EUVIMEDEUVIMED entdecken
Crossref

Machine Learning‐Enhanced Fiber‐Optic Raman Spectroscopy for In Situ Oral Cancer Classification

Xianchang Li iD, Shiding Zhang, Haijun Yang, Hao Wu, Kaiwen Yang, Xiang Zhu, Shi Zhou, Lifeng Zhang, Jiming Hu

Journal of Biophotonics · 2026

DOI: 10.1002/jbio.70373 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Biophotonics, 2026. Verfasst von Xianchang Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: Huzhou Key Laboratory of Green Energy Materials and Battery Cascade Utilization, School of Intelligent Manufacturing, Huzhou College, Huzhou, China. Hauptthemen laut MEDLINE: Spectrum Analysis, Raman, Mouth Neoplasms, Machine Learning, Fiber Optic Technology. Die Arbeit nennt 21 Literaturangaben. Gefördert von: the Scientific and Technological Development in Henan Province, the Key Scientific Research Universities Program Foundation of Henan Province, the Science and Technology Plan Project of Huzhou.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A portable Raman spectroscopy system was developed for in vivo diagnosis of oral squamous cell carcinoma (OSCC) in clinical settings. 46 patients with histopathologically confirmed OSCC were involved. The preprocessed dataset was used to train four supervised machine learning classifiers, support vector machine (SVM), k‐nearest neighbors (KNN), ensemble algorithms (EA), and linear discriminant analysis (LDA), under a stratified ten‐fold cross‐validation scheme. Comparative evaluation demonstrated that SVM achieved perfect classification accuracy (100%), outperforming LDA (96.6%), EA (90.7%), and KNN (83.3%). SVM performance was evaluated against retained PC count to assess robustness and generalizability. The area under the receiver operating characteristic curve (AUC‐ROC) remained above 80% with two PCs and increased to 96% when eight PCs were retained. These findings underscore the clinical translational potential of machine learning driven Raman spectroscopy, with high discriminative power and generalizability for oral cancer.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spectrum Analysis, RamanMouth NeoplasmsMachine LearningFiber Optic TechnologyHumansClassification AlgorithmsSupport Vector MachineDiscriminant AnalysisCarcinoma, Squamous Cell

Stichwörter der Autor:innen

fiber Raman spectroscopyin vivo diagnosismachine learningoral cancer

Autor:innen und Institutionen

  • Huzhou Key Laboratory of Green Energy Materials and Battery Cascade Utilization, School of Intelligent Manufacturing, Huzhou College, Huzhou, China.
  • Henan Joint International Research Laboratory of Nanocomposite Sensing Materials, Anyang Institute of Technology, Anyang, China.
  • The Affiliated Anyang Tumor Hospital, Henan University of Science and Technology, Anyang, China.
  • Department of Electrical and Electronic Engineering, Kyushu Institute of Technology, Kitakyushu, Fukuoka, Japan.
  • College of Chemistry and Molecular Sciences, Wuhan University, Wuhan, China.

ORCID-Profile: Xianchang Li

Förderung

  • the Scientific and Technological Development in Henan Province
  • the Key Scientific Research Universities Program Foundation of Henan Province
  • the Science and Technology Plan Project of Huzhou

Zitieren

APA

Li, X., Zhang, S., Yang, H., Wu, H., Yang, K., Zhu, X., Zhou, S., Zhang, L., & Hu, J. (2026). Machine Learning‐Enhanced Fiber‐Optic Raman Spectroscopy for In Situ Oral Cancer Classification. Journal of Biophotonics. https://doi.org/10.1002/jbio.70373

Vancouver

Li X, Zhang S, Yang H, Wu H, Yang K, Zhu X, et al. Machine Learning‐Enhanced Fiber‐Optic Raman Spectroscopy for In Situ Oral Cancer Classification. Journal of Biophotonics. 2026. doi:10.1002/jbio.70373

BibTeX
@article{Li2026,
  author = {Li, Xianchang and Zhang, Shiding and Yang, Haijun and Wu, Hao and Yang, Kaiwen and Zhu, Xiang and Zhou, Shi and Zhang, Lifeng and Hu, Jiming},
  title = {Machine Learning‐Enhanced Fiber‐Optic Raman Spectroscopy for In Situ Oral Cancer Classification},
  journal = {Journal of Biophotonics},
  year = {2026},
  doi = {10.1002/jbio.70373}
}
Kostenlos starten →