基于深度学习的增强CT实体与囊性胰腺肿瘤检测
本研究回顾性训练并验证了基于nnU-Net的三维深度学习模型,用于在腹部增强CT上自动识别多种实体和囊性胰腺肿瘤患者。在时间独立测试集1中AUC为0.91(95%CI: 0.89, 0.94),在时空独立测试集2中AUC为0.87(95%CI: 0.84, 0.89)。对任意大小实体病变敏感度98%-100%,对≥1.0 cm囊性病变敏感度92%-93%,与放射科医师表现相当。
要点
- DL模型在增强CT上识别胰腺实体和囊性肿瘤整体性能高,AUC达0.87-0.91。
- 对实体病变敏感度98%-100%,对≥1.0 cm囊性病变敏感度92%-93%。
- DL与两位放射科医师诊断性能无显著差异,可作为辅助筛查工具。
核心结论
- 基于深度学习的模型在增强CT上识别多种实体和囊性胰腺病变患者中表现出高性能,与放射科医师相当。
研究设计与样本
- 回顾性研究,训练集852例(中位年龄60岁,范围19-85岁,男462例),测试集1共603例(中位年龄58岁,范围18-82岁,男376例),测试集2共589例(中位年龄63岁,范围18-99岁,男343例)。
- 采用三维nnU-Net深度学习模型,训练数据来自2014年1月至2015年3月因胰腺病变行切除术患者的CT及2014年无胰腺异常患者的CT。
- 测试集1为时间独立队列,测试集2为时间和空间独立队列;参考标准未在摘要中明确说明。
- 性能评估采用受试者工作特征曲线分析,并与两位 board-certified 放射科医师比较。
诊断标准与关键数值
- 测试集1中DL模型识别胰腺病变的AUC为0.91(95%CI: 0.89, 0.94),测试集2中AUC为0.87(95%CI: 0.84, 0.89)。
- DL模型识别任意大小实体病变的敏感度为98%-100%,识别≥1.0 cm囊性病变的敏感度为92%-93%。
临床应用与阅片要点
- DL模型可用于增强CT上胰腺实体和囊性病变的自动检测,辅助放射科医师减少漏诊。
- 对≥1.0 cm囊性病变敏感度高,但对<1.0 cm囊性病变的性能未在摘要中报告。
- 模型在时空独立测试集2中性能略下降(AUC 0.87 vs 0.91),提示外部验证时需注意泛化性。
局限性
- 回顾性研究设计。
- 训练集仅纳入接受切除术的胰腺病变患者,可能存在选择偏倚。
- 摘要未报告对<1.0 cm囊性病变及囊性病变特异度的数据。
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 Deep learning (DL) may facilitate the diagnosis of various pancreatic lesions at imaging. Purpose To develop and validate a DL-based approach for automatic identification of patients with various solid and cystic pancreatic neoplasms at abdominal CT and compare its diagnostic performance with that of radiologists. Materials and Methods In this retrospective study, a three-dimensional nnU-Net-based DL model was trained using the CT data of patients who underwent resection for pancreatic lesions between January 2014 and March 2015 and a subset of patients without pancreatic abnormality who underwent CT in 2014. Performance of the DL-based approach to identify patients with pancreatic lesions was evaluated in a temporally independent cohort (test set 1) and a temporally and spatially independent cohort (test set 2) and was compared with that of two board-certified radiologists. Performance was assessed using receiver operating characteristic analysis. Results The study included 852 patients in the training set (median age, 60 years [range, 19-85 years]; 462 men), 603 patients in test set 1 (median age, 58 years [range, 18-82 years]; 376 men), and 589 patients in test set 2 (median age, 63 years [range, 18-99 years]; 343 men). In test set 1, the DL-based approach had an area under the receiver operating characteristic curve (AUC) of 0.91 (95% CI: 0.89, 0.94) and showed slightly worse performance in test set 2 (AUC, 0.87 [95% CI: 0.84, 0.89]). The DL-based approach showed high sensitivity in identifying patients with solid lesions of any size (98%-100%) or cystic lesions measuring 1.0 cm or larger (92%-93%), which was comparable with the radiologists (95%-100% for solid lesions [P = .51 to P > .99]; 93%-98% for cystic lesions ≥1.0 cm [P = .38 to P > .99]). Conclusion The deep learning-based approach demonstrated high performance in identifying patients with various solid and cystic pancreatic lesions at CT. © RSNA, 2022 Online supplemental material is available for this article.
引用
- Park, Shin, You, et al. Deep Learning-based Detection of Solid and Cystic Pancreatic Neoplasms at Contrast-enhanced CT. Radiology. 2022. PMID: 35997607. doi:10.1148/radiol.220171
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。