Exploring Strategies for Personalized Radiation Therapy Part II Predicting Tumor Drift Patterns with Diffusion Models

TL;DR

This paper introduces a novel diffusion model framework to predict tumor evolution in personalized radiotherapy, enabling early adaptive treatment decisions and improving safety and efficacy in brain cancer therapy.

Contribution

It develops a diffusion model-based approach to simulate tumor response, addressing limitations of existing radiomics models in predicting spatial and temporal tumor evolution.

Findings

Diffusion models effectively simulate patient-specific tumor evolution.

The approach localizes regions associated with treatment response.

It provides a foundation for early, adaptive radiotherapy interventions.

Abstract

Radiation therapy outcomes are decided by two key parameters, dose and timing, whose best values vary substantially across patients. This variability is especially critical in the treatment of brain cancer, where fractionated or staged stereotactic radiosurgery improves safety compared to single fraction approaches, but complicates the ability to predict treatment response. To address this challenge, we employ Personalized Ultra-fractionated Stereotactic Adaptive Radiotherapy (PULSAR), a strategy that dynamically adjusts treatment based on how each tumor evolves over time. However, the success of PULSAR and other adaptive approaches depends on predictive tools that can guide early treatment decisions and avoid both overtreatment and undertreatment. However, current radiomics and dosiomics models offer limited insight into the evolving spatial and temporal patterns of tumor response. To overcome these limitations, we propose a novel framework using Denoising Diffusion Implicit Models (DDIM), which learns data-driven mappings from pre to post treatment imaging. In this study, we developed single step and iterative denoising strategies and compared their performance. The results show that diffusion models can effectively simulate patient specific tumor evolution and localize regions associated with treatment response. The proposed strategy provides a promising foundation for modeling heterogeneous treatment response and enabling early, adaptive interventions, paving the way toward more personalized and biologically informed radiotherapy.