文献速递肿瘤 PET/CT

利用常规可获取的[18F]FDG-PET/CT参数改进非小细胞肺癌纵隔淋巴结转移预测的机器学习工具

A machine learning tool to improve prediction of mediastinal lymph node metastases in non-small cell lung cancer using routinely obtainable [18F]FDG-PET/CT parameters.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2023-02-23

本研究基于491例非小细胞肺癌患者的治疗前[18F]FDG-PET/CT数据,评估机器学习模型能否优于标准视觉评估来提高纵隔淋巴结分期准确性。梯度提升分类器在测试队列的AUC为0.91(95%CI 0.87-0.94),验证队列AUC为0.94(95%CI 0.89-0.98),在约90%目标灵敏度下准确率显著高于常规视觉标准。

要点

  • 梯度提升分类器测试AUC 0.91(95%CI 0.87-0.94),验证AUC 0.94(95%CI 0.89-0.98)。
  • 约90%灵敏度下,模型测试/验证准确率0.78/0.87,高于纵隔淋巴结摄取>纵隔标准(0.7/0.75)。
  • 模型准确率亦高于联合PET/CT标准(PET阳性或淋巴结短径>10 mm;0.68/0.75)。

核心结论

  • 基于[18F]FDG-PET/CT常规可获取变量的机器学习模型,较现有视觉评估标准提高了纵隔淋巴结分期准确性。
  • 作者已提供实现该模型的网络应用程序。

研究设计与样本

  • 单中心回顾性分析,纳入491例连续的非小细胞肺癌患者治疗前[18F]FDG-PET/CT。
  • 训练+测试队列385例使用模拟PET/CT扫描仪,验证队列106例使用数字扫描仪。
  • 收集40个临床变量、肿瘤特征和图像变量(如原发肿瘤和淋巴结SUVmax及大小)。
  • 比较不同特征选择和分类方法组合,用于区分N0/1与N2/3病变。
  • 采用十折嵌套交叉验证得出十个测试折的平均ROC曲线下面积(“测试AUC”)及验证队列AUC;参考标准为多学科共识最终N分期(N2/3淋巴结96%有组织学结果)。

主要发现

  • N2/3病变见于190例患者(39%);训练+测试队列37%,验证队列46%(p=0.09)。
  • 最终模型为含10个特征的梯度提升分类器(GBM),测试AUC 0.91(95%CI 0.87-0.94),验证AUC 0.94(95%CI 0.89-0.98)。
  • 在约90%目标灵敏度下,GBM测试/验证准确率为0.78/0.87,显著高于“纵隔淋巴结摄取>纵隔”标准的0.7/0.75(各p<0.05)。
  • GBM准确率亦显著高于联合PET/CT标准(PET阳性或淋巴结短轴直径>10 mm)的0.68/0.75(各p<0.001)。
  • 两台扫描仪间PET图像协调化影响SUVmax和淋巴结视觉评估,但未降低GBM的AUC。

关键数值与推荐

  • 最终模型为含10个特征的梯度提升分类器,基于测试AUC 0.91(95%CI 0.87-0.94)选出。
  • 在约90%目标灵敏度下,GBM测试/验证准确率为0.78/0.87。
  • 对照标准“纵隔淋巴结摄取>纵隔”测试/验证准确率为0.7/0.75(各p<0.05)。
  • 对照联合PET/CT标准(PET阳性或淋巴结短轴直径>10 mm)测试/验证准确率为0.68/0.75(各p<0.001)。

临床怎么用

  • 原文未据此给出推荐。

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)。

原文

BACKGROUND: In patients with non-small cell lung cancer (NSCLC), accuracy of [18F]FDG-PET/CT for pretherapeutic lymph node (LN) staging is limited by false positive findings. Our aim was to evaluate machine learning with routinely obtainable variables to improve accuracy over standard visual image assessment. METHODS: Monocentric retrospective analysis of pretherapeutic [18F]FDG-PET/CT in 491 consecutive patients with NSCLC using an analog PET/CT scanner (training + test cohort, n = 385) or digital scanner (validation, n = 106). Forty clinical variables, tumor characteristics, and image variables (e.g., primary tumor and LN SUVmax and size) were collected. Different combinations of machine learning methods for feature selection and classification of N0/1 vs. N2/3 disease were compared. Ten-fold nested cross-validation was used to derive the mean area under the ROC curve of the ten test folds ("test AUC") and AUC in the validation cohort. Reference standard was the final N stage from interdisciplinary consensus (histological results for N2/3 LNs in 96%). RESULTS: N2/3 disease was present in 190 patients (39%; training + test, 37%; validation, 46%; p = 0.09). A gradient boosting classifier (GBM) with 10 features was selected as the final model based on test AUC of 0.91 (95% confidence interval, 0.87-0.94). Validation AUC was 0.94 (0.89-0.98). At a target sensitivity of approx. 90%, test/validation accuracy of the GBM was 0.78/0.87. This was significantly higher than the accuracy based on "mediastinal LN uptake > mediastinum" (0.7/0.75; each p < 0.05) or combined PET/CT criteria (PET positive and/or LN short axis diameter > 10 mm; 0.68/0.75; each p < 0.001). Harmonization of PET images between the two scanners affected SUVmax and visual assessment of the LNs but did not diminish the AUC of the GBM. CONCLUSIONS: A machine learning model based on routinely available variables from [18F]FDG-PET/CT improved accuracy in mediastinal LN staging compared to established visual assessment criteria. A web application implementing this model was made available.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Rogasch JMM, Michaels L, Baumgärtner GL, et al. A machine learning tool to improve prediction of mediastinal lymph node metastases in non-small cell lung cancer using routinely obtainable [18F]FDG-PET/CT parameters. Eur J Nucl Med Mol Imaging. 2023. PMID: 36820890. doi:10.1007/s00259-023-06145-z

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。