We evaluated synthetic pretraining and multi-cohort transfer learning for deep learning-based super-resolution of intracranial 4D Flow MRI across heterogeneous neurologic cohorts. This mixed prospecti...
arXiv:2610.33124v1 Announce Type: cross Abstract: 4D Flow MRI promises opportunities for non-invasive mapping of neurovascular hemodynamics, but its clinical utility faces trade-offs between resoluti...
The paper presents a deep learning super‑resolution framework for 4D flow MRI of carotid arteries, using convolutional block attention modules to focus on clinically relevant spatial features and reduce noise. Trained on 120 patients with 240 stenosed carotid arteries, the model leverages patient‑specific CFD simulations as high‑resolution ground truth. Results show a significant reduction in RMSE and improved reconstruction of complex flow patterns compared to a baseline without attention.
The study introduces a physics‑guided, self‑supervised deep learning framework that estimates macromolecular pool fraction (MPF) maps directly from conventional clinical brain MRI sequences (T1‑, T2‑, and FLAIR) without requiring specialized quantitative magnetization transfer scans. By embedding an analytical two‑pool magnetization transfer model and conditioning on acquisition parameters, the method was trained on 7,705 multisite, multivendor MRI sessions and achieved consistent MPF values across vendors and protocols, with a 35.6% reduction in lesions of demyelinating disease compared to normal‑appearing white matter. Cross‑protocol validation in a healthy volunteer showed a mean voxel‑wise absolute difference of 7.7% and a concordance correlation coefficient of 0.888, demonstrating robust cross‑protocol performance.
The study presents a multimodal BrainAGE framework that fuses structural T1-weighted MRI with DeepCBV maps—vascular information synthesized from non‑contrast MRI—to estimate brain age more accurately. Using two separate 3D convolutional neural networks, the combined model achieved a mean absolute error of 3.95 years on cognitively normal controls, outperforming single‑modality models. Saliency analyses showed MRI highlighted white matter and cortical atrophy, while DeepCBV emphasized vascular‑rich regions, and the integrated approach revealed stronger differentiation between stable and progressive MCI, indicating sensitivity to early vascular changes.
X‑LMC is a spatiotemporal deep‑learning framework that automatically scores leptomeningeal collateral (LMC) status from time‑resolved biplane digital subtraction angiography (DSA). It uses a DINOv2 backbone to encode spatial frames, a token‑level cross‑view attention module to fuse orthogonal projections, and a recurrent network to model contrast bolus dynamics. On a multicenter dataset of 134 M1‑segment occlusion patients, X‑LMC achieved a Quadratic Weighted Kappa of 0.398 and a macro‑F1 of 0.711, outperforming static and other spatiotemporal baselines and matching clinical inter‑rater agreement.
This study presents a domain-aware deep learning framework based on nnU-Net for segmenting ischemic stroke lesions on non‑contrast CT scans and quantifying net water uptake (NWU). Trained on data from Hamburg and the Acute Ischemic Stroke Dataset, the model was fine‑tuned on small target‑domain subsets from Boston and ISLES, achieving median Dice scores of 0.68 and 0.56 for lesions ≥30 mL, and an NWU mean absolute error of 1.37 percentage points on the Boston cohort. The results demonstrate that target‑domain adaptation can enable accurate NCCT‑only infarct segmentation and low‑error NWU estimation across heterogeneous multicenter datasets.
FlowMoDL is an unrolled neural network designed for highly accelerated 4D flow MRI reconstruction, optimizing both anatomical magnitude and phase-derived velocity accuracy. It alternates a learned (3+1)D spatiotemporal denoiser with conjugate‑gradient data‑consistency updates, using a dual‑pathway conditioning scheme to handle acceleration factors from 10× to 50×. Trained with a deep‑supervision composite loss that penalizes velocity magnitude and angular errors, FlowMoDL outperforms classical and deep‑learning baselines on the multi‑center CMRx4DFlow dataset, achieving superior gradient‑step efficiency and robust convergence across all acceleration factors.
arXiv:2608. 00073v1 Announce Type: cross Abstract: Rigorous dataset partitioning is a foundational, yet frequently overlooked, prerequisite for reliable deep learning in longitudinal medical imaging.
arXiv:2609.22377v2 Announce Type: replace-cross Abstract: Intrathecal contrast-enhanced MRI shows how a tracer injected into the cerebrospinal fluid spreads through the brain, but requires repeated s...
The paper introduces Neuro‑JEPA, a sparse multimodal foundation model that learns unified representations of brain MRI across T1w, T2w, and FLAIR sequences using a latent predictive objective and a Mixture‑of‑Experts architecture. It was pretrained on over 1.5 million scans from 428,647 studies and systematically evaluates architectural, masking, objective, and sparsity choices for robust multimodal representation learning. Across 47 tasks from three health systems and 12 public datasets, Neuro‑JEPA consistently outperforms a simple CNN baseline, demonstrating its effectiveness for both clinical and research applications.
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.