Format

Send to

Choose Destination
Biomed Opt Express. 2018 Aug 15;9(9):4294-4305. doi: 10.1364/BOE.9.004294. eCollection 2018 Sep 1.

Combining high wavenumber and fingerprint Raman spectroscopy for the detection of prostate cancer during radical prostatectomy.

Aubertin K1,2, Desroches J3, Jermyn M3,4, Trinh VQ1,2,5,6, Saad F1,2,7,8, Trudel D1,2,5,6, Leblond F1,3.

Author information

1
Centre de recherche du Centre hospitalier de l'Université de Montréal (CRCHUM), 900 rue St-Denis, Montréal, Quebec H2X 0A9, Canada.
2
Institut du cancer Montréal (ICM), 900 rue St-Denis, Montréal, Quebec H2X 0A9, Canada.
3
Polytechnique Montréal, Department of Engineering Physics, CP 6079, Succ. Centre-Ville, Montréal, Quebec H3C 3A7, Canada.
4
Dartmouth College, Thayer School of Engineering, 14 Engineering Drive, Hanover, NH 03755, USA.
5
Centre hospitalier de l'Université de Montréal (CHUM), Laboratoire de pathologie et cytologie, 1100 rue Sanguinet, Montréal, Quebec H2X 0C2, Canada.
6
Université de Montréal, Department of Pathology and Cellular Biology, 2900 Boulevard Edouard-Montpetit, Montréal, Quebec H3T 1J4, Canada.
7
Centre hospitalier de l'Université de Montréal (CHUM), Division of Urology, 1051 rue Sanguinet, Montréal, Quebec H2X 0C1, Canada.
8
Université de Montréal, Department of Surgery, 2900 Boulevard Edouard-Montpetit, Montréal, Quebec H3T 1J4, Canada.

Abstract

For prostate cancer (PCa) patients, radical prostatectomy (complete removal of the prostate) is the only curative surgical option. To date, there is no clinical technique allowing for real-time assessment of surgical margins to minimize the extent of residual cancer. Here, we present a tissue interrogation technique using a dual excitation wavelength Raman spectroscopy system capable of sequentially acquiring fingerprint (FP) and high wavenumber (HWN) Raman spectra. Results demonstrate the ability of the system to detect PCa in post-prostatectomy specimens. In total, 477 Raman spectra were collected from 18 human prostate slices. Each area measured with Raman spectroscopy was characterized as either normal or cancer based on histopathological analyses, and each spectrum was classified based on supervised learning using support vector machines (SVMs). Based on receiver operating characteristic (ROC) analysis, FP (area under the curve [AUC] = 0.89) had slightly superior cancer detection capabilities compared with HWN (AUC = 0.86). Optimal performance resulted from combining the spectral information from FP and HWN (AUC = 0.91), suggesting that the use of these two spectral regions may provide complementary molecular information for PCa detection. The use of leave-one-(spectrum)-out (LOO) or leave-one-patient-out (LOPO) cross-validation produced similar classification results when combining FP with HWN. Our findings suggest that the application of machine learning using multiple data points from the same patient does not result in biases necessarily impacting the reliability of the classification models.

KEYWORDS:

(170.3880) Medical and biological imaging; (170.4580) Optical diagnostics for medicine; (170.5660) Raman spectroscopy; (170.6935) Tissue characterization

Conflict of interest statement

F.L. is co-founder of ODS Medical Inc., a medical device company that seeks to commercialize the Raman spectroscopy system for real-time detection of tissue abnormalities.

Supplemental Content

Full text links

Icon for PubMed Central
Loading ...
Support Center