Li Jiaqi, Weng Jiuling, Du Wen, Gao Min, Cui Haobo, Jiang Pingping, Wang Haihui, Peng Xin
Department of Oral and Maxillofacial Surgery, Peking University School and Hospital of Stomatology, Beijing, China.
Laboratory of Haihui Data Analysis, School of Mathematical Sciences, Beihang University, Beijing, China.
J Stomatol Oral Maxillofac Surg. 2025 Feb;126(1):102030. doi: 10.1016/j.jormas.2024.102030. Epub 2024 Sep 2.
This study aims to develop a machine learning diagnostic model for parotid gland tumors based on preoperative contrast-enhanced CT imaging features to assist in clinical decision-making.
Clinical data and contrast-enhanced CT images of 144 patients with parotid gland tumors from the Peking University School of Stomatology Hospital, collected from January 2019 to December 2022, were gathered. The 3D slicer software was utilized to accurately annotate the tumor regions, followed by exploring the correlation between multiple preoperative contrast-enhanced CT imaging features and the benign or malignant nature of the tumor, as well as the type of benign tumor. A prediction model was constructed using the k-nearest neighbors (KNN) algorithm.
Through feature selection, four key features-morphology, adjacent structure invasion, boundary, and suspicious cervical lymph node metastasis-were identified as crucial in preoperative discrimination between benign and malignant tumors. The KNN prediction model achieved an accuracy rate of 94.44 %. Additionally, six features including arterial phase CT value, age, delayed phase CT value, pre-contrast CT value, venous phase CT value, and gender, were also significant in the classification of benign tumors, with a KNN prediction model accuracy of 95.24 %.
The machine learning model based on preoperative contrast-enhanced CT imaging features can effectively discriminate between benign and malignant parotid gland tumors and classify benign tumors, providing valuable reference information for clinicians.
本研究旨在基于术前增强CT影像特征开发一种用于腮腺肿瘤的机器学习诊断模型，以辅助临床决策。
收集了2019年1月至2022年12月期间北京大学口腔医学院附属口腔医院144例腮腺肿瘤患者的临床资料和增强CT图像。利用3D Slicer软件精确标注肿瘤区域，随后探究多个术前增强CT影像特征与肿瘤良恶性以及良性肿瘤类型之间的相关性。使用k近邻（KNN）算法构建预测模型。
通过特征选择，确定了形态、邻近结构侵犯、边界和可疑颈部淋巴结转移这四个关键特征在术前鉴别良恶性肿瘤中至关重要。KNN预测模型的准确率达到94.44%。此外，动脉期CT值、年龄、延迟期CT值、平扫CT值、静脉期CT值和性别这六个特征在良性肿瘤分类中也具有显著性，KNN预测模型的准确率为95.24%。
基于术前增强CT影像特征的机器学习模型能够有效鉴别腮腺肿瘤的良恶性并对良性肿瘤进行分类，为临床医生提供有价值的参考信息。
