Raman spectroscopy based diagnosis of pancreatic ductal adenocarcinoma.

Pancreatic ductal adenocarcinoma is currently the 12th most frequent form of cancer worldwide, characterized by a very low 5-year survival rate. Although several therapeutic approaches have been proposed to treat this form of pancreatic cancer, surgical resection is still commonly recognized as the most effective technique to slow down the disease progression and maximize the 5-year survival rate. Analogously, one critical issue is the ability of current diagnostic methodologies to distinguish between irregular growth of the tumor mass and surrounding inflammatory tissues. In this pilot study, we apply Raman spectroscopy, supported by a series of machine learning techniques, to distinguish among healthy, pancreatitis and ductal adenocarcinoma tissues, respectively, for a total of 15 cases. Raman spectroscopy is a label-free, non-destructive spectral technique exploiting Raman scattering. In turn, by applying a combination of principal component analysis and random forest classifier on the Raman spectral dataset, we achieved a maximum accuracy of up to 96%. Our findings clearly indicate that Raman spectroscopy could become a powerful spectral technique to support pathologists in improving pancreatic cancer diagnosis.