文献速递胸部肿瘤放疗放疗物理与技术

人工智能筛查的间质性肺病与局部晚期非小细胞肺癌放射性肺炎的关联

Association of artificial intelligence-screened interstitial lung disease with radiation pneumonitis in locally advanced non-small cell lung cancer.
PubMed 文献 · Radiother Oncol · 2025-09-13

该回顾性研究纳入698例2006至2021年接受根治性放疗的局部晚期非小细胞肺癌患者,用卷积神经网络从计划CT识别放射学间质性肺病。23%患者为AI-ILD阳性;多因素分析中AI-ILD状态和评分是≥3级放射性肺炎的显著预测因子,真性放射学ILD者≥3级放射性肺炎达25%、5级达7%。

要点

  • AI-ILD阳性与≥3级放射性肺炎风险升高独立相关(OR 2.15)。
  • 真性放射学ILD患者≥3级放射性肺炎25%、5级7%。
  • AI-ILD阳性与阴性者中位总生存3.6年与2.3年无显著差异。

核心结论

  • AI-ILD算法可识别≥3级放射性肺炎风险显著升高的局部晚期非小细胞肺癌放疗患者。

研究设计与样本

  • 回顾性评估2006至2021年在本机构接受根治性放疗的全部局部晚期非小细胞肺癌患者,共698例。
  • 用既往开发的卷积神经网络基于计划CT图像识别放射学ILD,AI筛查阳性者由胸部放射科医生复核确认真性放射学ILD。
  • 采用单因素和多因素logistic回归及Kaplan-Meier生存分析评估算法输出、临床和剂量学变量与≥3级放射性肺炎及死亡的关系。

主要发现

  • 698例中放射性肺炎0、1、2、3、4、5级分别占51%、27%、17%、4.4%、0.14%、0.57%。
  • 23%患者被分类为AI-ILD阳性。
  • 多因素分析中仅AI-ILD状态(OR 2.15,p=0.03)和AI-ILD评分(OR 35.27,p<0.01)是≥3级放射性肺炎的显著预测因子。
  • AI-ILD阴性患者中位总生存3.6年,AI-ILD阳性患者2.3年,差异无统计学意义。
  • 真性放射学ILD患者严重毒性发生率更高,≥3级放射性肺炎25%、5级放射性肺炎7%;多因素分析中真性放射学ILD与≥3级放射性肺炎风险升高相关(OR 5.42,p<0.01)。

临床怎么用

  • 可考虑将计划CT的AI-ILD筛查用于局部晚期非小细胞肺癌根治性放疗前的放射性肺炎风险分层。
  • 对AI-ILD阳性尤其经放射科医生确认真性放射学ILD者,应加强放射性肺炎监测与风险缓解。

局限性

  • 本研究为单机构回顾性分析。

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: Interstitial lung disease (ILD) has been correlated with an increased risk for radiation pneumonitis (RP) following lung SBRT, but the degree to which locally advanced NSCLC (LA-NSCLC) patients are affected has yet to be quantified. An algorithm to identify patients at high risk for RP may help clinicians mitigate risk. METHODS: All LA-NSCLC patients treated with definitive radiotherapy at our institution from 2006 to 2021 were retrospectively assessed. A convolutional neural network was previously developed to identify patients with radiographic ILD using planning computed tomography (CT) images. All screen-positive (AI-ILD + ) patients were reviewed by a thoracic radiologist to identify true radiographic ILD (r-ILD). The association between the algorithm output, clinical and dosimetric variables, and the outcomes of grade ≥3 RP and mortality were assessed using univariate (UVA) and multivariable (MVA) logistic regression, and Kaplan-Meier survival analysis. RESULTS: 698 patients were included in the analysis. Grade (G) 0-5 RP was reported in 51 %, 27 %, 17 %, 4.4 %, 0.14 % and 0.57 % of patients, respectively. Overall, 23 % of patients were classified as AI-ILD+. On MVA, only AI-ILD status (OR 2.15, p = 0.03) and AI-ILD score (OR 35.27, p < 0.01) were significant predictors of G3+RP. Median OS was 3.6 years in AI-ILD- patients and 2.3 years in AI-ILD+patients (NS). Patients with r-ILD had significantly higher rates of severe toxicities, with G3+RP 25 % and G5 RP 7 %. R-ILD was associated with an increased risk for G3+RP on MVA (OR 5.42, p < 0.01). CONCLUSION: Our AI-ILD algorithm detects patients with significantly increased risk for G3+RP.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Bacon H, McNeil N, Patel T, et al. Association of artificial intelligence-screened interstitial lung disease with radiation pneumonitis in locally advanced non-small cell lung cancer. Radiother Oncol. 2025. PMID: 40953708. doi:10.1016/j.radonc.2025.111144

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。