Mechanistic Learning with Guided Diffusion Models to Predict Spatio-Temporal Brain Tumor Growth

2025-09-11

AI Summary

Accurate spatiotemporal prediction of brain tumor progression is critical for clinical decision-making. This paper proposes a mechanism-guided diffusion generative framework that embeds ordinary differential equation (ODE)-based tumor dynamics—including radiotherapy effects—into the DDIM denoising process, enabling biologically constrained MRI sequence generation via gradient guidance. A novel tumor growth probability map is introduced to explicitly model directional growth patterns and spatial extent, significantly enhancing biological plausibility and anatomical fidelity in four-dimensional predictions under limited-data conditions. Evaluated on pediatric diffuse midline glioma data, our method generates high-fidelity longitudinal MRI volumes, achieving superior spatial similarity metrics versus baselines and accurate localization of tumor growth regions, as confirmed by 95% Hausdorff distance. To our knowledge, this is the first end-to-end system integrating mechanistic modeling with diffusion-based generation, establishing a new paradigm for interpretable and verifiable medical image forecasting.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Predicting the spatio-temporal progression of brain tumors is essential for guiding clinical decisions in neuro-oncology. We propose a hybrid mechanistic learning framework that combines a mathematical tumor growth model with a guided denoising diffusion implicit model (DDIM) to synthesize anatomically feasible future MRIs from preceding scans. The mechanistic model, formulated as a system of ordinary differential equations, captures temporal tumor dynamics including radiotherapy effects and estimates future tumor burden. These estimates condition a gradient-guided DDIM, enabling image synthesis that aligns with both predicted growth and patient anatomy. We train our model on the BraTS adult and pediatric glioma datasets and evaluate on 60 axial slices of in-house longitudinal pediatric diffuse midline glioma (DMG) cases. Our framework generates realistic follow-up scans based on spatial similarity metrics. It also introduces tumor growth probability maps, which capture both clinically relevant extent and directionality of tumor growth as shown by 95th percentile Hausdorff Distance. The method enables biologically informed image generation in data-limited scenarios, offering generative-space-time predictions that account for mechanistic priors.

Problem

• Predict spatio-temporal brain tumor growth progression
• Synthesize anatomically feasible future MRI scans
• Generate tumor growth probability maps with directionality

Innovation

• Hybrid mechanistic learning with diffusion models
• Mathematical tumor growth modeling with ODEs
• Gradient-guided DDIM for realistic MRI synthesis