ImmunoDiff: A Diffusion Model for Immunotherapy Response Prediction in Lung Cancer
This work addresses a critical unmet need for lung cancer patients by improving prediction accuracy, though it is incremental as it builds on existing diffusion and conditioning methods.
The study tackled the problem of predicting immunotherapy response in Non-Small Cell Lung Cancer by introducing ImmunoDiff, a diffusion model that synthesizes post-treatment CT scans from baseline imaging, resulting in a 21.24% improvement in balanced accuracy for response prediction and a 0.03 increase in c-index for survival prediction.
Accurately predicting immunotherapy response in Non-Small Cell Lung Cancer (NSCLC) remains a critical unmet need. Existing radiomics and deep learning-based predictive models rely primarily on pre-treatment imaging to predict categorical response outcomes, limiting their ability to capture the complex morphological and textural transformations induced by immunotherapy. This study introduces ImmunoDiff, an anatomy-aware diffusion model designed to synthesize post-treatment CT scans from baseline imaging while incorporating clinically relevant constraints. The proposed framework integrates anatomical priors, specifically lobar and vascular structures, to enhance fidelity in CT synthesis. Additionally, we introduce a novel cbi-Adapter, a conditioning module that ensures pairwise-consistent multimodal integration of imaging and clinical data embeddings, to refine the generative process. Additionally, a clinical variable conditioning mechanism is introduced, leveraging demographic data, blood-based biomarkers, and PD-L1 expression to refine the generative process. Evaluations on an in-house NSCLC cohort treated with immune checkpoint inhibitors demonstrate a 21.24% improvement in balanced accuracy for response prediction and a 0.03 increase in c-index for survival prediction. Code will be released soon.