An Efficient 3D Latent Diffusion Model for T1-contrast Enhanced MRI Generation

2025-09-28

AI Summary

To address the clinical risks of nephrogenic systemic fibrosis in high-risk patients and imaging inconsistencies caused by gadolinium-based contrast agents (GBCAs), this work proposes a gadolinium-free method for synthesizing T1-weighted contrast-enhanced (T1C) MRI images. We introduce T1C-RFlow, a 3D latent-space rectified flow model that jointly leverages a pretrained autoencoder to extract latent representations from T1-weighted and T2-FLAIR inputs, then performs efficient diffusion-based generation directly in the latent space. Evaluated on the BraTS 2024 dataset across glioma, meningioma, and metastasis cases, our method achieves superior performance: NMSE = 0.044, SSIM = 0.937, and inference time of only 6.9 seconds per case—several times faster than conventional diffusion models—while preserving lesion fidelity. The key contribution is the first integration of rectified flow into multi-parametric MRI latent-space T1C synthesis, uniquely balancing clinical safety, reconstruction quality, and computational efficiency.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Objective: Gadolinium-based contrast agents (GBCAs) are commonly employed with T1w MRI to enhance lesion visualization but are restricted in patients at risk of nephrogenic systemic fibrosis and variations in GBCA administration can introduce imaging inconsistencies. This study develops an efficient 3D deep-learning framework to generate T1-contrast enhanced images (T1C) from pre-contrast multiparametric MRI. Approach: We propose the 3D latent rectified flow (T1C-RFlow) model for generating high-quality T1C images. First, T1w and T2-FLAIR images are input into a pretrained autoencoder to acquire an efficient latent space representation. A rectified flow diffusion model is then trained in this latent space representation. The T1C-RFlow model was trained on a curated dataset comprised of the BraTS 2024 glioma (GLI; 1480 patients), meningioma (MEN; 1141 patients), and metastases (MET; 1475 patients) datasets. Selected patients were split into train (N=2860), validation (N=612), and test (N=614) sets. Results: Both qualitative and quantitative results demonstrate that the T1C-RFlow model outperforms benchmark 3D models (pix2pix, DDPM, Diffusion Transformers (DiT-3D)) trained in the same latent space. T1C-RFlow achieved the following metrics - GLI: NMSE 0.044 +/- 0.047, SSIM 0.935 +/- 0.025; MEN: NMSE 0.046 +/- 0.029, SSIM 0.937 +/- 0.021; MET: NMSE 0.098 +/- 0.088, SSIM 0.905 +/- 0.082. T1C-RFlow had the best tumor reconstruction performance and significantly faster denoising times (6.9 s/volume, 200 steps) than conventional DDPM models in both latent space (37.7s, 1000 steps) and patch-based in image space (4.3 hr/volume). Significance: Our proposed method generates synthetic T1C images that closely resemble ground truth T1C in much less time than previous diffusion models. Further development may permit a practical method for contrast-agent-free MRI for brain tumors.

Problem

• Generating T1-contrast enhanced MRI without gadolinium contrast agents
• Overcoming imaging inconsistencies from variable contrast agent administration
• Creating synthetic T1C images from pre-contrast multiparametric MRI scans

Innovation

• Uses pre-contrast MRI to generate contrast-enhanced images
• Employs a 3D latent rectified flow diffusion model
• Leverages pretrained autoencoder for efficient latent space