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

TL;DR

This paper introduces a latent diffusion model that predicts post-treatment glioblastoma MRI from pre-treatment scans, enabling early assessment of treatment response and tumor evolution for personalized medicine.

Contribution

It presents a novel slice-to-slice translation approach using a latent diffusion model conditioned on pre-treatment MRI and tumor localization, incorporating survival data to improve prediction quality.

Findings

Model trained on 140 GBM patients with MRI and survival data.

Generated post-treatment MRI accurately reflects tumor evolution.

Enhanced prediction quality with classifier-free guidance and survival information.

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 Fran\c{c}ois 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.