Related Experiment Video
Updated: Jul 5, 2026
06:03
Orthotopic Transplantation of Syngeneic Lung Adenocarcinoma Cells to Study PD-L1 Expression
Published on: January 19, 2019
16.7K
CT-Based Deep Foundation Model for Predicting Immune Checkpoint Inhibitor-Induced Pneumonitis Risk in Lung Cancer
Amgad Muneer1, Eman Showkatian1, Yuliya Kitsel1,2
1Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
Summary
A new AI model, CIPHER, predicts immune checkpoint inhibitor-induced pneumonitis (ICI-P) from baseline CT scans, outperforming traditional methods. This tool aids early risk identification for better patient management in lung cancer immunotherapy.
Area of Science:
- Artificial intelligence in medical imaging
- Deep learning for predictive diagnostics
- Oncology and immunotherapy research
Background:
- Immune checkpoint inhibitors (ICIs) offer advanced cancer treatment but can cause severe immune-related adverse events (irAEs), notably pneumonitis (ICI-P).
- Early identification of patients at high risk for ICI-P is crucial for proactive monitoring and timely intervention to optimize treatment outcomes.
Purpose of the Study:
- To develop and validate a deep learning foundation model, CIPHER, for predicting ICI-P risk using baseline CT scans in lung cancer patients.
- To assess the model's performance against established radiomic approaches.
Main Methods:
- Designed CIPHER, a deep learning model using contrastive learning and a transformer-based masked autoencoder, pre-trained on a large dataset of non-small cell lung cancer (NSCLC) CT scans.
- Fine-tuned and validated CIPHER on internal and external NSCLC cohorts, comparing its predictive accuracy against classical radiomic models.
Main Results:
- CIPHER demonstrated strong performance in predicting ICI-P, with AUCs ranging from 0.77 to 0.85 in internal validation and 0.83 in external validation.
- The model outperformed radiomic models in head-to-head comparisons, showing superior specificity without compromising sensitivity in external validation.
Conclusions:
- CIPHER is the first AI foundation model for immune toxicity prediction, successfully developed and validated for forecasting ICI-P risk from pre-treatment CT scans.
- Prospective validation and integration into clinical workflows could significantly improve patient management and outcomes in immunotherapy.
Related Concept Videos
01:15Ischemic Stroke l: Introduction
Ischemic stroke is an acute cerebrovascular condition in which blood flow to a brain region is suddenly interrupted, leading to tissue infarction. Neurons depend on continuous oxygen and glucose supply, so even brief reductions in perfusion cause energy failure, ionic imbalance, and irreversible injury. Ischemic strokes are classified into thrombotic and embolic types based on their underlying mechanisms.Thrombotic MechanismsThrombotic stroke develops when a clot forms within a cerebral artery.
01:15Ischemic Stroke ll: Pathophysiology
An ischemic stroke occurs when a cerebral blood vessel becomes obstructed, most often by a thrombus or embolus, interrupting the delivery of oxygen and glucose to brain tissue. Because neurons rely on continuous aerobic metabolism, energy failure begins within minutes of reduced perfusion. The region receiving the least blood flow becomes the infarct core, an area of irreversible cellular death. Surrounding this core lies the penumbra, a zone of hypoperfused but still viable tissue that is...
01:26Transient Ischemic Attack l: Introduction
A transient ischemic attack (TIA) is a brief episode of neurological dysfunction caused by a temporary, focal reduction in cerebral blood flow. Although symptoms resemble those of an ischemic stroke, the interruption in perfusion is short-lived and does not cause permanent infarction. TIAs are clinically important because they often serve as early warning events for future stroke.Mechanisms of Transient Cerebral IschemiaTransient cerebral ischemia may arise through several mechanisms. One...