Handheld macroscopic Raman spectroscopy imaging instrument for machine-learning-based molecular tissue margins characterization

• Published in: Journal of biomedical optics Vol. 26; no. 2; p. 022911
• Main Authors: Daoust, François, Nguyen, Tien, Orsini, Patrick, Bismuth, Jacques, de Denus-Baillargeon, Marie-Maude, Veilleux, Israel, Wetter, Alexandre, Mckoy, Philippe, Dicaire, Isabelle, Massabki, Maroun, Petrecca, Kevin, Leblond, Frédéric
• Format: Journal Article
• Language: English
• Published: United States Society of Photo-Optical Instrumentation Engineers 01.02.2021; S P I E - International Society for
• Subjects: Brain cancer; Breast cancer; Cancer; Histology; In vivo methods and tests; Lasers; Learning algorithms; Luminescence quenching; Machine learning; Magnetic resonance imaging; Medical imaging; Microscopes; Muscles; Neuroimaging; Prostate; Raman spectroscopy; Special Series on Artificial Intelligence and Machine Learning in Biomedical Optics; Spectroscopy; Spectrum analysis; Support vector machines; Surgeons; Surgery; Surgical outcomes; Tissues; Tomography; Tumors; Workflow; macroscopic imaging; imaging systems; Raman spectroscopy; machine learning; surgical guidance
• ISSN: 1083-3668; 1560-2281
• DOI: 10.1117/1.JBO.26.2.022911

Significance: Raman spectroscopy has been developed for surgical guidance applications interrogating live tissue during tumor resection procedures to detect molecular contrast consistent with cancer pathophysiological changes. To date, the vibrational spectroscopy systems developed for medical applications include single-point measurement probes and intraoperative microscopes. There is a need to develop systems with larger fields of view (FOVs) for rapid intraoperative cancer margin detection during surgery. Aim: We design a handheld macroscopic Raman imaging system for in vivo tissue margin characterization and test its performance in a model system. Approach: The system is made of a sterilizable line scanner employing a coherent fiber bundle for relaying excitation light from a 785-nm laser to the tissue. A second coherent fiber bundle is used for hyperspectral detection of the fingerprint Raman signal over an area of 1  cm2. Machine learning classifiers were trained and validated on porcine adipose and muscle tissue. Results: Porcine adipose versus muscle margin detection was validated ex vivo with an accuracy of 99% over the FOV of 95  mm2 in ∼3  min using a support vector machine. Conclusions: This system is the first large FOV Raman imaging system designed to be integrated in the workflow of surgical cancer resection. It will be further improved with the aim of discriminating brain cancer in a clinically acceptable timeframe during glioma surgery.