Zhongxu Li ¹ Xiaobo Dai ¹ Zhixin Li ¹ Zhenxin Wu ¹ Lili Xue ² Yi Li ¹ Bing Yan ^1*

• ¹ West China School of Stomatology, Sichuan University, Chengdu, China
• ² Department of Stomatology, First Affiliated Hospital of Xiamen University, Xiamen, Fujian Province, China

Purpose: Accurate assessment of the surgical margins of tongue squamous cell carcinoma (TSCC), especially the deep muscle tissue, can help to completely remove the cancer cells and thus minimize the risk of recurrence. This study was to develop a classification model that classify TSCC and normal tissues, in order to aid in the rapid and accurate intraoperative assessment of TSCC surgical deep muscle tissue margins. Materials and methods: The study obtained 240 Raman spectra from 60 sections (30 TSCC and 30 normal) from 15 patients diagnosed with TSCC. The classification model based on the analysis of Raman spectral data was developed, utilizing principal component analysis (PCA) and linear discriminant analysis (LDA) for the diagnosis and classification of TSCC. The leave-one-out cross validation was employed to estimate and evaluate the prediction performance model. Results: This approach effectively classified TSCC tissue and normal muscle tissue, achieving an accuracy of exceeding 90%. The Raman analysis showed that TSCC tissues contained significantly higher levels of proteins, lipids, and nucleic acids compared to the adjacent normal tissues. In addition, we have also explored the potential of Raman spectroscopy in classifying different histological grades of TSCC. Conclusions: The PCA-LDA tissue classification model based on Raman spectroscopy exhibited good accuracy, which could help to aid in identifying tumor-free margins during surgical interventions and present a promising avenue for the development of rapid and accurate intraoperative techniques.