Combined information from Raman spectroscopy and optical coherence tomography for enhanced diagnostic accuracy in tissue discrimination

Abstract

Optical spectroscopy and imaging methods have proved to have potential to discriminate between normal and abnormal tissue types through minimally invasive procedures. Raman spectroscopy and Optical Coherence Tomography (OCT) provides chemical and morphological information of tissues respectively, which are complementary to each other. When used individually they might not be able to obtain high enough sensitivity and specificity that is clinically relevant. In this study we combined Raman spectroscopy information with information obtained from OCT to enhance the sensitivity and specificity in discriminating between Colonic Adenocarcinoma from Normal Colon. OCT being an imaging technique, the information from this technique is conventionally analyzed qualitatively. To combine with Raman spectroscopy information, it was essential to quantify the morphological information obtained from OCT. Texture analysis was used to extract information from OCT images, which in-turn was combined with the information obtained from Raman spectroscopy. The sensitivity and specificity of the classifier was estimated using leave one out cross validation (LOOCV) method where support vector machine (SVM) was used for binary classification of the tissues. The sensitivity obtained using Raman spectroscopy and OCT individually was 89% and 78% respectively and the specificity was 77% and 74% respectively. Combining the information derived using the two techniques increased both sensitivity and specificity to 94% demonstrating that combining complementary optical information enhances diagnostic accuracy. These results demonstrate that a multimodal approach using Raman-OCT would be able to enhance the diagnostic accuracy for identifying normal and cancerous tissue types.