EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

CT-based deep foundation model for predicting immune checkpoint inhibitor-induced pneumonitis risk in lung cancer

Amgad Muneer, Eman Showkatian, Yuliya Kitsel, Maliazurina B Saad, Sheeba J Sujit, Felipe Soto, Girish S Shroff, Saadia A Faiz, Mohammad I Ghanbar, Sherif M Ismail, Natalie I Vokes, Tina Cascone und 14 weitere

Journal for ImmunoTherapy of Cancer · 2026

DOI: 10.1136/jitc-2026-015014 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal for ImmunoTherapy of Cancer, 2026. Verfasst von Amgad Muneer und 25 weiteren Autor:innen. Beteiligte Einrichtung: Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA. Hauptthemen laut MEDLINE: Immune Checkpoint Inhibitors, Lung Neoplasms, Pneumonia, Tomography, X-Ray Computed. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NCI NIH HHS, Tumor Measurement Initiative through the MD Anderson Strategic Initiative Development Program, CPRIT.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Immune checkpoint inhibitors (ICIs) have revolutionized cancer therapy, but can cause serious immune-related adverse events, 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 patients with lung cancer. Using self-supervised learning, CIPHER was pretrained on 590,284 CT slices from 2,500 patients with non-small cell lung cancer (NSCLC) to learn representations of heterogeneous lung parenchyma. Following pretraining, CIPHER was adapted to the internal MD Anderson Cancer Center 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 controls.

Results

In our internal immunotherapy cohort, CIPHER consistently distinguished patients at elevated risk of ICI-P from those without the event, with area under the curves (AUCs) ranging from 0.77 to 0.85. In head-to-head benchmarking, CIPHER achieved an AUC of 0.83, outperforming the clinical, radiomics and ensemble models. In the external validation cohort, CIPHER maintained high performance (AUC=0.83; balanced accuracy=81.7%), exceeding the radiomics model (DeLong p=0.0318) and demonstrating superior specificity without sacrificing sensitivity. By contrast, the radiomics model, despite high sensitivity (85.0%), showed markedly lower specificity (45.8%). Confusion matrix analyses confirmed CIPHER’s robust classification, correctly identifying 80 of 96 non-ICI-P cases and 16 of 20 ICI-P cases.

Conclusions

We developed and externally validated CIPHER, a CT-based imaging biomarker for pretreatment ICI-P risk stratification in NSCLC. CIPHER shows promise as a non-invasive tool for ICI-P risk assessment but warrants prospective validation before clinical translation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Immune Checkpoint InhibitorsLung NeoplasmsPneumoniaTomography, X-Ray ComputedDeep LearningCarcinoma, Non-Small-Cell LungHumansFemaleMaleMiddle AgedAged

Stichwörter der Autor:innen

Immune Checkpoint InhibitorImmune related adverse event - irAELung CancerPneumonitis

Substanzen

Immune Checkpoint Inhibitors

Autor:innen und Institutionen

  • Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.
  • Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.
  • Department of Pulmonary Medicine, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.
  • Department of Thoracic Imaging, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.
  • Department of Pulmonary and Critical Care Medicine, Johns Hopkins University, Baltimore, Maryland, USA.
  • Institute for Data Science in Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.

Förderung

  • NCI NIH HHS
  • Tumor Measurement Initiative through the MD Anderson Strategic Initiative Development Program
  • CPRIT
  • Permanent Health Funds
  • MD Anderson Cancer Center Support
  • Philanthropic contributions from Mrs. Andrea Mugnaini and Dr. Edward L.C. Smith
  • The University of Texas MD Anderson Lung Moon Shot Program
  • National Institutes of Health

Zitieren

APA

Muneer, A., Showkatian, E., Kitsel, Y., Saad, M. B., Sujit, S. J., Soto, F., Shroff, G. S., Faiz, S. A., Ghanbar, M. I., Ismail, S. M., Vokes, N. I., Cascone, T., Le, X., Zhang, J., Byers, L. A., Jaffray, D., Chang, J. Y., Liao, Z., Naing, A., …, & Wu, J. (2026). CT-based deep foundation model for predicting immune checkpoint inhibitor-induced pneumonitis risk in lung cancer. Journal for ImmunoTherapy of Cancer. https://doi.org/10.1136/jitc-2026-015014

Vancouver

Muneer A, Showkatian E, Kitsel Y, Saad MB, Sujit SJ, Soto F, et al. CT-based deep foundation model for predicting immune checkpoint inhibitor-induced pneumonitis risk in lung cancer. Journal for ImmunoTherapy of Cancer. 2026. doi:10.1136/jitc-2026-015014

BibTeX
@article{Muneer2026,
  author = {Muneer, Amgad and Showkatian, Eman and Kitsel, Yuliya and Saad, Maliazurina B and Sujit, Sheeba J and Soto, Felipe and Shroff, Girish S and Faiz, Saadia A and Ghanbar, Mohammad I and Ismail, Sherif M and Vokes, Natalie I and Cascone, Tina and Le, Xiuning and Zhang, Jianjun and Byers, Lauren A and Jaffray, David and Chang, Joe Y and Liao, Zhongxing and Naing, Aung and Gibbons, Don L and Vaporciyan, Ara A and Heymach, John V and Suresh, Karthik and Altan, Mehmet and Sheshadri, Ajay and Wu, Jia},
  title = {CT-based deep foundation model for predicting immune checkpoint inhibitor-induced pneumonitis risk in lung cancer},
  journal = {Journal for ImmunoTherapy of Cancer},
  year = {2026},
  doi = {10.1136/jitc-2026-015014}
}
Kostenlos starten →