Pre to Post-Treatment Glioblastoma MRI Prediction using a Latent Diffusion Model

2025-10-13

AI Summary

To address the delayed assessment of treatment response in glioblastoma (GBM) patients—current clinical MRI evaluation requires ≥2 months—this work proposes a slice-level post-treatment MRI synthesis method based on latent diffusion models (LDMs), enabling early visual prediction from pre- to post-treatment imaging. We introduce a novel tiled conditional input scheme that fuses pre-treatment T1-weighted contrast-enhanced (T1-Gd) MRI with tumor localization masks, and incorporate classifier-free guidance to embed patient overall survival information into the generative process, thereby enhancing clinical plausibility. Evaluated on a local cohort of 140 GBM patients, the model generates realistic post-treatment MRI volumes consistent with observed tumor evolution patterns. Quantitative and qualitative analyses demonstrate significant improvement in early treatment response discrimination compared to conventional approaches. The method provides interpretable, visually grounded evidence to support personalized therapeutic decision-making.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Glioblastoma (GBM) is an aggressive primary brain tumor with a median survival of approximately 15 months. In clinical practice, the Stupp protocol serves as the standard first-line treatment. However, patients exhibit highly heterogeneous therapeutic responses which required at least two months before first visual impact can be observed, typically with MRI. Early prediction treatment response is crucial for advancing personalized medicine. Disease Progression Modeling (DPM) aims to capture the trajectory of disease evolution, while Treatment Response Prediction (TRP) focuses on assessing the impact of therapeutic interventions. Whereas most TRP approaches primarly rely on timeseries data, we consider the problem of early visual TRP as a slice-to-slice translation model generating post-treatment MRI from a pre-treatment MRI, thus reflecting the tumor evolution. To address this problem we propose a Latent Diffusion Model with a concatenation-based conditioning from the pre-treatment MRI and the tumor localization, and a classifier-free guidance to enhance generation quality using survival information, in particular post-treatment tumor evolution. Our model were trained and tested on a local dataset consisting of 140 GBM patients collected at Centre François Baclesse. For each patient we collected pre and post T1-Gd MRI, tumor localization manually delineated in the pre-treatment MRI by medical experts, and survival information.

Problem

• Predicting post-treatment glioblastoma MRI scans from pre-treatment images
• Modeling tumor evolution using latent diffusion for treatment response prediction
• Addressing heterogeneous therapeutic responses through early visual prediction

Innovation

• Latent Diffusion Model for MRI prediction
• Concatenation-based conditioning with tumor localization
• Classifier-free guidance using survival information