Individualized Prediction of Radiation Pneumonitis Using RP-GAN: Leveraging Global Lung Features and Explainable Artificial Intelligence

dose regions showed a significant decline in sensitivity, with the recall decreasing to 0.273. XAI visualization confirmed that the model focused not only on the tumor bed but also on the peritumoral parenchyma and contralateral lung.ConclusionThe proposed RP-GAN architecture effectively captures subtle textural changes across the whole lung microenvironment without requiring manual annotations. This framework provides a robust tool for individualized RP risk assessment, facilitating the optimization of radiation therapy plans.