Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study

作者：Maliazurina B. Saad, Lingzhi Hong, Muhammad Aminu, Natalie I. Vokes, Pingjun Chen, Morteza Salehjahromi, Kang Qin, Sheeba J. Sujit, Xuetao Lu, Elliana Young, Qasem Al-Tashi, Rizwan Qureshi, Carol C. Wu, Brett W. Carter, Steven H. Lin, Percy P. Lee, Saumil Gandhi, Joe Y. Chang, Ruijiang Li, Michael F. Gensheimer, Heather A. Wakelee, Joel W. Neal, Hyun‐Sung Lee, Chao Cheng, Vamsidhar Velcheti, Yanyan Lou, Milena Petranović, Waree Rinsurongkawong, Xiuning Le, Vadeerat Rinsurongkawong, Amy Spelman, Yasir Y. Elamin, Marcelo V. Negrão, Ferdinandos Skoulidis, Carl M. Gay, Tina Cascone, Mara B. Antonoff, Boris Sepesi, Jeff Lewis, Ignacio I. Wistuba, John D. Hazle, Caroline Chung, David A. Jaffray, Don L. Gibbons, Ara A. Vaporciyan, J Jack Lee, John V. Heymach, Jianjun Zhang, Jia Wu · 发表于：The Lancet Digital Health · 年份：2023 · DOI：10.1016/s2589-7500(23)00082-1 · 被引用次数：112 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Cancer Immunotherapy and Biomarkers、Lung Cancer Diagnosis and Treatment

BACKGROUND: Only around 20-30% of patients with non-small-cell lung cancer (NCSLC) have durable benefit from immune-checkpoint inhibitors. Although tissue-based biomarkers (eg, PD-L1) are limited by suboptimal performance, tissue availability, and tumour heterogeneity, radiographic images might holistically capture the underlying cancer biology. We aimed to investigate the application of deep learning on chest CT scans to derive an imaging signature of response to immune checkpoint inhibitors and evaluate its added value in the clinical context. METHODS: In this retrospective modelling study, 976 patients with metastatic, EGFR/ALK negative NSCLC treated with immune checkpoint inhibitors at MD Anderson and Stanford were enrolled from Jan 1, 2014, to Feb 29, 2020. We built and tested an ensemble deep learning model on pretreatment CTs (Deep-CT) to predict overall survival and progression-free survival after treatment with immune checkpoint inhibitors. We also evaluated the added predictive value of the Deep-CT model in the context of existing clinicopathological and radiological metrics. FINDINGS: Our Deep-CT model demonstrated robust stratification of patient survival of the MD Anderson testing set, which was validated in the external Stanford set. The performance of the Deep-CT model remained significant on subgroup analyses stratified by PD-L1, histology, age, sex, and race. In univariate analysis, Deep-CT outperformed the conventional risk factors, including histology, smok...