基于计算机断层扫描的影像组学列线图用于甲状腺乳头状微小癌术前中央区淋巴结转移预测的建立与验证
本研究在两家医院共452例甲状腺乳头状微小癌患者中建立并验证基于术前CT的影像组学列线图,用于预测中央区淋巴结转移。列线图结合影像组学评分与临床危险因素,在内外部测试集的AUC分别为0.800和0.803,高于影像组学评分和临床模型,也超过放射科医师的判读,并借助RNA测序数据探索了其潜在生物学基础。
要点
- 基于术前CT的影像组学列线图可无创预测甲状腺乳头状微小癌中央区淋巴结转移,内部测试集AUC为0.800,外部测试集AUC为0.803。
- 列线图整合了影像组学评分与性别、年龄、肿瘤直径、CT报告淋巴结状态等临床危险因素。
- 五种机器学习模型在内测试集AUC为0.606至0.730,均优于放射科医师对CT淋巴结状态的判读。
核心结论
- 该影像组学列线图在多机构数据中成功识别甲状腺乳头状微小癌的中央区淋巴结转移,诊断能力超过放射科医师,有潜力作为无创术前工具整合进临床决策。
研究设计与样本
- 研究纳入2012年1月至2020年12月两家医院的452例甲状腺乳头状微小癌患者,随机分为训练集339例、内部测试集86例、外部测试集27例,从原发灶术前CT图像提取影像组学特征。
诊断标准与关键数值
- 最终筛选25个影像组学特征训练机器学习模型;五种算法(K近邻、逻辑回归、线性支持向量机、高斯支持向量机、多项式支持向量机)在内测试集AUC为0.606至0.730;列线图内测试集AUC为0.800、外测试集AUC为0.803,均高于影像组学评分与临床模型。
临床应用与阅片要点
- 列线图结合影像组学评分与性别、年龄、肿瘤直径、CT报告淋巴结状态,可用于术前评估中央区淋巴结转移风险;其诊断能力超过放射科医师对CT淋巴结状态的判读。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: This study aims to develop and validate a computed tomography (CT)-based radiomics nomogram for pre-operatively predicting central lymph node metastasis (CLNM) in patients with papillary thyroid microcarcinoma (PTMC) and explore the underlying biological basis by using RNA sequencing data.
METHODS: This study trained 452 PTMC patients across two hospitals from January 2012 to December 2020. The sets were randomly divided into the training (n = 339), internal test (n = 86), external test (n = 27) sets. Radiomics features were extracted from primary lesion's pre-operative CT images for each patient. After screening for features, five algorithms such as K-nearest neighbor, logistics regression, linear-support vector machine (SVM), Gaussian SVM, and polynomial SVM were used to establish the radiomics models. The performance of these five algorithms was evaluated and compared directly to radiologist's interpretation (CT-reported lymph node status). The radiomics signature score (Rad-score) was generated using a linear combination of the selected features. By combining the clinical risk factors and Rad score, a radiomics nomogram was established and compared with Rad-score and clinical model. The performance of the nomogram was evaluated based on the receiver operating characteristic (ROC) curve, calibration curve, and the decision curve analysis (DCA). The potential biological basis of nomogram was revealed by performing genetic analysis based on the RNA sequencing data.
RESULTS: A total of 25 radiomic features were ultimately selected to train the machine learning models, and the five machine learning models outperformed the radiologists' interpretation by achieving area under the ROC curves (AUCs) ranging from 0.606 to 0.730 in the internal test set. By incorporating the Rad score and clinical risk factors (sex, age, tumor-diameter, and CT-reported lymph node status), this nomogram achieved AUCs of 0.800 and 0.803 in the internal and external test set, which were higher than that of the Rad-score and clinical model, respectively. Calibration curves and DCA also showed that the nomogram had good performance. As for the biological basis exploration, in patients predicted by nomogram to be PTC patients with CLMN, 109 genes were dysregulated, and some of them were associated with pathways and biological processes such as tumor angiogenesis.
CONCLUSION: This radiomics nomogram successfully identified CLNM on pretreatment imaging across multiple institutions, exceeding the diagnostic ability of radiologists and had the potential to be integrated into clinical decision making as a non-invasive pre-operative tool.
引用
- Mou Y, Han X, Li J, et al. Development and Validation of a Computed Tomography-Based Radiomics Nomogram for the Preoperative Prediction of Central Lymph Node Metastasis in Papillary Thyroid Microcarcinoma. Acad Radiol. 2023. PMID: 38071100. doi:10.1016/j.acra.2023.11.030
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。