文献速递肿瘤 PET/CT

基于神经网络的18F-FDG PET/CT病灶自动分类及无远处转移鼻咽癌的预后预测

Neural Network-based Automated Classification of 18 F-FDG PET/CT Lesions and Prognosis Prediction in Nasopharyngeal Carcinoma Without Distant Metastasis.
PubMed 文献 · Clin Nucl Med · 2025-05-09

回顾性纳入83例治疗前接受18F-FDG PET/CT的无远处转移鼻咽癌患者,评估PET辅助报告系统(PARS)诊断恶性病灶的灵敏度、特异度和准确率,并比较PARS与手动分割获得的代谢参数及其预后价值。PARS基于患者和基于病灶的准确率分别为97.2%和96.7%,代谢参数与手动分割高度相关且一致,MTV和年龄为独立预后因素,二者联合可改善预后预测和风险分层。

要点

  • PARS基于患者诊断恶性病灶的灵敏度88.9%、特异度97.4%、准确率97.2%。
  • 手动分割获得的MTV和TLG高于PARS,但两方法代谢参数高度相关且一致。
  • MTV和年龄为独立预后因素,联合指标低风险组预后更好(χ²=42.25,P<0.001;χ²=20.44,P<0.001)。

核心结论

  • PARS在无远处转移鼻咽癌患者中初步验证显示对病灶识别和分类具有高诊断灵敏度和准确率,代谢参数与手动分割相关性好。
  • MTV反映预后,其与年龄联合可增强预后预测和风险分层。

研究设计与样本

  • 回顾性收集83例接受治疗前18F-FDG PET/CT的无远处转移鼻咽癌患者。
  • 以组织病理学为金标准,计算PARS诊断恶性病灶的灵敏度、特异度和准确率。
  • 分别用PARS和手动分割获取原发肿瘤代谢参数,分析两方法差异与一致性。
  • 评估PET代谢参数对无进展生存(PFS)和总生存(OS)的预后价值。

主要发现

  • PARS基于患者的准确率97.2%、灵敏度88.9%、特异度97.4%;基于病灶的准确率96.7%、灵敏度84.0%、特异度96.9%。
  • 手动分割得到的MTV和TLG高于PARS。
  • 两种方法获得的代谢参数高度相关且一致。
  • ROC分析显示代谢参数在预后预测中存在差异,但总体对3年PFS和OS预测表现良好。
  • MTV和年龄为独立预后因素,联合二者的Cox比例风险模型预测显著改善;基于联合指标的低风险组预后更好(χ²=42.25,P<0.001;χ²=20.44,P<0.001)。

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 evaluate the diagnostic performance of the PET Assisted Reporting System (PARS) in nasopharyngeal carcinoma (NPC) patients without distant metastasis, and to investigate the prognostic significance of the metabolic parameters. PATIENTS AND METHODS: Eighty-three NPC patients who underwent pretreatment 18 F-FDG PET/CT were retrospectively collected. First, the sensitivity, specificity, and accuracy of PARS for diagnosing malignant lesions were calculated, using histopathology as the gold standard. Next, metabolic parameters of the primary tumor were derived using both PARS and manual segmentation. The differences and consistency between the 2 methods were analyzed. Finally, the prognostic value of PET metabolic parameters was evaluated. Prognostic analysis of progression-free survival (PFS) and overall survival (OS) was conducted. RESULTS: PARS demonstrated high patient-based accuracy (97.2%), sensitivity (88.9%), and specificity (97.4%), and 96.7%, 84.0%, and 96.9% based on lesions. Manual segmentation yielded higher metabolic tumor volume (MTV) and total lesion glycolysis (TLG) than PARS. Metabolic parameters from both methods were highly correlated and consistent. ROC analysis showed metabolic parameters exhibited differences in prognostic prediction, but generally performed well in predicting 3-year PFS and OS overall. MTV and age were independent prognostic factors; Cox proportional-hazards models incorporating them showed significant predictive improvements when combined. Kaplan-Meier analysis confirmed better prognosis in the low-risk group based on combined indicators (χ² = 42.25, P < 0.001; χ² = 20.44, P < 0.001). CONCLUSIONS: Preliminary validation of PARS in NPC patients without distant metastasis shows high diagnostic sensitivity and accuracy for lesion identification and classification, and metabolic parameters correlate well with manual. MTV reflects prognosis, and its combination with age enhances prognostic prediction and risk stratification.

来源:Clin Nucl Med,查看原文。版权归原作者所有。

引用

  1. Lv Y, Zheng D, Wang R, et al. Neural Network-based Automated Classification of 18 F-FDG PET/CT Lesions and Prognosis Prediction in Nasopharyngeal Carcinoma Without Distant Metastasis. Clin Nucl Med. 2025. PMID: 40357637. doi:10.1097/RLU.0000000000005942

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。