CT-Based Deep Foundation Model for Predicting Immune Checkpoint Inhibitor-Induced Pneumonitis Risk in Lung Cancer

作者：Amgad Muneer, Eman Showkatian, Yuliya Kitsel, Maliazurina B. Saad, Sheeba J. Sujit, Felipe Soto, Girish S. Shroff, Saadia A. Faiz, Mohammad I. Ghanbar, Sohair Ismail, Natalie I. Vokes, Tina Cascone, Xiuning Le, Jianjun Zhang, L. Byers, David Jaffray, Joe Y. Chang, Zhongxing Liao, Aung Naing, Don L. Gibbons, Ara A. Vaporciyan, John V. Heymach, Karthik S. Suresh, Mehmet Altan, Ajay Sheshadri, Jia Wu · 发表于：medRxiv · 年份：2026 · DOI：10.64898/2026.04.21.26351428 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Cancer Immunotherapy and Biomarkers、Lung Cancer Diagnosis and Treatment

ABSTRACT Background Immune checkpoint inhibitors (ICIs) have revolutionized cancer therapy but can cause serious immune-related adverse events (irAEs), with pneumonitis (ICI-P) being among the most severe. Early identification of high-risk patients before ICI initiation is critical for close monitoring, timely intervention, and optimizing outcomes. Purpose To develop and validate a deep learning foundation model to predict ICI-P from baseline CT scans in patients with lung cancer. Methods We designed the Checkpoint-Inhibitor Pneumonitis Hazard EstimatoR (CIPHER), a deep learning-powered foundation model combining contrastive learning with a transformer-based masked autoencoder to predict ICI-P from baseline CT scans in lung cancer patients. Using self-supervised learning, CIPHER was pretrained on 590,284 CT slices from 2,500 non-small cell lung cancer (NSCLC) patients, to learn representations of heterogeneous lung parenchyma. Following pretraining, CIPHER was adapted to the internal MDA NSCLC immunotherapy cohort of 347 patients, of whom 33 developed adjudicated ICI-P. Fine-tuning was performed using 254 non-ICI-P patients only, and a held-out internal validation set of 93 patients, including 33 ICI-P cases and 60 non-ICI-P controls, was reserved for evaluation. CIPHER was benchmarked against clinical, radiomics, and ensemble comparator models and externally validated in an independent Johns Hopkins NSCLC cohort of 116 patients, including 20 ICI-P cases and 96 non-ICI-P cont...