文献速递头颈甲状腺与浅表CT

基于机器学习的CT影像组学无创预测甲状腺微小乳头状癌中央区淋巴结转移:一项多中心研究

Non-invasive prediction of central lymph node metastasis in papillary thyroid microcarcinoma with machine learning-based CT radiomics: a multicentre study.
PubMed 文献 · Br J Radiol · 2026-01-01

本研究回顾性纳入3个医疗中心921例病理证实为甲状腺微小乳头状癌的患者,提取CT影像组学特征并采用5种机器学习分类器建模,XGBoost分类器表现最佳(验证集平均AUC 0.756)。将XGBoost放射组学评分与年龄、性别联合构建的列线图模型在训练集、内部验证集、外部测试集1和外部测试集2的AUC分别为0.847、0.773、0.807和0.746,均优于临床模型。

要点

  • 基于XGBoost的CT影像组学列线图可用于术前无创预测甲状腺微小乳头状癌中央区淋巴结转移。
  • 列线图模型在4个数据集中的AUC均高于临床模型,且临床获益更优。
  • 全部921例中35.18%(324/921)为中央区淋巴结转移阳性。

核心结论

  • 基于XGBoost分类器的列线图模型表现良好,为甲状腺微小乳头状癌患者中央区淋巴结转移的无创诊断提供了潜在方法。

研究设计与样本

  • 回顾性多中心研究,纳入3个医疗中心921例病理证实为甲状腺微小乳头状癌的患者,分为训练集、内部验证集、外部测试集1和外部测试集2;从CT图像提取甲状腺肿瘤影像组学特征,采用5种机器学习分类器建模。

诊断标准与关键数值

  • XGBoost分类器表现最佳,验证集平均AUC为0.756;列线图模型(XGBoost放射组学评分+年龄+性别)训练集AUC 0.847(0.809-0.879),内部验证集AUC 0.773(0.682-0.847),外部测试集1 AUC 0.807(0.757-0.852),外部测试集2 AUC 0.746(0.645-0.830);临床模型对应AUC分别为0.706(0.660-0.748)、0.671(0.575-0.758)、0.639(0.580-0.695)、0.608(0.502-0.707)。

临床应用与阅片要点

  • 作者认为该列线图模型为术前准确评估中央区淋巴结转移状态提供了无创且易用的潜在替代方法。

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: This study aimed to develop and validate a machine learning-based computed tomography (CT) radiomics method to preoperatively predict the presence of central lymph node metastasis (CLNM) in patients with papillary thyroid microcarcinoma (PTMC).

METHODS: A total of 921 patients with histopathologically proven PTMC from 3 medical centres were included in this retrospective study and divided into training, internal validation, external test 1, and external test 2 sets. Radiomics features of thyroid tumours were extracted from CT images and selected for dimensional reduction. Five machine learning classifiers were applied, and the best classifier was selected to calculate radiomics scores (rad-scores). Then, the rad-scores and clinical factors were combined to construct a nomogram model.

RESULTS: In the 4 sets, 35.18% (324/921) patients were CLNM+. The XGBoost classifier showed the best performance, with the highest average area under the curve (AUC) of 0.756 in the validation set. The nomogram model incorporating XGBoost-based rad-scores with age and sex showed better performance than the clinical model in the training [AUC: 0.847 (0.809-0.879) vs. 0.706 (0.660-0.748)], internal validation [AUC: 0.773 (0.682-0.847) vs. 0.671 (0.575-0.758)], external test 1 [AUC: 0.807 (0.757-0.852) vs. 0.639 (0.580-0.695)], and external test 2 [AUC: 0.746 (0.645-0.830) vs. 0.608 (0.502-0.707)] sets. Furthermore, the nomogram showed better clinical benefit than the clinical and radiomics models.

CONCLUSIONS: The nomogram model based on the XGBoost classifier exhibited favourable performance. This model provides a potential approach for the non-invasive diagnosis of CLNM in patients with PTMC.

ADVANCES IN KNOWLEDGE: This study developed a potential surrogate of preoperative accurate evaluation of CLNM status, which is non-invasive and easy-to-use.

来源:Br J Radiol,查看原文。版权归原作者所有。

引用

  1. Cheng F, Lin G, Chen W, et al. Non-invasive prediction of central lymph node metastasis in papillary thyroid microcarcinoma with machine learning-based CT radiomics: a multicentre study. Br J Radiol. 2026. PMID: 41065404. doi:10.1093/bjr/tqaf247

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。