mlsanityData to 14 Oct 2026

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

arXiv 2509.24194 ↗First posted 29 Sep 2025cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 20 of its 45 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

20 of 45 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Self-Supervised Adversarial Diffusion Models for Fast MRI Reconstruction21 Jun
  2. 2023Synthetic CT Generation from MRI using 3D Transformer-based Denoising Diffusion Model31 May
  3. 2023Cycle-guided Denoising Diffusion Probability Model for 3D Cross-modality MRI Synthesis28 Apr
  4. 2023Memory-Efficient 3D Denoising Diffusion Models for Medical Image Processing27 Mar

Other references · 16

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  8. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  9. 2019Automated brain extraction of multi-sequence MRI using artificial neural networkscited by 134
  10. 2023DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generationcited by 110
  11. 2020Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoderscited by 30
  12. 2025Unifying Biomedical Vision-Language Expertise: Towards a Generalist Foundation Model via Multi-CLIP Knowledge Distillationcited by 8
4 more
  1. 2022Instability and Local Minima in GAN Training with Kernel Discriminatorscited by 7
  2. 2024Deep Learning Based Apparent Diffusion Coefficient Map Generation from Multi-parametric MR Images for Patients with Diffuse Gliomascited by 3
  3. 2024T1-contrast Enhanced MRI Generation from Multi-parametric MRI for Glioma Patients with Latent Tumor Conditioningcited by 3
  4. 2025Interactive Gadolinium-Free MRI Synthesis: A Transformer with Localization Prompt Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Conditional Generative Models for Contrast-Enhanced Synthesis of T1w and T1 Maps in Brain MRI
  2. 2025Synthesizing Accurate and Realistic T1-weighted Contrast-Enhanced MR Images using Posterior-Mean Rectified Flow
  3. 2024Towards Learning Contrast Kinetics with Multi-Condition Latent Diffusion Models
  4. 2022DS3-Net: Difficulty-perceived Common-to-T1ce Semi-Supervised Multimodal MRI Synthesis Network
  5. 2026Anatomically-conditioned Latent Diffusion Model for Data-Efficient Few-Shot Cross-Domain 3D Glioma MRI Synthesis
  6. 20263D-LLDM: Label-Guided 3D Latent Diffusion Model for Improving High-Resolution Synthetic MR Imaging in Hepatic Structure Segmentation
  7. 2025Diffusion-Based Synthesis of 3D T1w MPRAGE Images from Multi-Echo GRE with Multi-Parametric MRI Integration
  8. 20263D-GlioPREDICT: 3D Latent Diffusion for Post-Radiotherapy Brain MRI Prediction in Patients with Glioma