利用 CT 放射组学特征鉴别自身免疫性胰腺炎与胰腺导管腺癌。
Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features.
机构信息
The Russell H. Morgan Department of Radiology and Radiological Science, School of Medicine, Johns Hopkins University, JHOC 3140E, 601N. Caroline Street, 21287 Baltimore, USA.
Department of Pathology, The Sol Goldman Pancreatic Cancer Research Center, School of Medicine, Johns Hopkins University, 21287 Baltimore, USA; Sidney Kimmel Comprehensive Cancer Center, School of Medicine, Johns Hopkins University, 21287 Baltimore, USA.
出版信息
Diagn Interv Imaging. 2020 Sep;101(9):555-564. doi: 10.1016/j.diii.2020.03.002. Epub 2020 Apr 8.
PURPOSE
The purpose of this study was to determine whether computed tomography (CT)-based machine learning of radiomics features could help distinguish autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC).
MATERIALS AND METHODS
Eighty-nine patients with AIP (65 men, 24 women; mean age, 59.7±13.9 [SD] years; range: 21-83 years) and 93 patients with PDAC (68 men, 25 women; mean age, 60.1±12.3 [SD] years; range: 36-86 years) were retrospectively included. All patients had dedicated dual-phase pancreatic protocol CT between 2004 and 2018. Thin-slice images (0.75/0.5mm thickness/increment) were compared with thick-slices images (3 or 5mm thickness/increment). Pancreatic regions involved by PDAC or AIP (areas of enlargement, altered enhancement, effacement of pancreatic duct) as well as uninvolved parenchyma were segmented as three-dimensional volumes. Four hundred and thirty-one radiomics features were extracted and a random forest was used to distinguish AIP from PDAC. CT data of 60 AIP and 60 PDAC patients were used for training and those of 29 AIP and 33 PDAC independent patients were used for testing.
RESULTS
The pancreas was diffusely involved in 37 (37/89; 41.6%) patients with AIP and not diffusely in 52 (52/89; 58.4%) patients. Using machine learning, 95.2% (59/62; 95% confidence interval [CI]: 89.8-100%), 83.9% (52:67; 95% CI: 74.7-93.0%) and 77.4% (48/62; 95% CI: 67.0-87.8%) of the 62 test patients were correctly classified as either having PDAC or AIP with thin-slice venous phase, thin-slice arterial phase, and thick-slice venous phase CT, respectively. Three of the 29 patients with AIP (3/29; 10.3%) were incorrectly classified as having PDAC but all 33 patients with PDAC (33/33; 100%) were correctly classified with thin-slice venous phase with 89.7% sensitivity (26/29; 95% CI: 78.6-100%) and 100% specificity (33/33; 95% CI: 93-100%) for the diagnosis of AIP, 95.2% accuracy (59/62; 95% CI: 89.8-100%) and area under the curve of 0.975 (95% CI: 0.936-1.0).
CONCLUSIONS
Radiomic features help differentiate AIP from PDAC with an overall accuracy of 95.2%.
目的
本研究旨在确定基于计算机断层扫描（CT）的放射组学特征的机器学习是否有助于鉴别自身免疫性胰腺炎（AIP）与胰腺导管腺癌（PDAC）。
材料与方法
回顾性纳入 89 例 AIP 患者（65 例男性，24 例女性；平均年龄 59.7±13.9[SD]岁；年龄范围：21-83 岁）和 93 例 PDAC 患者（68 例男性，25 例女性；平均年龄 60.1±12.3[SD]岁；年龄范围：36-86 岁）。所有患者均于 2004 年至 2018 年接受了专用双期胰腺协议 CT 检查。比较了薄层图像（0.75/0.5mm 层厚/层距）和厚层图像（3 或 5mm 层厚/层距）。将胰腺受累的区域（扩大区域、增强改变、胰管闭塞）和不受累的实质区域作为三维体积进行分割。提取了 431 个放射组学特征，并使用随机森林来区分 AIP 和 PDAC。60 例 AIP 和 60 例 PDAC 患者的 CT 数据用于训练，29 例 AIP 和 33 例 PDAC 独立患者的 CT 数据用于测试。
结果
37 例（37/89；41.6%）AIP 患者胰腺弥漫受累，52 例（52/89；58.4%）患者胰腺未弥漫受累。使用机器学习，62 例测试患者中，95.2%（59/62；95%置信区间[CI]：89.8-100%）、83.9%（52/67；95%CI：74.7-93.0%）和 77.4%（48/62；95%CI：67.0-87.8%）分别正确分类为存在 PDAC 或 AIP，使用的薄层静脉期、薄层动脉期和厚层静脉期 CT 图像。29 例 AIP 患者中有 3 例（3/29；10.3%）被错误分类为 PDAC，但所有 33 例 PDAC 患者（33/33；100%）均被正确分类，薄层静脉期 CT 对 AIP 的诊断具有 89.7%的灵敏度（26/29；95%CI：78.6-100%）和 100%的特异性（33/33；95%CI：93-100%），对 AIP 的总体诊断准确率为 95.2%（59/62；95%CI：89.8-100%），曲线下面积为 0.975（95%CI：0.936-1.0）。
结论
放射组学特征有助于鉴别 AIP 和 PDAC，总体准确率为 95.2%。
Zotero 插件