Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University.
Medical AI Lab, School of Biomedical Engineering.
Int J Surg. 2024 May 1;110(5):2669-2678. doi: 10.1097/JS9.0000000000001213.
Occult peritoneal metastases (OPM) in patients with pancreatic ductal adenocarcinoma (PDAC) are frequently overlooked during imaging. The authors aimed to develop and validate a computed tomography (CT)-based deep learning-based radiomics (DLR) model to identify OPM in PDAC before treatment.
This retrospective, bicentric study included 302 patients with PDAC (training: n =167, OPM-positive, n =22; internal test: n =72, OPM-positive, n =9: external test, n =63, OPM-positive, n =9) who had undergone baseline CT examinations between January 2012 and October 2022. Handcrafted radiomics (HCR) and DLR features of the tumor and HCR features of peritoneum were extracted from CT images. Mutual information and least absolute shrinkage and selection operator algorithms were used for feature selection. A combined model, which incorporated the selected clinical-radiological, HCR, and DLR features, was developed using a logistic regression classifier using data from the training cohort and validated in the test cohorts.
Three clinical-radiological characteristics (carcinoembryonic antigen 19-9 and CT-based T and N stages), nine HCR features of the tumor, 14 DLR features of the tumor, and three HCR features of the peritoneum were retained after feature selection. The combined model yielded satisfactory predictive performance, with an area under the curve (AUC) of 0.853 (95% CI: 0.790-0.903), 0.845 (95% CI: 0.740-0.919), and 0.852 (95% CI: 0.740-0.929) in the training, internal test, and external test cohorts, respectively (all P <0.05). The combined model showed better discrimination than the clinical-radiological model in the training (AUC=0.853 vs. 0.612, P <0.001) and the total test (AUC=0.842 vs. 0.638, P <0.05) cohorts. The decision curves revealed that the combined model had greater clinical applicability than the clinical-radiological model.
The model combining CT-based DLR and clinical-radiological features showed satisfactory performance for predicting OPM in patients with PDAC.
在胰腺导管腺癌（PDAC）患者中，隐匿性腹膜转移（OPM）在影像学检查中经常被忽视。作者旨在开发和验证一种基于计算机断层扫描（CT）的深度学习放射组学（DLR）模型，以在治疗前识别 PDAC 中的 OPM。
这项回顾性、双中心研究纳入了 302 例 PDAC 患者（训练集：n =167，OPM 阳性，n =22；内部测试集：n =72，OPM 阳性，n =9；外部测试集：n =63，OPM 阳性，n =9），他们在 2012 年 1 月至 2022 年 10 月期间接受了基线 CT 检查。从 CT 图像中提取肿瘤的手工放射组学（HCR）和 DLR 特征以及腹膜的 HCR 特征。使用互信息和最小绝对收缩和选择算子算法进行特征选择。使用来自训练队列的逻辑回归分类器开发了一种包含选定的临床影像学、HCR 和 DLR 特征的综合模型，并在测试队列中进行了验证。
经过特征选择后，保留了三个临床影像学特征（癌胚抗原 19-9 和基于 CT 的 T 和 N 分期）、九个肿瘤 HCR 特征、14 个肿瘤 DLR 特征和三个腹膜 HCR 特征。综合模型具有令人满意的预测性能，在训练、内部测试和外部测试队列中的曲线下面积（AUC）分别为 0.853（95%CI：0.790-0.903）、0.845（95%CI：0.740-0.919）和 0.852（95%CI：0.740-0.929）（均 P <0.05）。综合模型在训练（AUC=0.853 与 0.612，P <0.001）和总测试（AUC=0.842 与 0.638，P <0.05）队列中的鉴别能力均优于临床影像学模型。决策曲线显示，综合模型比临床影像学模型具有更高的临床适用性。
该模型结合了基于 CT 的 DLR 和临床影像学特征，对预测 PDAC 患者的 OPM 具有令人满意的性能。
