Cheng Nai-Ming, Yao Jiawen, Cai Jinzheng, Ye Xianghua, Zhao Shilin, Zhao Kui, Zhou Wenlan, Nogues Isabella, Huo Yuankai, Liao Chun-Ta, Wang Hung-Ming, Lin Chien-Yu, Lee Li-Yu, Xiao Jing, Lu Le, Zhang Ling, Yen Tzu-Chen
Department of Nuclear Medicine, Chang Gung Memorial Hospital, Keelung, and Chang Gung University, Taoyuan City, Taiwan, ROC.
PAII Inc., Bethesda, Maryland.
Clin Cancer Res. 2021 Jul 15;27(14):3948-3959. doi: 10.1158/1078-0432.CCR-20-4935. Epub 2021 May 4.
Accurate prognostic stratification of patients with oropharyngeal squamous cell carcinoma (OPSCC) is crucial. We developed an objective and robust deep learning-based fully-automated tool called the DeepPET-OPSCC biomarker for predicting overall survival (OS) in OPSCC using [F]fluorodeoxyglucose (FDG)-PET imaging.
The DeepPET-OPSCC prediction model was built and tested internally on a discovery cohort ( = 268) by integrating five convolutional neural network models for volumetric segmentation and ten models for OS prognostication. Two external test cohorts were enrolled-the first based on the Cancer Imaging Archive (TCIA) database ( = 353) and the second being a clinical deployment cohort ( = 31)-to assess the DeepPET-OPSCC performance and goodness of fit.
After adjustment for potential confounders, DeepPET-OPSCC was found to be an independent predictor of OS in both discovery and TCIA test cohorts [HR = 2.07; 95% confidence interval (CI), 1.31-3.28 and HR = 2.39; 95% CI, 1.38-4.16; both = 0.002]. The tool also revealed good predictive performance, with a c-index of 0.707 (95% CI, 0.658-0.757) in the discovery cohort, 0.689 (95% CI, 0.621-0.757) in the TCIA test cohort, and 0.787 (95% CI, 0.675-0.899) in the clinical deployment test cohort; the average time taken was 2 minutes for calculation per exam. The integrated nomogram of DeepPET-OPSCC and clinical risk factors significantly outperformed the clinical model [AUC at 5 years: 0.801 (95% CI, 0.727-0.874) vs. 0.749 (95% CI, 0.649-0.842); = 0.031] in the TCIA test cohort.
DeepPET-OPSCC achieved an accurate OS prediction in patients with OPSCC and enabled an objective, unbiased, and rapid assessment for OPSCC prognostication.
对口咽鳞状细胞癌（OPSCC）患者进行准确的预后分层至关重要。我们开发了一种基于深度学习的客观且强大的全自动工具，称为DeepPET - OPSCC生物标志物，用于使用[F]氟脱氧葡萄糖（FDG）-PET成像预测OPSCC患者的总生存期（OS）。
通过整合五个用于体积分割的卷积神经网络模型和十个用于OS预后的模型，在一个发现队列（n = 268）上内部构建并测试了DeepPET - OPSCC预测模型。招募了两个外部测试队列——第一个基于癌症影像存档（TCIA）数据库（n = 353），第二个是临床部署队列（n = 31）——以评估DeepPET - OPSCC的性能和拟合优度。
在对潜在混杂因素进行调整后，发现DeepPET - OPSCC在发现队列和TCIA测试队列中均为OS的独立预测因子[风险比（HR）= 2.07；95%置信区间（CI），1.31 - 3.28和HR = 2.39；95% CI，1.38 - 4.16；P均 = 0.002]。该工具还显示出良好的预测性能，在发现队列中的c指数为0.707（95% CI，0.658 - 0.757），在TCIA测试队列中为0.689（95% CI，0.621 - 0.757），在临床部署测试队列中为0.787（95% CI，0.675 - 0.899）；每次检查计算平均耗时2分钟。DeepPET - OPSCC与临床风险因素的综合列线图在TCIA测试队列中显著优于临床模型[5年时的曲线下面积（AUC）：0.801（95% CI，0.727 - 0.874）对0.749（95% CI，0.649 - 0.842）；P = 0.031]。
DeepPET - OPSCC在OPSCC患者中实现了准确的OS预测，并能够对OPSCC预后进行客观、无偏且快速的评估。
