文献速递肿瘤 PET/CT

基于18F-FDG PET/CT影像组学预测最大径≤3 cm浸润性腺癌的脏层胸膜侵犯

Predicting visceral pleural invasion in invasive adenocarcinoma with a maximum diameter ≤ 3 cm based on 18F-FDG PET/CT radiomics.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2025-08-14

研究纳入590例最大径≤3 cm的浸润性腺癌患者,分为训练集364例、验证集1共156例和验证集2共70例,构建临床+PET/CT常规模型、CT及PET影像组学模型和联合模型。联合模型在训练集及两个验证集的AUC分别为0.824、0.835和0.787,高于常规模型及单一影像组学模型,部分差异有统计学意义。

要点

  • 联合模型在训练集AUC为0.824,高于常规模型0.734、CT影像组学模型0.790和PET影像组学模型0.748,差异有统计学意义(P<0.05)。
  • 验证集1中联合模型AUC为0.835,高于PET影像组学模型的0.747,差异有统计学意义(P=0.028)。
  • 验证集2中联合模型AUC为0.787,高于PET影像组学模型0.657(P=0.043)和CT影像组学模型0.694(P=0.025)。

核心结论

  • 基于PET/CT影像组学的联合模型是术前预测浸润性腺癌患者脏层胸膜侵犯状态的有效且无创的工具。

研究设计与样本

  • 研究纳入590例最大径≤3 cm的浸润性腺癌患者,分为训练集364例、验证集1共156例和验证集2共70例。
  • 采用逻辑回归基于临床和PET/CT影像特征构建常规模型,影像组学特征经组内相关系数、Pearson相关分析和最小绝对收缩和选择算子筛选后计算CT和PET rad-score,最终用多变量逻辑回归构建联合模型。

主要发现

  • 肿瘤类型(OR:3.258,P=0.012)、肿瘤与胸膜距离(OR:0.464,P=0.001)和最大标准化摄取值(SUVmax)(OR:1.109,P=0.002)用于构建常规模型。
  • 10个CT影像组学特征和6个PET影像组学特征分别用于建立CT和PET rad-score模型。
  • 训练集中联合模型AUC为0.824,高于常规模型0.734、CT rad-score模型0.790和PET rad-score模型0.748,Delong检验差异有统计学意义(P<0.05)。
  • 验证集1中联合模型AUC最高为0.835,与PET rad-score模型0.747差异有统计学意义(P=0.028)。
  • 验证集2中联合模型AUC最高为0.787,与PET rad-score模型0.657(P=0.043)和CT rad-score模型0.694(P=0.025)差异有统计学意义。

关键数值与推荐

  • 常规模型纳入肿瘤类型(OR:3.258,P=0.012)、肿瘤与胸膜距离(OR:0.464,P=0.001)和SUVmax(OR:1.109,P=0.002)。
  • 训练集中联合模型AUC 0.824 vs 常规模型0.734、CT rad-score模型0.790、PET rad-score模型0.748,差异有统计学意义(P<0.05)。
  • 验证集1中联合模型AUC 0.835 vs PET rad-score模型0.747,差异有统计学意义(P=0.028)。
  • 验证集2中联合模型AUC 0.787 vs PET rad-score模型0.657(P=0.043)、CT rad-score模型0.694(P=0.025),差异有统计学意义。

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

PURPOSE: To investigate the feasibility of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) radiomics in preoperative prediction of visceral pleural invasion (VPI) status in invasive adenocarcinoma (IAC) with a maximum diameter ≤ 3 cm. MATERIALS AND METHODS: A total of 590 IAC patients with a maximum diameter ≤ 3 cm were enrolled and divided into training set (n = 364), validations set 1 (n = 156) and validation set 2 (n = 70). A conventional model was built based on clinical and PET/CT imaging features by logistic regression. Radiomics features extracted from CT and PET images were screened using interclass correlation coefficients, Pearson correlation analysis and the least absolute shrinkage and selection operator. These selected features were used to calculate the CT and PET rad-scores. Finally, a combined model was constructed using multivariate logistic regression. RESULTS: Tumor type [odds ratio (OR): 3.258, P = 0.012], distance between tumor and pleura (OR: 0.464, P = 0.001), and maximum standardized uptake value (SUVmax) (OR: 1.109, P = 0.002) were used to construct the conventional model. Ten CT radiomics features and six PET radiomics features were used to establish the CT and PET rad-score models. The area under the curve (AUC) value of the combined model (0.824) was higher than conventional model (0.734), CT rad-score model (0.790) and PET rad-score model (0.748) in the training set, and the differences were statistically significant as tested by Delong test (P < 0.05). In the validation set 1 and validation set 2, the combined model exhibited the highest AUC values (0.835 and 0.787), and the difference between the combined model and PET rad-score model (validation set 1: 0.835 vs. 0.747, P = 0.028; validation set 2: 0.787 vs. 0.657, P = 0.043) and CT rad-score model (validation set 2: 0.787 vs. 0.694, P = 0.025) was statistically significant. CONCLUSION: The combined model based on PET/CT radiomics is an effective and non-invasive tool for preoperative predicting VPI status in IAC patients.

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

引用

  1. Dong Q, Sun J, You J, et al. Predicting visceral pleural invasion in invasive adenocarcinoma with a maximum diameter ≤ 3 cm based on 18F-FDG PET/CT radiomics. Eur J Nucl Med Mol Imaging. 2025. PMID: 40804299. doi:10.1007/s00259-025-07511-9

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。