文献速递肿瘤 PET/CT甲状腺核医学放射性药物与辐射防护

人工智能辅助机会性识别免疫检查点抑制剂相关不良事件:[18F]FDG PET/CT研究

Artificial intelligence-enabled opportunistic identification of immune checkpoint inhibitor-related adverse events using [18F]FDG PET/CT.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2025-05-29

本研究纳入64例接受免疫检查点抑制剂(ICI)治疗的肺癌、黑色素瘤或淋巴瘤患者,利用人工智能自动勾画器官并量化治疗前后[18F]FDG PET/CT的SUVmax和SUVmean。结果显示甲状腺摄取在ICI治疗后升高(ΔSUVmax=0.44,p=0.04;ΔSUVmean=0.22,p=0.08),且摄取升高者甲状腺相关不良事件更常见(29% vs 3%,p=0.008),在甲状腺功能减退病例中摄取升高最明显。作者认为该人工智能辅助机会性筛查方法可有效检测甲状腺相关irAEs,尤其是甲状腺功能减退。

要点

  • 64例ICI治疗患者中,55%(SUVmax)和53%(SUVmean)出现甲状腺摄取升高。
  • 甲状腺摄取升高者甲状腺相关不良事件发生率29% vs 3%(p=0.008)。
  • 甲状腺功能减退病例的甲状腺摄取升高最明显(SUVmax p=0.002;SUVmean p=0.03)。

核心结论

  • 人工智能辅助机会性[18F]FDG PET/CT筛查通过摄取量化可有效检测甲状腺相关免疫相关不良事件,尤其是甲状腺功能减退。
  • 该方法有望作为早期irAE检测的生物标志物,改善患者管理并优化免疫治疗。

研究设计与样本

  • 纳入64例接受ICI治疗的肺癌、黑色素瘤或淋巴瘤患者,均有治疗前后[18F]FDG PET/CT。
  • 采用涉及多个依次应用的深度学习模型的人工智能方法自动勾画解剖结构。
  • 自动去除肿瘤病灶后,量化甲状腺、心肌、胰腺、肝脏、骨、脾和肾上腺的SUVmax与SUVmean。
  • 统计分析识别与临床观察到的炎症相关不良事件相关的摄取变化。

主要发现

  • 64例患者平均扫描间隔4.5个月,ICI治疗后甲状腺摄取升高(ΔSUVmax=0.44,p=0.04;ΔSUVmean=0.22,p=0.08)。
  • 55%(SUVmax)和53%(SUVmean)的患者出现甲状腺摄取升高。
  • 甲状腺相关不良事件在甲状腺摄取升高者中更常见(29% vs 3%,p=0.008)。
  • 甲状腺功能减退病例中甲状腺摄取升高最明显(SUVmax p=0.002;SUVmean p=0.03)。
  • 心肌、胰腺和肝脏摄取升高但无统计学显著性(p > 0.05)。

临床怎么用

  • 作者认为人工智能辅助机会性[18F]FDG PET/CT筛查通过摄取量化可有效检测甲状腺相关irAEs,尤其是甲状腺功能减退。
  • 作者认为该方法有望作为早期irAE检测的生物标志物,改善患者管理并优化免疫治疗。

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: Immune checkpoint inhibitors (ICI) have transformed cancer therapy, improving outcomes in malignancies like lung cancer, melanoma, and lymphoma by targeting PD-1, PD-L1, and CTLA-4 to enhance T cell-mediated tumor destruction. However, ICI often induce immune-related adverse events (irAEs) across multiple organs. [18F]FDG PET/CT is a valuable tool for assessing immune activation, but whole-organ inflammation evaluation remains time-consuming and prone to variability. This study investigates AI-driven organ-level [18F]FDG PET/CT uptake changes pre- and post-ICI therapy to opportunistically detect irAEs. METHODS: A total of 64 patients with lung cancer, melanoma, or lymphoma who underwent [18F]FDG PET/CT before and after ICI therapy were included. Automated delineation of anatomical structures was performed using an artificial intelligence approach involving multiple subsequently applied deep learning models. SUVmax and SUVmean were quantified for irAE-related organs (thyroid, myocardium, pancreas, liver, bone, spleen, and adrenal glands) after automated tumor lesion removal. Statistical analysis identified uptake changes linked to clinically observed inflammation-related adverse events. RESULTS: Among 64 patients (mean scan interval 4.5 months), thyroid uptake increased post-ICI (ΔSUVmax=0.44, p = 0.04; ΔSUVmean=0.22, p = 0.08). Increased uptake occurred in 55% (SUVmax) and 53% (SUVmean) of patients. Thyroid-related adverse events were more frequent in those with increased uptake (29% vs. 3%, p = 0.008), with uptake increase being the most pronounced in the cases of hypothyroidism (p = 0.002 for SUVmax, p = 0.03 for SUVmean). Myocardial, pancreatic, and hepatic uptake increased but without statistical significance (p > 0.05). CONCLUSION: AI-enabled opportunistic [18F]FDG PET/CT screening effectively detects thyroid-related irAEs, particularly hypothyroidism, through uptake quantification. This approach offers a promising biomarker for early irAE detection, enhancing patient management and immunotherapy optimization.

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

引用

  1. Spielvogel CP, Lazarevic A, Zisser L, et al. Artificial intelligence-enabled opportunistic identification of immune checkpoint inhibitor-related adverse events using [18F]FDG PET/CT. Eur J Nucl Med Mol Imaging. 2025. PMID: 40439712. doi:10.1007/s00259-025-07364-2

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。