arXiv:2609. 20562v1 Announce Type: new Abstract: Automated quality assessment, enhancement, and segmentation of multiple structures in $0.
arXiv:2511. 14897v2 Announce Type: replace-cross Abstract: We present an unsupervised single image bidirectional Magnetic Resonance Image (MRI) synthesizer that synthesizes an Ultra-Low Field (ULF) like image from a High-Field (HF) magnitude image and vice-versa.
The paper introduces AURA, an nnU-Net-based asymmetric supervision strategy for segmenting ultra‑low‑field (0.064 T) pediatric brain MRI. It treats high‑field‑derived (HF) and low‑field‑edited (LF) annotations as distinct observations, anchoring training to the HF mask while gating LF contributions through a reliability mechanism. On a 16‑case development split, AURA achieved Dice scores comparable to HF‑only training and improved boundary metrics, demonstrating its potential for ULF MRI segmentation.
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.
arXiv:2606. 18354v1 Announce Type: cross Abstract: Recent advances in generative machine learning models have significantly improved medical imaging, offering promising solutions for data augmentation, privacy preservation, and improved model generalization.
arXiv:2606. 15457v1 Announce Type: cross Abstract: 3D FLAIR MRI is widely recommended as one of the standard MRI sequences for brain imaging in multiple sclerosis (MS), but publicly available MS datasets remain relatively small and vary across scanners, acquisition protocols, and lesion patterns.
The paper presents a unified conditional model for translating brain MRI scans across different field strengths and modalities using conditional latent bridge matching. The single model achieves competitive results on all three tasks of the MRIxFields2026 challenge without task‑specific architectures, and it generates 30 axial slices in under 90 seconds or a full volume in under 70 seconds on a single NVIDIA A5000 GPU. Extensive ablations of the model’s components are also provided.
arXiv:2606. 24313v1 Announce Type: new Abstract: AI-driven image-to-image synthesis is rapidly advancing, with growing applications in medical imaging.
arXiv:2607. 17782v1 Announce Type: cross Abstract: Foundation models pretrained using self-supervised learning have transformed computer vision by learning transferable representations from large-scale unlabeled data.
The paper presents LoFi RADIO, a distilled ViT-S backbone designed for grading the severity of seven common artifacts in ultra‑low‑field neonatal brain MRI. It tackles the LISA 2026 Task 1a challenge by evaluating various backbones paired with a classification MLP, finding no single backbone dominates across all artifacts. The authors improve performance by routing complementary foundation model teachers through a per‑artifact gate and by distilling these teachers into the single in‑domain student, achieving comparable or better weighted composite scores without the need for multiple large models at inference.
arXiv:2609.00960v1 Announce Type: new Abstract: Magnetic resonance images of the same subject look markedly different across field strengths, which complicates the comparison and pooling of data acro...
arXiv:2603. 03710v3 Announce Type: replace-cross Abstract: Zero-shot MRI reconstruction relies on generative priors, but single-modality unconditional priors produce hallucinations under severe ill-posedness.