基于CT影像组学特征和深度学习特征的胰腺腺鳞癌与胰腺导管腺癌的鉴别诊断  

Differentiating pancreatic adenosquamous carcinoma from pancreatic ductal adenocarcinoma by CT radiomic anddeep learning features

作　　者：李琪 周健 方旭 俞婕妤 朱蒙蒙 袁小涵 李颖 郭逸飞 汪军 陈士跃 边云 邵成伟 Li Qi;Zhou Jian;Fang Xu;Yu Jieyu;Zhu Mengmeng;Yuan Xiaohan;Li Ying;Guo Yifei;Wang Jun;Chen Shiyue;Bian Yun;Shao Chenwei(Department of Radiology,First Afiliated Hospital of Naval Medical University,Shanghai 200434,China;Department of Radiology,96601 Military Hospital of PLA,Huangshan,245800,China)

机构地区：[1]海军军医大学第一附属医院放射诊断科,上海200433 [2]96601部队医院影像科,黄山245800

出　　处：《中华胰腺病杂志》2023年第3期171-179,共9页Chinese Journal of Pancreatology

基　　金：国家自然科学基金(82271972、82171930、82202125)。

摘　　要：目的林构建并验证基于增强CT的融合影像组学及深度学习特征的模型,评估该模型术前鉴别诊断胰腺腺鳞癌(PASC)和胰腺导管腺癌(PDAC)的效能。方法去回顾性收集2011年1月至2020年12月间海军军医大学第一附属医院经手术病理证实且术前1个月内行增强CT检查的201例PASC患者(PASC组)和332例PDAC患者(PDAC组)的临床资料。依据国际预测模型建模共识,按收治时间顺序将2011年1月至2018年1月共397例患者(156例PASC和241例PDAC)组成训练集,将2018年2月至2020年12月共136例患者(45例PASC和91例PDAC)组成验证集。采用nnU-Net模型进行胰腺肿瘤自动分割,评估临床及CT特征、提取门静脉期影像组学特征及深度学习特征,随后进行特征降维和特征筛选。利用二元logistic回归模型,在训练集中建立临床模型、影像组学模型和深度学习模型,采用受试者工作特征曲线下面积(AUC)、灵敏度、特异度和准确度评估3种模型的性能,采用决策曲线分析(decision curve analysis,DCA)评估模型的临床净收益。结果在训练集和验证集中,PASC组和PDAC组肿瘤大小、环形强化、上游胰腺萎缩及肿瘤囊变差异均有统计学意义(P值均<0.05)。多因素logistic回归结果显示,临床模型中肿瘤大小、环形强化、胆总管扩张及上游胰腺萎缩与PASC显著相关。影像组学模型中,环形强化、胆总管扩张、上游胰腺萎缩和影像组学分数与PASC显著相关。深度学习模型中,环形强化、上游胰腺萎缩和深度学习分数与PASC显著相关。在训练集中,深度学习模型诊断能力最强,其AUC值、灵敏度、特异度和准确度分别为0.86(95%CI0.82~0.90)、75.00%、84.23%和80.60%,而临床模型和影像组学模型分别为0.81(95%CI0.76~0.85)、62.18%、85.89%、76.57%和0.84(95%CI0.80~0.88)、73.08%、82.16%、78.59%。在验证集中,深度学习模型的AUC值、灵敏度、特异度和准确度分别为0.78(95%CI0.67~0.84)、68.89%、78.02%�Objective To develop and validate the models based on mixed enhanced computed tomography(CT)radiomics and deep learning features,and evaluate the efficacy for differentiating pancreatic adenosquamous carcinoma(PASC)from pancreatic ductal adenocarcinoma(PDAC)before surgery.Methods The clinical data of 201 patients with surgically resected and histopathologically confirmed PASC(PASC group)and 332 patients with surgically resected histopathologically confirmed PDAC(PDAC group)who underwent enhanced CT within 1 month before surgery in the First Affiliated Hospital of Naval Medical University from January 2011 to December 2020 were retrospectively collected.The patients were chronologically divided into a training set(treated between January 2011 and January 2018,156 patients with PASC and 241 patients with PDAC)and a validation set(treated between February 2018 and December 2020,45 patients with PASC and 91 patients with PDAC)according to the international consensus on the predictive model.The nnU-Net model was used for pancreatic tumor automatic segmentation,the clinical and CT images were evaluated,and radiomics features and deep learning features during portal vein phase were extracted;then the features were dimensionally reduced and screened.Binary logistic analysis was performed to develop the clinical,radiomics and deep learning models in the training set.The models'performances were determined by area under the ROC curve(AUC),sensitivity,specificity,accuracy,and decision curve analysis(DCA).Results Significant differences were observed in tumor size,ring-enhancement,upstream pancreatic parenchymal atrophy and cystic degeneration of tumor both in PASC and PDAC group in the training and validation set(all P value<0.05).The multivariable logistic regression analysis showed the tumor size,ringenhancement,dilation of the common bile duct and upstream pancreatic parenchymal atrophy were associated with PASC significantly in the clinical model.The ring-enhancement,dilation of the common bile duct,upstream pancreatic

关 键 词：胰腺肿瘤 导管腺癌 癌 腺鳞状 体层摄影术 X线计算机 诊断 鉴别 

分 类 号：R735.9[医药卫生—肿瘤]