文献速递甲状腺与浅表头颈US

用于甲状腺乳头状癌术前预测中央区淋巴结转移的临床-影像组学列线图的开发与验证

Development and Validation of Clinical-Radiomics Nomogram for Preoperative Prediction of Central Lymph Node Metastasis in Papillary Thyroid Carcinoma.
PubMed 文献 · Acad Radiol · 2024-01-16

本研究纳入2022年1月至2023年1月间1069例甲状腺乳头状癌患者,随机分为训练队列748例和验证队列321例,从原始灰阶超声图像提取129个影像组学特征,结合影像组学标签与临床危险因素构建临床-影像组学列线图。列线图包含年龄、肿瘤大小、边缘、侧方淋巴结转移和影像组学标签五个预测因子,训练队列AUC为0.960(95%CI 0.947-0.972),验证队列AUC为0.925(95%CI 0.895-0.955),判别能力优于临床标签、影像组学标签和常规超声模型。

要点

  • 临床-影像组学列线图包含年龄、肿瘤大小、边缘、侧方淋巴结转移和影像组学标签五个预测因子。
  • 训练队列AUC 0.960(95%CI 0.947-0.972),验证队列AUC 0.925(95%CI 0.895-0.955)。
  • 列线图判别能力优于临床标签、影像组学标签和常规超声模型。

核心结论

  • 整合影像组学标签与关键临床特征的临床-影像组学列线图可有效预测甲状腺乳头状癌患者的中央区淋巴结转移。

研究设计与样本

  • 回顾性研究,纳入1069例甲状腺乳头状癌患者,随机分为训练队列748例和验证队列321例,从原始灰阶超声图像提取129个影像组学特征,采用最小冗余最大相关性和最小绝对收缩与选择算子回归筛选特征并计算影像组学标签,结合影像组学标签与临床危险因素用多变量逻辑回归构建列线图。

诊断标准与关键数值

  • 临床-影像组学列线图训练队列AUC 0.960(95%CI 0.947-0.972),验证队列AUC 0.925(95%CI 0.895-0.955);列线图判别能力优于临床标签、影像组学标签和常规超声模型。

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

BACKGROUND: This investigation sought to create and verify a nomogram utilizing ultrasound radiomics and crucial clinical features to preoperatively identify central lymph node metastasis (CLNM) in patients diagnosed with papillary thyroid carcinoma (PTC).

METHODS: We enrolled 1069 patients with PTC between January 2022 and January 2023. All patients were randomly divided into a training cohort (n = 748) and a validation cohort (n = 321). We extracted 129 radiomics features from the original gray-scale ultrasound image. Then minimum Redundancy-Maximum Relevance and Least Absolute Shrinkage and Selection Operator regression were used to select the CLNM-related features and calculate the radiomic signature. Incorporating the radiomic signature and clinical risk factors, a clinical-radiomics nomogram was constructed using multivariable logistic regression. The predictive performance of clinical-radiomics nomogram was evaluated by calibration, discrimination, and clinical utility in the training and validation cohorts.

RESULTS: The clinical-radiomics nomogram which consisted of five predictors (age, tumor size, margin, lateral lymph node metastasis, and radiomics signature), showed good calibration and discrimination in both the training (AUC 0.960; 95% CI, 0.947-0.972) and the validation (AUC 0.925; 95% CI, 0.895-0.955) cohorts. Discrimination of the clinical-radiomics nomogram showed better discriminative ability than the clinical signature, radiomics signature, and conventional ultrasound model in both the training and validation cohorts. Decision curve analysis showed satisfactory clinical utility of the nomogram.

CONCLUSION: The clinical-radiomics nomogram incorporating radiomic signature and key clinical features was efficacious in predicting CLNM in PTC patients.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Feng JW, Liu SQ, Qi GF, et al. Development and Validation of Clinical-Radiomics Nomogram for Preoperative Prediction of Central Lymph Node Metastasis in Papillary Thyroid Carcinoma. Acad Radiol. 2024. PMID: 38233259. doi:10.1016/j.acra.2023.12.008

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。