Spatio-Temporal Mixture-of-Modality-Experts Diffusion for Quantitative DCE-MRI Synthesis from Incomplete MR Sequences

• URL: http://arxiv.org/abs/2606.25535v1
• Date: Wed, 24 Jun 2026 08:10:27 GMT
• Title: Spatio-Temporal Mixture-of-Modality-Experts Diffusion for Quantitative DCE-MRI Synthesis from Incomplete MR Sequences
• Abstract summary: ST-MoME is a conditional diffusion framework that synthesizes 3D DCE parameter maps from diverse subsets multimodal MRI.<n>It performs diffusion directly in image space with 3D patch-based training and a Swin-based backbone.<n>It achieves the lowest mean Normalized Mean Square Error (NMSE) aggregated across all three DCE parameters, with leading performance on $v_p$ and $v_e$, competitive results on $Kmathrmtrans$, and the lowest reconstruction error within the clinically critical tumor region.
• Score: 2.4827516038838064
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantitative maps from dynamic contrast-enhanced MRI (DCE-MRI) are essential for tumor assessment but are often unavailable due to contrast-agent risks and protocol variability. Prior methods predict these maps from other MRI modalities, yet most assume fixed, fully observed inputs and fail under realistic missingness. We present Spatio-Temporal Mixture-of-Modality-Experts (ST-MoME), a conditional diffusion framework that synthesizes 3D DCE parameter maps from diverse subsets of multimodal MRI. ST-MoME fuses modality-specific expert features through a spatio-temporal gating network that produces voxel-wise, timestep-dependent weights, forming a conditioning tensor that guides denoising. To preserve quantitative fidelity, ST-MoME performs diffusion directly in image space with 3D patch-based training and a Swin-based backbone. On a clinical brain-tumor cohort of 386 patients, we evaluate ST-MoME across 16 controlled modality-availability scenarios. It achieves the lowest mean Normalized Mean Square Error (NMSE) aggregated across all three DCE parameters, with leading performance on $v_p$ and $v_e$, competitive results on $K^{\mathrm{trans}}$, and the lowest reconstruction error within the clinically critical tumor region. A post-hoc analysis of the learned gating dynamics shows a structural-early, physiological-late fusion schedule consistent with clinical intuition.

