文献速递肿瘤 PET/CT

引入基于深度学习的[18F]FDG PET去噪对数字PET/CT中EORTC和PERCIST治疗反应评估的影响

The impact of introducing deep learning based [18F]FDG PET denoising on EORTC and PERCIST therapeutic response assessments in digital PET/CT.
PubMed 文献 · EJNMMI Res · 2024-08-10

研究前瞻性纳入110例接受基线和随访标准数字[18F]FDG PET/CT的患者,比较标准PET与AI去噪半时长PET混合分类与标准分类对EORTC和PERCIST治疗反应评估的一致性。混合分类与标准分类中369/397(93%)一致,加权Cohen's kappa=0.86(95%CI:0.78-0.94),11/110(10%)患者至少一项分类不一致,可能影响2%患者的管理。结论认为标准PET与AI去噪半时长PET比较可行且临床似乎满意。

要点

  • 混合分类与标准分类一致率为369/397(93%),加权Cohen's kappa=0.86(95%CI:0.78-0.94)。
  • 11/110(10%)患者至少一项EORTC或PERCIST混合分类与标准分类不一致。
  • 不一致分类可能影响2%患者的管理。

核心结论

  • 尽管比较相似PET图像更利于治疗反应评估,标准[18F]FDG PET与AI去噪半时长PET比较可行且临床似乎满意。

研究设计与样本

  • 前瞻性纳入110例接受基线和随访标准数字[18F]FDG PET/CT的患者。
  • 由2位读者以基线标准PET1与随访标准PET2之间的EORTC及适用时的PERCIST反应分类作为金标准,与标准PET1和AI PET2混合分类(第1组;n=64)或AI PET1和标准PET2混合分类(第2组;n=46)比较。
  • 分类分别使用超高清PET(有或无AI去噪,简写为UHD)的标准化摄取值或EANM研究限值v2(EARL2)合规值(标准PET经高斯滤波,AI PET使用相同滤波器)建立。

主要发现

  • 总体汇总两组,11/110(10%)患者至少一项EORTCUHD或EARL2或PERCISTUHD或EARL2混合分类与标准分类不一致。
  • 369/397(93%)分类一致,未加权Cohen's kappa=0.86(95%CI:0.78-0.94)。
  • 修改后的混合分类与标准分类可能影响2%患者的管理。

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: [18F]FDG PET denoising by SubtlePET™ using deep learning artificial intelligence (AI) was previously found to induce slight modifications in lesion and reference organs' quantification and in lesion detection. As a next step, we aimed to evaluate its clinical impact on [18F]FDG PET solid tumour treatment response assessments, while comparing "standard PET" to "AI denoised half-duration PET" ("AI PET") during follow-up. RESULTS: 110 patients referred for baseline and follow-up standard digital [18F]FDG PET/CT were prospectively included. "Standard" EORTC and, if applicable, PERCIST response classifications by 2 readers between baseline standard PET1 and follow-up standard PET2 as a "gold standard" were compared to "mixed" classifications between standard PET1 and AI PET2 (group 1; n = 64), or between AI PET1 and standard PET2 (group 2; n = 46). Separate classifications were established using either standardized uptake values from ultra-high definition PET with or without AI denoising (simplified to "UHD") or EANM research limited v2 (EARL2)-compliant values (by Gaussian filtering in standard PET and using the same filter in AI PET). Overall, pooling both study groups, in 11/110 (10%) patients at least one EORTCUHD or EARL2 or PERCISTUHD or EARL2 mixed vs. standard classification was discordant, with 369/397 (93%) concordant classifications, unweighted Cohen's kappa = 0.86 (95% CI: 0.78-0.94). These modified mixed vs. standard classifications could have impacted management in 2% of patients. CONCLUSIONS: Although comparing similar PET images is preferable for therapy response assessment, the comparison between a standard [18F]FDG PET and an AI denoised half-duration PET is feasible and seems clinically satisfactory.

来源:EJNMMI Res,查看原文。版权归原作者所有。

引用

  1. Weyts K, Lequesne J, Johnson A, et al. The impact of introducing deep learning based [18F]FDG PET denoising on EORTC and PERCIST therapeutic response assessments in digital PET/CT. EJNMMI Res. 2024. PMID: 39126532. doi:10.1186/s13550-024-01128-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。