Predicting Immune Checkpoint Inhibitor-Related Pneumonitis via Computed Tomography and Whole-Lung Analysis Deep...

Immune checkpoint inhibitor-related pneumonitis (ICI-P) is a fatal adverse event of immunotherapy. However, there is a lack of methods to identify patients who have a high risk of developing ICI-P in immunotherapy.

We aim at predicting the individualized risk of developing ICI-P by computed tomography (CT) images and deep learning to assist in personalized immunotherapy planning.

We first explored the prognostic value of the commonly used clinical factors. Moreover, we proposed a novel whole-lung analysis deep learning (DL) model, which is constructed using a combination of Densely Connected Convolutional Networks (DenseNet) and Feature Pyramid Networks (FPN). This DL model mines global lung information from CT images for predicting the risk of developing ICI-P, and it is fully automated and does not require manually annotating images. Finally, 157 patients were collected and randomly divided into training and testing sets for performance evaluation.

In the testing set, the clinical model achieved an Area Under the Curve (AUC) of 0.710 and accuracy of 0.625. By mining global lung information, the DL model achieved AUC=0.780 and accuracy=0.729 in the testing set, where the DL score revealed a significant difference between ICI-P and non-ICI-P patients. Through deep learning visualization technique, we found that many areas outside of tumor (e.g., pleural retraction, pleural effusion, and the abnormalities in vessels) are important for predicting the risk of developing ICI-P in immunotherapy.

The whole-lung analysis DL model provides an easy-to-use method for identifying patients at high risk of developing ICI-P by CT images, which is important for individualized treatment planning in immunotherapy. The performance improvement over the clinical model indicates that mining whole-lung information in CT images is effective for prognostic prediction in immunotherapy.