinoma in the stomach , 2010, The British journal of surgery.

[38]  Elena Mazza,et al.  Anaplastic astrocytoma in adults. , 2007, Critical reviews in oncology/hematology.

[39]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[40]  Thomas Lengauer,et al.  ROCR: visualizing classifier performance in R , 2005, Bioinform..

[41]  Abdelilah Beljebbar,et al.  Modeling and quantifying biochemical changes in C6 tumor gliomas by Fourier transform infrared imaging. , 2008, Analytical chemistry.

[42]  Steven Salzberg,et al.  On Comparing Classifiers: Pitfalls to Avoid and a Recommended Approach , 1997, Data Mining and Knowledge Discovery.

[43]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[44]  Ron Kohavi,et al.  Wrappers for performance enhancement and oblivious decision graphs , 1995 .

[45]  Nicholas Stone,et al.  Investigation of support vector machines and Raman spectroscopy for lymph node diagnostics. , 2010, The Analyst.

[46]  Christoph Krafft,et al.  Suitability of infrared spectroscopic imaging as an intraoperative tool in cerebral glioma surgery , 2009, Analytical and bioanalytical chemistry.

[47]  L. Choo-Smith,et al.  Discriminating Vital Tumor from Necrotic Tissue in Human Glioblastoma Tissue Samples by Raman Spectroscopy , 2002, Laboratory Investigation.

[48]  Christoph Krafft,et al.  Characterization of lipid extracts from brain tissue and tumors using Raman spectroscopy and mass spectrometry , 2009, Analytical and bioanalytical chemistry.

[49]  Jørgen Bru,et al.  Fiber optic probes for biomedical optical spectroscopy , 2008 .

[50]  T. B. Bakker Schut,et al.  Discriminating basal cell carcinoma from its surrounding tissue by Raman spectroscopy. , 2002, The Journal of investigative dermatology.

[51]  C. Klötzsch,et al.  Leitlinien für Diagnostik und Therapie in der Neurologie , 2012 .

[52]  C. Krafft,et al.  Biomedical applications of Raman and infrared spectroscopy to diagnose tissues , 2006 .

[53]  Cedric E. Ginestet ggplot2: Elegant Graphics for Data Analysis , 2011 .

[54]  B. Scheithauer,et al.  The 2007 WHO classification of tumours of the central nervous system , 2007, Acta Neuropathologica.

[55]  Bruce R. Kowalski,et al.  31 Pattern recognition in chemistry , 1982, Classification, Pattern Recognition and Reduction of Dimensionality.

[56]  Abdelilah Beljebbar,et al.  Discriminating healthy from tumor and necrosis tissue in rat brain tissue samples by Raman spectral imaging. , 2007, Biochimica et biophysica acta.

[57]  F. Zanella,et al.  Fluorescence-guided surgery with 5-aminolevulinic acid for resection of malignant glioma: a randomised controlled multicentre phase III trial. , 2006, The Lancet. Oncology.

[58]  Claudia Beleites,et al.  Assessing and improving the stability of chemometric models in small sample size situations , 2008, Analytical and bioanalytical chemistry.

[59]  Ron Wehrens,et al.  The pls Package: Principal Component and Partial Least Squares Regression in R , 2007 .

[60]  Christoph Krafft,et al.  Near infrared Raman spectra of human brain lipids. , 2005, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[61]  Hugh Barr,et al.  Raman spectroscopy, a potential tool for the objective identification and classification of neoplasia in Barrett's oesophagus , 2003, The Journal of pathology.