Raman spectroscopy based diagnosis of pancreatic ductal adenocarcinoma

Abstract 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 recognize...

Full description

Saved in:
Bibliographic Details
Main Authors: Gianmarco Lazzini, Raffele Gaeta, Luca Emanuele Pollina, Annalisa Comandatore, Niccolò Furbetta, Luca Morelli, Mario D’Acunto
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-98122-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849699616845463552
author Gianmarco Lazzini
Raffele Gaeta
Luca Emanuele Pollina
Annalisa Comandatore
Niccolò Furbetta
Luca Morelli
Mario D’Acunto
author_facet Gianmarco Lazzini
Raffele Gaeta
Luca Emanuele Pollina
Annalisa Comandatore
Niccolò Furbetta
Luca Morelli
Mario D’Acunto
author_sort Gianmarco Lazzini
collection DOAJ
description Abstract 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 $$\sim$$ ∼ 96%. Our findings clearly indicate that Raman spectroscopy could become a powerful spectral technique to support pathologists in improving pancreatic cancer diagnosis.
format Article
id doaj-art-0e428bafd47e4505b7d104ee74a34eec
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-0e428bafd47e4505b7d104ee74a34eec2025-08-20T03:18:32ZengNature PortfolioScientific Reports2045-23222025-04-0115111410.1038/s41598-025-98122-9Raman spectroscopy based diagnosis of pancreatic ductal adenocarcinomaGianmarco Lazzini0Raffele Gaeta1Luca Emanuele Pollina2Annalisa Comandatore3Niccolò Furbetta4Luca Morelli5Mario D’Acunto6CNR-IBF, Istituto di Biofisica Consiglio Nazionale delle RicercheSecond Division of Surgical Pathology, University Hospital of PisaSecond Division of Surgical Pathology, University Hospital of PisaGeneral Surgery Unit, Department of Translational Research and New Technologies in Medicine and Surgery, University of PisaDepartment of Surgery, Amsterdam UMC, Location Vrije UniversiteitDepartment of Surgery, Amsterdam UMC, Location Vrije UniversiteitCNR-IBF, Istituto di Biofisica Consiglio Nazionale delle RicercheAbstract 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 $$\sim$$ ∼ 96%. Our findings clearly indicate that Raman spectroscopy could become a powerful spectral technique to support pathologists in improving pancreatic cancer diagnosis.https://doi.org/10.1038/s41598-025-98122-9Raman spectroscopyPancreatic ductal adenocarcinomaGaussian Naive-BayesRandom forest classifierSPectral SELection
spellingShingle Gianmarco Lazzini
Raffele Gaeta
Luca Emanuele Pollina
Annalisa Comandatore
Niccolò Furbetta
Luca Morelli
Mario D’Acunto
Raman spectroscopy based diagnosis of pancreatic ductal adenocarcinoma
Scientific Reports
Raman spectroscopy
Pancreatic ductal adenocarcinoma
Gaussian Naive-Bayes
Random forest classifier
SPectral SELection
title Raman spectroscopy based diagnosis of pancreatic ductal adenocarcinoma
title_full Raman spectroscopy based diagnosis of pancreatic ductal adenocarcinoma
title_fullStr Raman spectroscopy based diagnosis of pancreatic ductal adenocarcinoma
title_full_unstemmed Raman spectroscopy based diagnosis of pancreatic ductal adenocarcinoma
title_short Raman spectroscopy based diagnosis of pancreatic ductal adenocarcinoma
title_sort raman spectroscopy based diagnosis of pancreatic ductal adenocarcinoma
topic Raman spectroscopy
Pancreatic ductal adenocarcinoma
Gaussian Naive-Bayes
Random forest classifier
SPectral SELection
url https://doi.org/10.1038/s41598-025-98122-9
work_keys_str_mv AT gianmarcolazzini ramanspectroscopybaseddiagnosisofpancreaticductaladenocarcinoma
AT raffelegaeta ramanspectroscopybaseddiagnosisofpancreaticductaladenocarcinoma
AT lucaemanuelepollina ramanspectroscopybaseddiagnosisofpancreaticductaladenocarcinoma
AT annalisacomandatore ramanspectroscopybaseddiagnosisofpancreaticductaladenocarcinoma
AT niccolofurbetta ramanspectroscopybaseddiagnosisofpancreaticductaladenocarcinoma
AT lucamorelli ramanspectroscopybaseddiagnosisofpancreaticductaladenocarcinoma
AT mariodacunto ramanspectroscopybaseddiagnosisofpancreaticductaladenocarcinoma