文献速递腹部CT

放射组学-临床联合模型是否有助于鉴别胰腺癌与肿块型胰腺炎

Is the radiomics-clinical combined model helpful in distinguishing between pancreatic cancer and mass-forming pancreatitis?
PubMed 文献 · Eur J Radiol · 2023-05-03

本研究纳入201例可切除胰腺导管腺癌(PDAC)和54例肿块型胰腺炎(MFP)患者,基于CT放射组学特征构建LASSOscore和PCAscore,并与年龄、CA19-9、双管征等临床变量联合建立LASSOCli和PCACli模型。在验证队列中,PCACli模型鉴别可切除PDAC与MFP的AUC为0.880,与EUS-FNA的AUC 0.810表现相当;决策曲线分析显示在35%风险阈值下,PCACli模型净获益优于EUS-FNA,每1000例患者可避免70例活检。

要点

  • PCACli模型在验证队列中鉴别可切除PDAC与MFP的AUC为0.880,与EUS-FNA的AUC 0.810表现相当。
  • 在35%风险阈值下,PCACli模型净获益优于EUS-FNA,每1000例患者可避免70例活检。
  • 放射组学特征(LASSOscore、PCAscore)联合年龄、CA19-9和双管征可提高基线临床模型的诊断准确性。

核心结论

  • PCACli模型在鉴别可切除PDAC与MFP方面与EUS-FNA表现相当。

研究设计与样本

  • 回顾性研究,纳入201例可切除PDAC和54例MFP患者;开发队列为无术前EUS-FNA的患者(175例PDAC,38例MFP),验证队列为接受EUS-FNA的患者(26例PDAC,16例MFP);基于CT放射组学特征构建LASSOscore和PCAscore,并与临床特征联合建立LASSOCli和PCACli模型;采用ROC分析和决策曲线分析评估模型与EUS-FNA在验证队列中的效用。

诊断标准与关键数值

  • 验证队列中,LASSOscore鉴别可切除PDAC与MFP的AUC为0.743(95% CI: 0.590-0.896),PCAscore的AUC为0.788(95% CI: 0.639-0.938)。
  • 验证队列中,基线仅临床模型(onlyCli)的AUC为0.760(95% CI: 0.614-0.960)。
  • 验证队列中,PCACli模型(联合年龄、CA19-9、双管征)的AUC为0.880(95% CI: 0.776-0.983),LASSOCli模型的AUC为0.825(95% CI: 0.694-0.955)。
  • 验证队列中,EUS-FNA的AUC为0.810(95% CI: 0.685-0.935),PCACli模型表现与之相当。
  • 决策曲线分析显示,在35%风险阈值下,PCACli模型净获益优于EUS-FNA,每1000例患者可避免70例活检。

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)。

英文原文(摘要)· 点击展开

PURPOSE: To develop CT-based radiomics models for distinguishing between resectable PDAC and mass-forming pancreatitis (MFP) and to provide a non-invasive tool for cases of equivocal imaging findings with EUS-FNA needed.

METHODS: A total of 201 patients with resectable PDAC and 54 patients with MFP were included. Development cohort: patients without preoperative EUS-FNA (175 PDAC cases, 38 MFP cases); validation cohort: patients with EUS-FNA (26 PDAC cases, 16 MFP cases). Two radiomic signatures (LASSOscore, PCAscore) were developed based on the LASSO model and principal component analysis. LASSOCli and PCACli prediction models were established by combining clinical features with CT radiomic features. ROC analysis and decision curve analysis (DCA) were performed to evaluate the utility of the model versus EUS-FNA in the validation cohort.

RESULTS: In the validation cohort, the radiomic signatures (LASSOscore, PCAscore) were both effective in distinguishing between resectable PDAC and MFP (AUCLASSO = 0.743, 95% CI: 0.590-0.896; AUCPCA = 0.788, 95% CI: 0.639-0.938) and improved the diagnostic accuracy of the baseline onlyCli model (AUConlyCli = 0.760, 95% CI: 0.614-0.960) after combination with variables including age, CA19-9, and the double-duct sign (AUCPCACli = 0.880, 95% CI: 0.776-0.983; AUCLASSOCli = 0.825, 95% CI: 0.694-0.955). The PCACli model showed comparable performance to FNA (AUCFNA = 0.810, 95% CI: 0.685-0.935). In DCA, the net benefit of the PCACli model was superior to that of EUS-FNA, avoiding biopsies in 70 per 1000 patients at a risk threshold of 35%.

CONCLUSIONS: The PCACli model showed comparable performance with EUS-FNA in discriminating resectable PDAC from MFP.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Qu, Zhou, Yuan, et al. Is the radiomics-clinical combined model helpful in distinguishing between pancreatic cancer and mass-forming pancreatitis? Eur J Radiol. 2023. PMID: 37172441. doi:10.1016/j.ejrad.2023.110857

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。