Related papers

• MUMINS: Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis [12.80647654676651]
  We propose MUMINS (Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis), an efficient diffusion framework.<n>It jointly diffuses a baseline scan and its follow-up residual, summed to synthesize the follow-up scan, while concurrently predicting a spatial uncertainty map.<n>Designed without organ-specifics, the same architecture is reused across anatomies via separate, dataset-specific retraining.
  arXiv  Detail & Related papers  (2026-09-15T13:32:37Z)
• 3D Classification of Paramagnetic Rim Lesions in Multiple Sclerosis via Asymmetric QSM-FLAIR Modeling [4.672573934670909]
  Paramagnetic rim lesions (Rim$+$) identified on susceptibility-sensitive MRI have recently emerged as a specific biomarker of chronic active inflammation in Multiple Sclerosis (MS)<n>We propose a 3D multimodal deep learning framework for lesion-level Rim$+$/Rim$-$ classification from Quantitative Susceptibility Mapping (QSM) and FLAIR MRI.
  arXiv  Detail & Related papers  (2026-06-15T14:10:30Z)
• Wavelet-Fusion Diffusion Model for Multimodal Brain MRI Synthesis with Modality and Metadata Conditioning [0.0]
  Multimodal MRI provides complementary information for neuroimaging analysis, where different imaging modalities capture distinct anatomical, tissue, and pathological features.<n>Large-scale structural MRI resources are increasingly available, but their modality coverage is often uneven across public and pooled neuroimaging datasets.<n>Our approach combines a Wavelet-Fusion variational autoencoder (WF-VAE) latent compressor with a conditional 3D U-Net diffusion model trained in the learned latent space.
  arXiv  Detail & Related papers  (2026-05-30T11:57:27Z)
• D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities [54.87947751720332]
  We propose a novel segmentation model D3Seg to maintain stable performance under missing-modality settings.<n>The proposed model achieves approximately 1.5-2.0% Dice improvement on enhancing tumor (ET) and around 1.0% on tumor core (TC) across multiple missing modality configurations.
  arXiv  Detail & Related papers  (2026-05-21T09:55:42Z)
• Mamba-driven MRI-to-CT Synthesis for MRI-only Radiotherapy Planning [4.3531418255555545]
  Mamba is a state-space model for cross-modality translation.<n>We adapt both the U-Mamba and the SegMamba architecture, originally proposed for segmentation, to perform cross-modality image generation.<n>Our 3D Mamba architecture effectively captures complex features and long-range volumetric dependencies, thus allowing accurate CT synthesis.
  arXiv  Detail & Related papers  (2026-03-24T14:56:39Z)
• A Systematic Benchmark of GAN Architectures for MRI-to-CT Synthesis [38.31064949197421]
  Generative Adversarial Network (GAN) architectures have been proposed for MRI-to-CT translation.<n>We present a benchmark of ten GAN evaluated on the SynthRAD2025 dataset across three anatomical districts.
  arXiv  Detail & Related papers  (2026-03-13T18:54:20Z)
• TriFusion-SR: Joint Tri-Modal Medical Image Fusion and SR [42.84193423224821]
  Multimodal medical image fusion facilitates comprehensive diagnosis by aggregating complementary structural and functional information.<n>Existing approaches typically perform image fusion and super-resolution (SR) in separate stages, leading to artifacts and degraded perceptual quality.<n>We propose TriFusionSR, a wavelet-guided conditional diffusion framework for joint tri-modal fusion and SR.
  arXiv  Detail & Related papers  (2026-03-10T14:13:40Z)
• UniField: A Unified Field-Aware MRI Enhancement Framework [45.03230466428695]
  methodname is a unified framework integrating multiple modalities and enhancement tasks.<n>We exploit comprehensive 3D volumetric information by leveraging pre-trained 3D foundation models.<n>We organize and publicly release a comprehensive paired multi-field MRI dataset.
  arXiv  Detail & Related papers  (2026-03-10T05:45:12Z)
• MIRAGE: Knowledge Graph-Guided Cross-Cohort MRI Synthesis for Alzheimer's Disease Prediction [15.543131466384658]
  We introduce MIRAGE, a novel framework that reframes the missing-MRI problem as an anatomy-guided cross-modal latent distillation task.<n>We employ a frozen pre-trained 3D U-Net decoder strictly as an auxiliary regularization engine.<n>Experiments demonstrate that our framework successfully bridges the missing-modality gap, improving the AD classification rate by 13%.
  arXiv  Detail & Related papers  (2026-03-02T22:17:37Z)
• Revisiting Global Token Mixing in Task-Dependent MRI Restoration: Insights from Minimal Gated CNN Baselines [43.505945728449774]
  Global token mixing has become a popular model design choice for MRI restoration.<n>We ask whether global token mixing is actually beneficial in each individual task across three representative settings.<n>For accelerated MRI reconstruction, the minimal unrolled gated-CNN baseline is already highly competitive.<n>For super-resolution, where low-frequency k-space data are largely preserved by the controlled low-pass degradation, local gated models remain competitive.<n>For denoising with pronounced spatially heteroscedastic noise, token-mixing models achieve the strongest overall performance.
  arXiv  Detail & Related papers  (2026-03-02T04:57:52Z)
• Flow Matching for Conditional MRI-CT and CBCT-CT Image Synthesis [0.0]
  Flow Matching framework is used to generate synthetic CT from MRI or CBCT images.<n>We train models for MRI sCT and CBCT sCT across three anatomical regions.<n>The results indicate that the method accurately reconstructs global anatomical structures.<n>Future work will explore patch-based training and latent-space flow models to improve resolution and local structural fidelity.
  arXiv  Detail & Related papers  (2025-10-06T14:07:03Z)
• JSover: Joint Spectrum Estimation and Multi-Material Decomposition from Single-Energy CT Projections [45.14515691206885]
  Multi-material decomposition (MMD) enables quantitative reconstruction of tissue compositions in the human body.<n>Traditional MMD typically requires spectral CT scanners and pre-measured X-ray energy spectra, significantly limiting clinical applicability.<n>This paper proposes JSover, a fundamentally reformulated one-step SEMMD framework that jointly reconstructs multi-material compositions and estimates the energy spectrum directly from SECT projections.
  arXiv  Detail & Related papers  (2025-05-12T23:32:21Z)
• A Unified Model for Compressed Sensing MRI Across Undersampling Patterns [69.19631302047569]
  We propose a unified MRI reconstruction model robust to various measurement undersampling patterns and image resolutions.<n>Our model improves SSIM by 11% and PSNR by 4 dB over a state-of-the-art CNN (End-to-End VarNet) with 600$times$ faster inference than diffusion methods.
  arXiv  Detail & Related papers  (2024-10-05T20:03:57Z)
• NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation [55.51412454263856]
  This paper proposes to directly modulate the generation process of diffusion models using fMRI signals. By training with about 67,000 fMRI-image pairs from various individuals, our model enjoys superior fMRI-to-image decoding capacity.
  arXiv  Detail & Related papers  (2024-03-27T02:42:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.