Cancer Center, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi Hospital, Third Hospital of Shanxi Medical University, Taiyuan, 030032, China; Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China.
School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin, Guangxi, 541004, China.
Clin Radiol. 2023 Oct;78(10):e689-e697. doi: 10.1016/j.crad.2023.05.010. Epub 2023 Jun 6.
To develop a deep-learning model using contrast-enhanced chest computed tomography (CT) images to predict programmed death-ligand 1 (PD-L1) expression in patients with non-small-cell lung cancer (NSCLC).
Preoperative enhanced chest CT images and immunohistochemistry results for PD-L1 expression (<1% and ≥1% were defined as negative and positive, respectively) were collected retrospectively from 125 NSCLC patients to train and validate a deep-learning radiomics model (DLRM) for the prediction of PD-L1 expression in tumours. The DLRM was developed by combining the deep-learning signature (DLS) obtained from a convolutional neural network and clinicopathological factors. The indexes of the area under the curve (AUC), integrated discrimination improvement (IDI), and decision curve analysis (DCA) were used to evaluate the efficiency of the DLRM.
DLS and tumour stage were identified as independent predictors of PD-L1 expression by the DLRM. The AUCs of the DLRM were 0.804 (95% confidence interval: 0.697-0.911) and 0.804 (95% confidence interval: 0.679-0.929) in the training and validation cohorts, respectively. IDI analysis showed the DLRM had better diagnostic accuracy than DLS (0.0028 [p<0.05]) in the validation cohort. Additionally, DCA revealed that the DLRM had more net benefit than the DLS for clinical utility.
The proposed DLRM using enhanced chest CT images could function as a non-invasive diagnostic tool to differentiate PD-L1 expression in NSCLC patients.
利用增强胸部 CT 图像开发深度学习模型，预测非小细胞肺癌（NSCLC）患者程序性死亡配体 1（PD-L1）的表达。
回顾性收集 125 例 NSCLC 患者的术前增强胸部 CT 图像和 PD-L1 表达的免疫组化结果（<1%和≥1%分别定义为阴性和阳性），以训练和验证深度学习放射组学模型（DLRM）用于预测肿瘤中 PD-L1 的表达。DLRM 通过结合从卷积神经网络获得的深度学习特征（DLS）和临床病理因素进行开发。使用曲线下面积（AUC）、综合判别改善（IDI）和决策曲线分析（DCA）的指标来评估 DLRM 的效率。
DLRM 将 DLS 和肿瘤分期确定为 PD-L1 表达的独立预测因子。在训练和验证队列中，DLRM 的 AUC 分别为 0.804（95%置信区间：0.697-0.911）和 0.804（95%置信区间：0.679-0.929）。IDI 分析表明，在验证队列中，DLRM 比 DLS 具有更好的诊断准确性（0.0028 [p<0.05]）。此外，DCA 表明 DLRM 比 DLS 具有更高的临床实用净收益。
该研究提出的使用增强胸部 CT 图像的 DLRM 可以作为一种非侵入性诊断工具，用于区分 NSCLC 患者的 PD-L1 表达。
