上海口腔医学

上海口腔医学 ›› 2024, Vol. 33 ›› Issue (6): 608-616.doi: 10.19439/j.sjos.2024.06.007

• 论著 • 上一篇    下一篇

基于增强CT影像组学的机器学习模型预测舌鳞癌颈淋巴结转移的价值评价

孙恒祥1,2, 祝庆海1, 李怀奇1, 王晨星1*, 叶金海1,3*   

  1. 1.江苏省口腔疾病研究重点实验室, 南京医科大学附属口腔医院 口腔颌面外科, 江苏 南京 210029;
    2.亳州市人民医院 口腔科, 安徽 亳州 236800;
    3.复旦大学附属中山医院 口腔颌面外科, 上海 200032
  • 收稿日期:2024-08-11 修回日期:2024-09-24 出版日期:2024-12-25 发布日期:2025-01-07
  • 通讯作者: 叶金海,E-mail: yjh98001@163.com;王晨星,E-mail: doctorwcx@njmu.edu.cn。*共同通信作者
  • 作者简介:孙恒祥（1990-）,男,硕士研究生,E-mail: 819411082@qq.com
  • 基金资助:
    国家自然科学基金（82473200）;“江苏省卫生健康委科研项目”重点项目（K2023061）;江苏省老年健康科研项目（面上项目KLM2023019）

Clinical study of cervical lymph node metastasis in oral tongue squamous carcinoma by a machine learning model based on contrast-enhanced CT radiomics

SUN Heng-xiang1,2, ZHU Qing-hai1, LI Huai-qi1, WANG Chen-xing1, YE Jin-hai1,3   

  1. 1. Jiangsu Key Laboratory of Oral Diseases; Department of Oral and Maxillofacial Surgery, The Affiliated Stomatological Hospital of Nanjing Medical University. Nanjing 210029, Jiangsu Province;
    2. Department of Stomatology, Bozhou Peoples' Hospital. Bozhou 236800, Anhui Province;
    3. Department of Oral and Maxillofacial Surgery, Zhongshan Hospital, Fudan University. Shanghai 200032, China
  • Received:2024-08-11 Revised:2024-09-24 Online:2024-12-25 Published:2025-01-07

PDF (PC)

6

摘要： 目的: 探讨基于增强CT影像组学特征及临床参数构建的机器学习模型在预测舌鳞状细胞癌（tongue squamous cell carcinoma,TSCC）患者颈淋巴结转移中的价值。方法: 收集2015年1月—2022年7月在南京医科大学附属口腔医院接受治疗的TSCC患者75例,所有患者均具有完整临床数据、增强CT影像数据及术后淋巴结病理检查结果。将所有病例按8∶2的比例随机分配至训练组（n=60）和验证组（n=15）。从增强CT的静脉期影像数据中提取1 833个影像组学特征,采用相关系数筛选及LASSO方法进行特征筛选和降维,选出最优的影像组学特征组合。对筛选出的影像组学特征和临床特征使用多种机器学习算法模型（LR、KNN、Random Forest、Extra Trees、XGBoost和LightGBM）进行建模,以预测颈部淋巴结转移,并通过受试者工作特征（ROC）曲线和决策曲线分析（DCA）对模型的性能进行评估。采用SPSS 21.0软件包对数据进行统计学分析。结果: 通过对影像组学特征筛选和降维后,得到14个最优特征组合,并以此为基础建立了多种预测模型。其中,KNN模型在训练组和测试组中表现出较为均衡的拟合效果,AUC值分别为0.869和0.861。为了进一步提升模型的效能,将影像组学特征与患者临床特征进行融合建模,这一综合模型在训练组和测试组中的AUC值分别提高到0.893和0.880。DCA决策曲线显示,相比于单纯的影像组学模型,融合临床特征的影像组学-临床模型展现出更高的预测效果和临床应用价值。结论: 基于增强CT影像组学特征结合临床参数的预测模型,可有效估计TSCC患者的颈部淋巴结转移情况。此方法有助于对TSCC患者进行风险分层,优化临床决策,从而改善治疗策略和患者预后。

关键词: 舌鳞状细胞癌, 颈部淋巴结转移, 影像组学特征, 机器学习, 预测模型

Abstract: PURPOSE: To investigate the value of machine learning model based on enhanced CT imaging features and clinical parameters in predicting cervical lymph node metastasis in patients with tongue squamous cell carcinoma (TSCC). METHODS: A total of 75 patients with TSCC who were treated in the Affiliated Stomatology Hospital of Nanjing Medical University from January 2015 to July 2022 were collected. All patients had complete clinical data, enhanced CT image data and postoperative cervical lymph node pathological examination results. All cases were randomly assigned to the training group (n=60) and the validation group (n=15) in a ratio of 8∶2. A total of 1 833 radiomics features were extracted from the venous phase image data of enhanced CT. Correlation coefficient selection and LASSO method were used for feature selection and dimensionality reduction to select the optimal combination of radiomics features. Multiple machine learning algorithm models(LR, KNN, Random Forest, Extra Trees, XGBoost and LightGBM) were used to predict cervical lymph node metastasis on the selected radiomics and clinical features. The performance of the model was evaluated by receiver operating characteristic(ROC) curve and decision curve analysis(DCA). SPSS 21.0 software package was used for data analysis. RESULTS: After screening and dimensionality reduction, totally 14 optimal feature combinations were obtained, and a variety of prediction models were established based on them. Among them, the KNN model showed a more balanced fitting effect in the training group and the test group, with AUC values of 0.869 and 0.861, respectively. To further improve the efficiency of the model, we integrated imaging features with patient clinical features, and the AUC value of this comprehensive model was increased to 0.893 and 0.880 in the training group and the test group, respectively. The DCA decision curve showed that compared with the simple radiomic model, the image-clinical model with the integration of clinical features showed a higher predictive effect and clinical application value. CONCLUSIONS: The prediction model based on enhanced CT image omics features combined with clinical parameters can effectively estimate cervical lymph node metastasis in patients with TSCC. This approach facilitates risk stratification of patients with TSCC and optimizes clinical decisions to improve treatment strategies and patient outcomes.

Key words: Tongue squamous cell carcinoma, Cervical lymph node metastasis, Image omics features, Machine learning, Prediction model

中图分类号: