文献速递腹部CT

利用深度学习在门静脉期CT扫描上自动检测胰腺病变及主胰管扩张

Automatic Detection of Pancreatic Lesions and Main Pancreatic Duct Dilatation on Portal Venous CT Scans Using Deep Learning.
PubMed 文献 · Invest Radiol · 2023-06-08

本研究基于9家机构共2890例门静脉期CT扫描(其中2185例有胰腺肿瘤、705例为健康对照),提出并评估一种深度学习三步法检测胰腺肿瘤和主胰管扩张,在独立测试集756例中检出病变的AUC为0.98、敏感度为0.94,主胰管扩张检测AUC为0.97。

要点

  • 模型在独立测试集检出胰腺病变的AUC为0.98(95%CI 0.97-0.99),敏感度0.94(469/493)。
  • 小病灶(<2cm)和等密度病灶的敏感度分别为0.94(115/123)和0.95(53/56)。
  • 主胰管扩张检测AUC为0.97(95%CI 0.96-0.98),模型结合病灶直接检测与主胰管直径等次要特征。

核心结论

  • 该方法在独立测试队列中检测胰腺肿瘤和主胰管扩张表现出高定量性能,且在不同病变特征和类型亚组中表现稳健;结果证实将直接病灶检测与主胰管直径等次要特征相结合的价值,提示这可能是早期检测胰腺癌的有前景途径。

研究设计与样本

  • 研究纳入9家机构共2890例门静脉期CT扫描(2185例有胰腺肿瘤、705例健康对照),每例由9名放射科医生中的1名审阅;数据分为训练集2134例和独立测试集756例;方法分三步:分割网络5折交叉验证训练、后处理提取影像特征(归一化病灶风险、预测病灶直径、胰头/体/尾部主胰管直径)、校准2个逻辑回归模型分别预测病变存在和主胰管扩张;在独立测试队列上采用受试者工作特征分析评估性能,并按病变类型和特征定义亚组评估。

诊断标准与关键数值

  • 模型检出患者病变的AUC为0.98(95%CI 0.97-0.99),敏感度0.94(469/493;95%CI 0.92-0.97);小病灶(小于2cm)敏感度0.94(115/123;95%CI 0.87-0.98),等密度病灶敏感度0.95(53/56;95%CI 0.87-1.0);胰腺导管腺癌、神经内分泌肿瘤、导管内乳头状肿瘤的敏感度分别为0.94(95%CI 0.91-0.97)、1.0(95%CI 0.98-1.0)、0.96(95%CI 0.97-1.0);主胰管扩张检测AUC为0.97(95%CI 0.96-0.98)。

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

OBJECTIVES: This study proposes and evaluates a deep learning method to detect pancreatic neoplasms and to identify main pancreatic duct (MPD) dilatation on portal venous computed tomography scans.

MATERIALS AND METHODS: A total of 2890 portal venous computed tomography scans from 9 institutions were acquired, among which 2185 had a pancreatic neoplasm and 705 were healthy controls. Each scan was reviewed by one in a group of 9 radiologists. Physicians contoured the pancreas, pancreatic lesions if present, and the MPD if visible. They also assessed tumor type and MPD dilatation. Data were split into a training and independent testing set of 2134 and 756 cases, respectively.A method to detect pancreatic lesions and MPD dilatation was built in 3 steps. First, a segmentation network was trained in a 5-fold cross-validation manner. Second, outputs of this network were postprocessed to extract imaging features: a normalized lesion risk, the predicted lesion diameter, and the MPD diameter in the head, body, and tail of the pancreas. Third, 2 logistic regression models were calibrated to predict lesion presence and MPD dilatation, respectively. Performance was assessed on the independent test cohort using receiver operating characteristic analysis. The method was also evaluated on subgroups defined based on lesion types and characteristics.

RESULTS: The area under the curve of the model detecting lesion presence in a patient was 0.98 (95% confidence interval [CI], 0.97-0.99). A sensitivity of 0.94 (469 of 493; 95% CI, 0.92-0.97) was reported. Similar values were obtained in patients with small (less than 2 cm) and isodense lesions with a sensitivity of 0.94 (115 of 123; 95% CI, 0.87-0.98) and 0.95 (53 of 56, 95% CI, 0.87-1.0), respectively. The model sensitivity was also comparable across lesion types with values of 0.94 (95% CI, 0.91-0.97), 1.0 (95% CI, 0.98-1.0), 0.96 (95% CI, 0.97-1.0) for pancreatic ductal adenocarcinoma, neuroendocrine tumor, and intraductal papillary neoplasm, respectively. Regarding MPD dilatation detection, the model had an area under the curve of 0.97 (95% CI, 0.96-0.98).

CONCLUSIONS: The proposed approach showed high quantitative performance to identify patients with pancreatic neoplasms and to detect MPD dilatation on an independent test cohort. Performance was robust across subgroups of patients with different lesion characteristics and types. Results confirmed the interest to combine a direct lesion detection approach with secondary features such as the MPD diameter, thus indicating a promising avenue for the detection of pancreatic cancer at early stages.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Abi Nader, Vetil, Wood, et al. Automatic Detection of Pancreatic Lesions and Main Pancreatic Duct Dilatation on Portal Venous CT Scans Using Deep Learning. Invest Radiol. 2023. PMID: 37289274. doi:10.1097/RLI.0000000000000992

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。