• Jiawen Yao, Kai Cao, Yang Hou, Jian Zhou, Yingda Xia, Isabella Nogues, Qike Song, Hui Jiang, Xianghua Ye, Jianping Lu, Gang Jin, Hong Lu, Chuanmiao Xie, Rong Zhang, Jing Xiao, Zaiyi Liu, Feng Gao, Yafei Qi, Xuezhou Li, Yang Zheng, Le Lu, Yu Shi, and Ling Zhang.
• PAII Inc., Bethesda, MD.
• Ann. Surg. 2023 Jul 1; 278 (1): e68e79e68-e79.

ObjectiveTo develop an imaging-derived biomarker for prediction of overall survival (OS) of pancreatic cancer by analyzing preoperative multiphase contrast-enhanced computed topography (CECT) using deep learning.BackgroundExploiting prognostic biomarkers for guiding neoadjuvant and adjuvant treatment decisions may potentially improve outcomes in patients with resectable pancreatic cancer.MethodsThis multicenter, retrospective study included 1516 patients with resected pancreatic ductal adenocarcinoma (PDAC) from 5 centers located in China. The discovery cohort (n=763), which included preoperative multiphase CECT scans and OS data from 2 centers, was used to construct a fully automated imaging-derived prognostic biomarker-DeepCT-PDAC-by training scalable deep segmentation and prognostic models (via self-learning) to comprehensively model the tumor-anatomy spatial relations and their appearance dynamics in multiphase CECT for OS prediction. The marker was independently tested using internal (n=574) and external validation cohorts (n=179, 3 centers) to evaluate its performance, robustness, and clinical usefulness.ResultsPreoperatively, DeepCT-PDAC was the strongest predictor of OS in both internal and external validation cohorts [hazard ratio (HR) for high versus low risk 2.03, 95% confidence interval (CI): 1.50-2.75; HR: 2.47, CI: 1.35-4.53] in a multivariable analysis. Postoperatively, DeepCT-PDAC remained significant in both cohorts (HR: 2.49, CI: 1.89-3.28; HR: 2.15, CI: 1.14-4.05) after adjustment for potential confounders. For margin-negative patients, adjuvant chemoradiotherapy was associated with improved OS in the subgroup with DeepCT-PDAC low risk (HR: 0.35, CI: 0.19-0.64), but did not affect OS in the subgroup with high risk.ConclusionsDeep learning-based CT imaging-derived biomarker enabled the objective and unbiased OS prediction for patients with resectable PDAC. This marker is applicable across hospitals, imaging protocols, and treatments, and has the potential to tailor neoadjuvant and adjuvant treatments at the individual level.Copyright © 2022 Wolters Kluwer Health, Inc. All rights reserved.

21 keywords...

hide…