Yu Xin-Ying, Chen Jian, Li Lian-Yu, Chen Feng-En, He Qiang
Department of Gastroenterology, Beijing Tiantan Hospital, Capital Medical University, Beijing 100071, China.
Department of Cancer Prevention Center, Feicheng People's Hospital, Feicheng 271000, Shandong Province, China.
World J Gastroenterol. 2025 Apr 14;31(14):104280. doi: 10.3748/wjg.v31.i14.104280.
Esophageal squamous cell carcinoma is a major histological subtype of esophageal cancer. Many molecular genetic changes are associated with its occurrence. Raman spectroscopy has become a new method for the early diagnosis of tumors because it can reflect the structures of substances and their changes at the molecular level.
To detect alterations in Raman spectral information across different stages of esophageal neoplasia.
Different grades of esophageal lesions were collected, and a total of 360 groups of Raman spectrum data were collected. A 1D-transformer network model was proposed to handle the task of classifying the spectral data of esophageal squamous cell carcinoma. In addition, a deep learning model was applied to visualize the Raman spectral data and interpret their molecular characteristics.
A comparison among Raman spectral data with different pathological grades and a visual analysis revealed that the Raman peaks with significant differences were concentrated mainly at 1095 cm (DNA, symmetric PO, and stretching vibration), 1132 cm (cytochrome c), 1171 cm (acetoacetate), 1216 cm (amide III), and 1315 cm (glycerol). A comparison among the training results of different models revealed that the 1D-transformer network performed best. A 93.30% accuracy value, a 96.65% specificity value, a 93.30% sensitivity value, and a 93.17% F1 score were achieved.
Raman spectroscopy revealed significantly different waveforms for the different stages of esophageal neoplasia. The combination of Raman spectroscopy and deep learning methods could significantly improve the accuracy of classification.
食管鳞状细胞癌是食管癌的主要组织学亚型。许多分子遗传学改变与其发生相关。拉曼光谱能够在分子水平反映物质结构及其变化，已成为肿瘤早期诊断的新方法。
检测食管肿瘤不同阶段拉曼光谱信息的变化。
收集不同分级的食管病变组织，共采集360组拉曼光谱数据。提出一种一维变压器网络模型来处理食管鳞状细胞癌光谱数据的分类任务。此外，应用深度学习模型对拉曼光谱数据进行可视化并解读其分子特征。
不同病理分级的拉曼光谱数据比较及可视化分析显示，差异显著的拉曼峰主要集中在1095 cm（DNA，对称PO，伸缩振动）、1132 cm（细胞色素c）、1,171 cm（乙酰乙酸）、1216 cm（酰胺III）和1315 cm（甘油）处。不同模型训练结果比较显示，一维变压器网络表现最佳，准确率为93.30%，特异性为96.65%，敏感性为93.30%，F1评分为93.17%。
拉曼光谱显示食管肿瘤不同阶段的波形存在显著差异。拉曼光谱与深度学习方法相结合可显著提高分类准确率。
