文献速递腹部技术与安全CT

基于CT的影像组学与深度学习模型用于胰腺导管腺癌术前淋巴结分期的系统评价与Meta分析

Radiomics and deep learning models for CT pre-operative lymph node staging in pancreatic ductal adenocarcinoma: A systematic review and meta-analysis.
PubMed 文献 · Eur J Radiol · 2024-05-18

该系统评价与Meta分析纳入4项影像组学研究共213例和4项深度学习研究共272例胰腺导管腺癌患者,评估基于CT的影像组学算法与深度学习模型术前识别淋巴结转移的准确性,以组织病理学为参考标准。汇总敏感度为0.83(95%CI 0.77-0.88)、特异度为0.76(95%CI 0.62-0.86)、诊断比值比为15.70(95%CI 8.12-27.50)、AUC为0.85(95%CI 0.77-0.88)。作者结论认为这些模型在预测淋巴结转移方面表现良好,且纳入研究的RQS与METRICS评分呈强正相关。

要点

  • 汇总敏感度0.83、特异度0.76、AUC 0.85,提示CT影像组学与深度学习模型术前判断淋巴结转移有较好判别力。
  • 影像组学研究平均RQS总分12.00±3.89(RQS百分比33.33±10.80),平均METRICS评分63.60±10.88,方法学质量整体有限。
  • Meta回归显示研究类型(影像组学 vs 深度学习)与数据集大小对诊断比值比均无显著影响(P=0.09和P=0.26)。

核心结论

  • 基于CT的术前影像组学算法与深度学习模型在预测胰腺导管腺癌淋巴结转移方面表现出良好性能,汇总AUC为0.85(95%CI 0.77-0.88)。
  • 纳入研究的RQS与METRICS评分呈显著强正相关(P=0.016;r=0.810)。

研究设计与样本

  • 系统评价与Meta分析,检索PubMed、CENTRAL、Scopus、Web of Science和IEEE数据库截至2024年2月11日的文献。
  • 纳入报告基于CT的影像组学或深度学习模型检测胰腺导管腺癌淋巴结转移准确性、以组织病理学为参考标准的研究。
  • 纳入4项影像组学研究共213例患者和4项深度学习研究共272例患者。
  • 采用QUADAS-2、影像组学质量评分(RQS)和METRICS进行质量评价,计算汇总敏感度、特异度、诊断比值比和AUC。

诊断标准与关键数值

  • 全部研究汇总敏感度0.83(95%CI 0.77-0.88)。
  • 全部研究汇总特异度0.76(95%CI 0.62-0.86)。
  • 全部研究汇总诊断比值比15.70(95%CI 8.12-27.50)。
  • 全部研究汇总AUC 0.85(95%CI 0.77-0.88)。
  • 影像组学研究平均RQS总分12.00±3.89(RQS百分比33.33±10.80),平均METRICS评分63.60±10.88。

临床应用与阅片要点

  • 原文结论认为基于CT的影像组学算法与深度学习模型在胰腺导管腺癌术前预测淋巴结转移方面表现良好,阅片时可将其作为辅助判断信息。
  • 原文结论指出纳入研究的RQS与METRICS评分呈强正相关,提示两种质量评价工具结果一致。

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)。

英文原文(摘要)· 点击展开

PURPOSE: To evaluate the diagnostic accuracy of computed tomography (CT)-based radiomic algorithms and deep learning models to preoperatively identify lymph node metastasis (LNM) in patients with pancreatic ductal adenocarcinoma (PDAC).

METHODS: PubMed, CENTRAL, Scopus, Web of Science and IEEE databases were searched to identify relevant studies published up until February 11, 2024. Two reviewers screened all papers independently for eligibility. Studies reporting the accuracy of CT-based radiomics or deep learning models for detecting LNM in PDAC, using histopathology as the reference standard, were included. Quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2, the Radiomics Quality Score (RQS) and the the METhodological RadiomICs Score (METRICS). Overall sensitivity (SE), specificity (SP), diagnostic odds ratio (DOR), and the area under the curve (AUC) were calculated.

RESULTS: Four radiomics studies comprising 213 patients and four deep learning studies with 272 patients were included. The average RQS total score was 12.00 ± 3.89, corresponding to an RQS percentage of 33.33 ± 10.80, while the average METRICS score was 63.60 ± 10.88. A significant and strong positive correlation was found between RQS and METRICS (p = 0.016; r = 0.810). The pooled SE, SP, DOR, and AUC of all the studies were 0.83 (95 %CI = 0.77-0.88), 0.76 (95 %CI = 0.62-0.86), 15.70 (95 %CI = 8.12-27.50) and 0.85 (95 %CI = 0.77-0.88). Meta-regression analysis results indicated that neither the study type (radiomics vs deep learning) nor the dataset size of the studies had a significant effect on the DOR (p = 0.09 and p = 0.26, respectively).

CONCLUSION: Based on our meta-analysis findings, preoperative CT-based radiomics algorithms and deep learning models demonstrate favorable performance in predicting LNM in patients with PDAC, with a strong correlation between RQS and METRICS of the included studies.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Castellana R, Fanni SC, Roncella C, et al. Radiomics and deep learning models for CT pre-operative lymph node staging in pancreatic ductal adenocarcinoma: A systematic review and meta-analysis. Eur J Radiol. 2024. PMID: 38781919. doi:10.1016/j.ejrad.2024.111510

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。