An Chao, Li Dongyang, Li Sheng, Li Wangzhong, Tong Tong, Liu Lizhi, Jiang Dongping, Jiang Linling, Ruan Guangying, Hai Ning, Fu Yan, Wang Kun, Zhuo Shuiqing, Tian Jie
Department of Minimal Invasive Intervention, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-Sen University Cancer Center, Guangzhou, 510060, China.
Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University, Beijing, 100191, China.
Eur J Nucl Med Mol Imaging. 2022 Mar;49(4):1187-1199. doi: 10.1007/s00259-021-05573-z. Epub 2021 Oct 15.
Diagnosis of lymph node metastasis (LNM) is critical for patients with pancreatic ductal adenocarcinoma (PDAC). We aimed to build deep learning radiomics (DLR) models of dual-energy computed tomography (DECT) to classify LNM status of PDAC and to stratify the overall survival before treatment.
From August 2016 to October 2020, 148 PDAC patients underwent regional lymph node dissection and scanned preoperatively DECT were enrolled. The virtual monoenergetic image at 40 keV was reconstructed from 100 and 150 keV of DECT. By setting January 1, 2021, as the cut-off date, 113 patients were assigned into the primary set, and 35 were in the test set. DLR models using VMI 40 keV, 100 keV, 150 keV, and 100 + 150 keV images were developed and compared. The best model was integrated with key clinical features selected by multivariate Cox regression analysis to achieve the most accurate prediction.
DLR based on 100 + 150 keV DECT yields the best performance in predicting LNM status with the AUC of 0.87 (95% confidence interval [CI]: 0.85-0.89) in the test cohort. After integrating key clinical features (CT-reported T stage, LN status, glutamyl transpeptadase, and glucose), the AUC was improved to 0.92 (95% CI: 0.91-0.94). Patients at high risk of LNM portended significantly worse overall survival than those at low risk after surgery (P = 0.012).
The DLR model showed outstanding performance for predicting LNM in PADC and hold promise of improving clinical decision-making.
淋巴结转移（LNM）的诊断对胰腺导管腺癌（PDAC）患者至关重要。我们旨在构建双能计算机断层扫描（DECT）的深度学习影像组学（DLR）模型，以对PDAC的LNM状态进行分类，并在治疗前对总生存期进行分层。
2016年8月至2020年10月，148例接受区域淋巴结清扫且术前行DECT扫描的PDAC患者入组。从DECT的100 keV和150 keV重建40 keV的虚拟单能图像。以2021年1月1日为截止日期，113例患者被分配到主要数据集，35例在测试集中。开发并比较了使用40 keV、100 keV、150 keV和100 + 150 keV图像的DLR模型。将最佳模型与多变量Cox回归分析选择的关键临床特征相结合，以实现最准确的预测。
基于100 + 150 keV DECT的DLR在预测LNM状态方面表现最佳，测试队列中的曲线下面积（AUC）为0.87（95%置信区间[CI]：0.85 - 0.89）。整合关键临床特征（CT报告的T分期、LN状态、谷氨酰转肽酶和血糖）后，AUC提高到0.92（95% CI：0.91 - 0.94）。LNM高风险患者术后的总生存期明显比低风险患者差（P = 0.012）。
DLR模型在预测PADC中的LNM方面表现出色，有望改善临床决策。
