arXiv:2609.14312v1 Announce Type: new Abstract: Multi-shell diffusion MRI (dMRI) unlocks more expressive microstructural modeling than single-shell scans, yet its longer acquisition time hinders depl...
The paper introduces a 3D residual wavelet diffusion model for super‑resolving ultra low‑field MRI scans. By using a lossless wavelet reparameterisation, residual shifting, and domain randomisation, the method fits whole‑brain data on a single GPU, speeds up sampling, and generalises across scanners. It achieves volumetric accuracy comparable to leading regression approaches while producing per‑voxel uncertainty maps that reveal under‑determined regions and preserves disease‑relevant atrophy in cognitively impaired subjects.
The paper introduces a transfer‑learning framework that pre‑trains an implicit neural representation (INR) on a high‑resolution diffusion MRI template and then adapts it to individual subjects through registration and fine‑tuning. This approach enables native single‑subject super‑resolution, achieving a 4× through‑plane up‑sampling from 5 mm to 1.25 mm on Human Connectome Project data. Compared to a recent baseline, the method reduces NRMSE by 36–49 % and increases FSIM by 24–43 %, while training 6× faster and outperforming other INR‑based techniques on both image quality and domain‑specific metrics.
arXiv:2603. 05693v2 Announce Type: replace-cross Abstract: Accurate longitudinal analysis of brain MRI is often hindered by evolving lesions, which bias automated neuroimaging pipelines.
The paper introduces a subject‑specific spatial‑angular Gaussian field for self‑supervised joint k‑q diffusion MRI reconstruction. It uses shared 3D Gaussian primitives that provide local spatial support while each primitive carries a continuous q‑conditioned tensor‑residual response, allowing the signal at each location to be synthesized from overlapping primitive responses. Experiments on three HCP diffusion shells with various acceleration settings show consistent improvements in missing‑direction DWI reconstruction, tensor‑derived metrics, and principal diffusion orientation estimation.
The paper introduces AWR-Net, a two‑stage framework that decouples anatomy and appearance to synthesize realistic 3D fetal brain ultrasound volumes from anatomical label maps. The first stage uses wavelet diffusion to generate volumes from atlas pairs in the wavelet domain, while the second stage applies residual refinement in the image domain to adapt to real ultrasound appearance. Experiments on real fetal brain ultrasound data show that AWR‑Net outperforms existing synthesis methods, improving metrics such as normalized cross‑correlation and Fréchet Inception Distance, and also enhances downstream segmentation, especially for severe abnormal cases.
The paper introduces a multimodal latent diffusion model that jointly synthesizes volumetric MRI scans and tabular clinical data within a shared latent space using cross‑attention. By fusing the modalities through a variational autoencoder before diffusion, the model reconstructs MRI and tabular data with separate decoders, producing anatomically plausible images that align with synthesized clinical attributes. Evaluation on the German National Cohort dataset shows high‑fidelity image generation and superior tabular performance compared to CTGAN, marking the first demonstration of joint MRI‑tabular modeling in a single diffusion framework.
arXiv:2610.09376v1 Announce Type: new Abstract: Acquiring a complete set of magnetic resonance imaging (MRI) contrasts is time-intensive and uncomfortable for patients, despite the diagnostic value o...
The paper introduces CM-RED, a fast MRI reconstruction method that combines a pretrained consistency model with the regularization by denoising framework. By integrating controlled noise injection into accelerated proximal gradient updates, CM-RED achieves high‑quality reconstructions on fastMRI knee and brain datasets with only four network function evaluations. It consistently outperforms existing diffusion‑ and consistency‑based approaches in quantitative metrics, visual fidelity, and robustness to hyperparameter changes.
While whole-body multimodal medical imaging scanners have been increasingly recognized for more effective medical applications, the excessive long acquisition time in PET-MR scanning is a major obstacle in more efficient clinical practice. Deep learning-based MRI translation provides a potential solution to reduce scan duration.
The paper introduces a perceptually regularized diffusion framework for image super‑resolution, adding perceptual‑loss based regularization to the standard diffusion training objective. This approach incorporates prior knowledge to improve training convergence and encourages the recovery of meaningful image features. Experiments on benchmark datasets show enhanced perceptual quality while maintaining competitive distortion metrics.
The paper presents a systematic comparison of recurrent neural networks and Transformer models for iterative diffusion MRI tractography, focusing on training strategies, input representations, and hyperparameter tuning. It introduces a generation‑validation phase that provides streamline‑level supervision, enabling the models to achieve the best performance reported on the ISMRM2015 challenge dataset. The study also evaluates the effects of missing bundles, noisy training data, and invalid fibers, and demonstrates applicability to in‑vivo data from the Tractoinferno database.