Longitudinal NSCLC Treatment Progression via Multimodal Generative Models
This work addresses the critical challenge of predicting tumor evolution during radiotherapy for NSCLC patients, aiming to improve in-silico treatment monitoring and adaptive radiotherapy research.
This paper introduces a Virtual Treatment (VT) framework to predict non-small cell lung cancer (NSCLC) progression during radiotherapy by synthesizing follow-up CT images based on baseline CT, clinical variables, and radiation dose increments. Diffusion-based models within this framework consistently produced more stable and anatomically plausible tumor evolution trajectories compared to GAN-based baselines.
Predicting tumor evolution during radiotherapy is a clinically critical challenge, particularly when longitudinal changes are driven by both anatomy and treatment. In this work, we introduce a Virtual Treatment (VT) framework that formulates non-small cell lung cancer (NSCLC) progression as a dose-aware multimodal conditional image-to-image translation problem. Given a CT scan, baseline clinical variables, and a specified radiation dose increment, VT aims to synthesize plausible follow-up CT images reflecting treatment-induced anatomical changes. We evaluate the proposed framework on a longitudinal dataset of 222 stage III NSCLC patients, comprising 895 CT scans acquired during radiotherapy under irregular clinical schedules. The generative process is conditioned on delivered dose increments together with demographic and tumor-related clinical variables. Representative GAN-based and diffusion-based models are benchmarked across 2D and 2.5D configurations. Quantitative and qualitative results indicate that diffusion-based models benefit more consistently from multimodal, dose-aware conditioning and produce more stable and anatomically plausible tumor evolution trajectories than GAN-based baselines, supporting the potential of VT as a tool for in-silico treatment monitoring and adaptive radiotherapy research in NSCLC.