文献速递腹部技术与安全CT

深度学习在CT上检测胰腺癌:一项全国性人群研究

Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study.
PubMed 文献 · Radiology · 2022-09-13

该研究回顾性收集546例胰腺癌患者和733例正常胰腺对照的增强CT,开发并验证了基于深度学习的胰腺癌检测工具。在全国真实世界测试集中敏感度89.7%、特异度92.8%、AUC 0.95,对小于2cm的恶性肿瘤敏感度为74.7%。

要点

  • DL工具在CT上检测胰腺癌的敏感度约90%,与放射科医师报告相当。
  • 对小于2cm的胰腺癌敏感度降至74.7%,提示早期病灶仍是难点。
  • DL工具可作为CAD辅助,减少腹部CT上胰腺癌的漏诊。

核心结论

  • 基于深度学习的工具能在CT上准确检测胰腺癌,对小于2cm的肿瘤敏感度尚可。

研究设计与样本

  • 回顾性研究,纳入546例胰腺癌患者和733例正常胰腺对照,随机分为训练、验证和测试集。
  • 开发端到端工具,包括分割卷积神经网络和五个CNN集成的分类器,在内部测试集和全国真实世界验证集验证。
  • 真实世界验证集来自台湾多家机构,共1473例CT研究(669例恶性,804例对照)。
  • 比较CAD工具与放射科医师解读的敏感度,使用McNemar检验。

诊断标准与关键数值

  • 内部测试集:敏感度89.9%(98/109,95%CI 82.7-94.9),特异度95.9%(141/147,95%CI 91.3-98.5),AUC 0.96(95%CI 0.94-0.99)。
  • 真实世界测试集:敏感度89.7%(600/669,95%CI 87.1-91.9),特异度92.8%(746/804,95%CI 90.8-94.5),AUC 0.95(95%CI 0.94-0.96)。
  • 真实世界测试集中,小于2cm的恶性肿瘤敏感度74.7%(68/91,95%CI 64.5-83.3)。

临床应用与阅片要点

  • DL工具可作为腹部CT胰腺癌检测的辅助手段,尤其适用于减少漏诊。
  • 阅片时需注意小于2cm的胰腺癌,DL工具敏感度相对较低,仍应仔细评估。
  • DL工具高敏感度伴随一定假阳性,需结合临床和进一步检查。

局限性

  • 回顾性研究设计。
  • 原文未明确报告多中心设备与序列细节。
  • 真实世界验证集来自台湾机构,外推性需进一步验证。

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

Background Approximately 40% of pancreatic tumors smaller than 2 cm are missed at abdominal CT. Purpose To develop and to validate a deep learning (DL)-based tool able to detect pancreatic cancer at CT. Materials and Methods Retrospectively collected contrast-enhanced CT studies in patients diagnosed with pancreatic cancer between January 2006 and July 2018 were compared with CT studies of individuals with a normal pancreas (control group) obtained between January 2004 and December 2019. An end-to-end tool comprising a segmentation convolutional neural network (CNN) and a classifier ensembling five CNNs was developed and validated in the internal test set and a nationwide real-world validation set. The sensitivities of the computer-aided detection (CAD) tool and radiologist interpretation were compared using the McNemar test. Results A total of 546 patients with pancreatic cancer (mean age, 65 years ± 12 [SD], 297 men) and 733 control subjects were randomly divided into training, validation, and test sets. In the internal test set, the DL tool achieved 89.9% (98 of 109; 95% CI: 82.7, 94.9) sensitivity and 95.9% (141 of 147; 95% CI: 91.3, 98.5) specificity (area under the receiver operating characteristic curve [AUC], 0.96; 95% CI: 0.94, 0.99), without a significant difference (P = .11) in sensitivity compared with the original radiologist report (96.1% [98 of 102]; 95% CI: 90.3, 98.9). In a test set of 1473 real-world CT studies (669 malignant, 804 control) from institutions throughout Taiwan, the DL tool distinguished between CT malignant and control studies with 89.7% (600 of 669; 95% CI: 87.1, 91.9) sensitivity and 92.8% specificity (746 of 804; 95% CI: 90.8, 94.5) (AUC, 0.95; 95% CI: 0.94, 0.96), with 74.7% (68 of 91; 95% CI: 64.5, 83.3) sensitivity for malignancies smaller than 2 cm. Conclusion The deep learning-based tool enabled accurate detection of pancreatic cancer on CT scans, with reasonable sensitivity for tumors smaller than 2 cm. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Aisen and Rodrigues in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Chen, Wu, Wang, et al. Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study. Radiology. 2022. PMID: 36098642. doi:10.1148/radiol.220152

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。