Rectified flow-based prediction of post-treatment brain MRI from pre-radiotherapy priors for patients with glioma

TL;DR

This study presents a rectified flow-based AI model that predicts follow-up brain MRI scans from pre-treatment data, enabling real-time, realistic, and personalized post-treatment imaging for glioma patients.

Contribution

The paper introduces a novel rectified flow model for conditional MRI prediction that is faster and more accurate than existing diffusion models, supporting personalized treatment planning.

Findings

Generates realistic follow-up MRI with high SSIM and Dice scores

Achieves up to 250x faster inference than diffusion models

Enables counterfactual treatment simulations for personalized care

Abstract

Purpose/Objective: Brain tumors result in 20 years of lost life on average. Standard therapies induce complex structural changes in the brain that are monitored through MRI. Recent developments in artificial intelligence (AI) enable conditional multimodal image generation from clinical data. In this study, we investigate AI-driven generation of follow-up MRI in patients with in- tracranial tumors through conditional image generation. This approach enables realistic modeling of post-radiotherapy changes, allowing for treatment optimization. Material/Methods: The public SAILOR dataset of 25 patients was used to create a 2D rectified flow model conditioned on axial slices of pre-treatment MRI and RT dose maps. Cross-attention conditioning was used to incorporate temporal and chemotherapy data. The resulting images were validated with structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), Dice scores and Jacobian determinants. Results: The resulting model generates realistic follow-up MRI for any time point, while integrating treatment information. Comparing real versus predicted images, SSIM is 0.88, and PSNR is 22.82. Tissue segmentations from real versus predicted MRI result in a mean Dice-S{\o}rensen coefficient (DSC) of 0.91. The rectified flow (RF) model enables up to 250x faster inference than Denoising Diffusion Probabilistic Models (DDPM). Conclusion: The proposed model generates realistic follow-up MRI in real-time, preserving both semantic and visual fidelity as confirmed by image quality metrics and tissue segmentations. Conditional generation allows counterfactual simulations by varying treatment parameters, producing predicted morphological changes. This capability has potential to support adaptive treatment dose planning and personalized outcome prediction for patients with intracranial tumors.