Table of Contents Author Guidelines Submit a Manuscript
Volume 24 (2010), Issue 1-2, Pages 67-72

Discrimination between healthy and tumor tissues on formalin-fixed paraffin-embedded breast cancer samples using IR imaging

Audrey Bénard,1,4 Christine Desmedt,2 Virginie Durbecq,2 Ghizlane Rouas,2 Denis Larsimont,3 Christos Sotiriou,2 and Erik Goormaghtigh1

1Laboratory for the Structure and Function of Biological Membranes, Center for Structural Biology and Bioinformatics, Université Libre de Bruxelles, Brussels, Belgium
2Functional Genomics and Translational Research Unit, Department of Medical Oncology, J. Bordet Institute, Brussels, Belgium
3Pathology Department, J. Bordet Institute, Brussels, Belgium
4Laboratory for the Structure and Function of Biological Membranes, Center for Structural Biology and Bioinformatics, Campus Plaine, Université Libre de Bruxelles, Bld du Triomphe Acces 2, CP 206/02, B1050 Brussels, Belgium

Copyright © 2010 Hindawi Publishing Corporation. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


This work presents a pilot study to illustrate the potential of Fourier transform infrared (FT-IR) imaging in breast cancer research. Using this technique, we have acquired infrared (IR) microspectroscopic images from healthy and cancerous breast tissue section from one patient. First of all, a Student t-test was applied, showing DNA/RNA spectral region (1400–1000 cm−1) as the most discriminant for the differentiation between healthy and tumor samples. Afterwards, a supervised pattern recognition method, Partial Least Squares (PLS) was used to develop an automated classifier to discriminate the two classes of data. Infrared spectra of independent IR measurements were used to test the classifier. The class identity was correlated with information obtained by histopathologic gold standard. The results showed that more than 95% of the training and validation spectra were correctly identified. We demonstrate that combination between IR microspectroscopic imaging and multivariate data analysis can be used as a complement to present diagnostic tools for breast cancer.