文献速递甲状腺与浅表头颈US

基于超声影像组学与机器学习的模型用于术前鉴别滤泡性甲状腺肿瘤

Model Based on Ultrasound Radiomics and Machine Learning to Preoperative Differentiation of Follicular Thyroid Neoplasm.
PubMed 文献 · J Ultrasound Med · 2024-11-18

回顾性分析3家机构2017年1月至2023年12月389例术后诊断为滤泡性甲状腺癌或滤泡性甲状腺腺瘤患者的临床资料与超声图像,以随机森林影像组学模型鉴别二者,训练、验证、测试队列AUC分别为0.880、0.871、0.821,联合临床特征的组合模型AUC分别为0.883、0.874、0.876。

要点

  • 随机森林影像组学模型在训练、验证、测试队列鉴别滤泡性甲状腺癌与腺瘤的AUC分别为0.880、0.871、0.821。
  • 组合模型(影像组学+临床特征)AUC在训练、验证、测试队列分别为0.883、0.874、0.876,优于临床模型和影像组学模型。
  • 校准曲线显示组合模型一致性良好,决策曲线显示组合模型总体临床获益最高。

核心结论

  • 基于随机森林的超声影像组学模型可用于鉴别滤泡性甲状腺癌与滤泡性甲状腺腺瘤。
  • 组合模型是术前无创识别滤泡性甲状腺癌与腺瘤的直观工具。

研究设计与样本

  • 回顾性分析3家机构2017年1月至2023年12月术后诊断为滤泡性甲状腺癌或滤泡性甲状腺腺瘤的389例患者的临床资料和超声图像。
  • 本院患者按7:3比例随机分为训练队列和验证队列,外部测试队列由其他2家医院收集的数据组成。
  • 采用不同机器学习分类器基于影像组学特征建立模型,并将影像组学特征与临床特征结合建立组合模型并绘制列线图。
  • 通过受试者工作特征曲线下面积(AUC)、校准曲线和决策曲线评估模型性能。

诊断标准与关键数值

  • 基于随机森林的影像组学模型鉴别滤泡性甲状腺癌与滤泡性甲状腺腺瘤的AUC在训练队列为0.880(95%CI:0.8290-0.9308),验证队列为0.871(95%CI:0.7690-0.9734),测试队列为0.821(95%CI:0.7036-0.9389)。
  • 组合模型AUC在训练队列为0.883(95%CI:0.8359-0.9295),验证队列为0.874(95%CI:0.7873-0.9615),测试队列为0.876(95%CI:0.7809-0.9714)。
  • 校准曲线提示组合模型一致性良好。
  • 决策曲线显示组合模型总体临床获益最高。

临床应用与阅片要点

  • 作者认为基于随机森林的超声影像组学模型可用于鉴别滤泡性甲状腺癌与滤泡性甲状腺腺瘤。
  • 作者认为组合模型是术前无创识别滤泡性甲状腺癌与腺瘤的直观工具。

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

OBJECTIVES: To evaluate the value of radiomics based on ultrasonography in differentiating follicular thyroid carcinoma (FTC) and follicular thyroid adenoma (FTA) and construct a tool for preoperative noninvasive predicting FTC and FTA.

METHODS: The clinical data and ultrasound images of 389 patients diagnosed with FTC or FTA postoperatively were retrospectively analyzed at 3 institutions from January 2017 to December 2023. Patients in our hospital were randomly assigned in a 7:3 ratio to training cohort and validation cohort. External test cohort consisted of data collected from other 2 hospitals. Radiomics features were used to develop models based on different machine learning classifiers. A combined model was developed combining radiomics features with clinical characteristics and a nomogram was depicted. The performance of the models was assessed by area under the receiver operating characteristic curve (AUC), calibration curve and decision curve.

RESULTS: Radiomics model based on random forest showed best performance in discriminating FTC and FTA, with AUCs 0.880 (95% confidence interval [CI]: 0.8290-0.9308), 0.871 (95% CI: 0.7690-0.9734), and 0.821 (95% CI: 0.7036-0.9389) in training, validation, and test cohort, respectively. The combined model presented better efficacy comparing with clinical model and radiomics model, with AUCs 0.883 (95% CI: 0.8359-0.9295), 0.874 (95% CI: 0.7873-0.9615), and 0.876 (0.7809-0.9714) in training, validation, and test cohort, respectively. The calibration curves suggested good consistency and decision curves showed the highest overall clinical benefit for the combined model.

CONCLUSIONS: Ultrasound radiomics model based on random forest is feasible to differentiate FTC and FTA, and the combined model is an intuitively noninvasive tool for FTC and FTA preoperative identification.

来源:J Ultrasound Med,查看原文。版权归原作者所有。

引用

  1. Deng Y, Zeng Q, Zhao Y, et al. Model Based on Ultrasound Radiomics and Machine Learning to Preoperative Differentiation of Follicular Thyroid Neoplasm. J Ultrasound Med. 2024. PMID: 39555618. doi:10.1002/jum.16620

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。