Longitudinal NSCLC Treatment Progression via Multimodal Generative Models

TL;DR

This paper introduces a multimodal generative modeling framework to predict tumor evolution in NSCLC during radiotherapy, enabling in-silico treatment monitoring and adaptive planning.

Contribution

The work presents a novel dose-aware image translation model for longitudinal tumor progression prediction in NSCLC, benchmarking GAN and diffusion models on clinical data.

Findings

Diffusion models outperform GANs in stability and plausibility.

The framework accurately simulates treatment-induced anatomical changes.

Potential to improve adaptive radiotherapy strategies.

Abstract

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.