ImmunoDiff: A Diffusion Model for Immunotherapy Response Prediction in Lung Cancer

TL;DR

ImmunoDiff is a novel diffusion model that synthesizes post-treatment CT scans from baseline images, incorporating anatomical and clinical data to improve immunotherapy response prediction in lung cancer.

Contribution

The paper introduces ImmunoDiff, a diffusion-based framework that integrates anatomical priors and clinical variables for enhanced CT synthesis and response prediction in NSCLC.

Findings

21.24% improvement in response prediction accuracy

0.03 increase in survival prediction c-index

Effective integration of anatomical and clinical data

Abstract

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.