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:2605.24625v2 Announce Type: replace Abstract: Ultra-low-field (ULF) MRI offers portable and accessible neuroimaging but suffers from reduced signal-to-noise ratio and limited spatial resolution...
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.
arXiv:2609. 20562v1 Announce Type: new Abstract: Automated quality assessment, enhancement, and segmentation of multiple structures in $0.
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:2607. 07219v1 Announce Type: cross Abstract: Vision foundation models (VFMs) are increasingly being developed for radiological imaging, yet their definition, development and evaluation remain heterogeneous.
arXiv:2609.15888v1 Announce Type: cross Abstract: Deep networks trained on structural MRI for Alzheimer's disease (AD) staging often reach reasonable accuracy while attending to anatomically irreleva...
arXiv:2609.23983v1 Announce Type: new Abstract: Neuroimaging foundation models pretrained on large, predominantly western cohorts are increasingly proposed as general-purpose backbones for brain MRI...
arXiv:2608.28773v1 Announce Type: cross Abstract: Perceptual losses are widely used in medical image synthesis because they encourage agreement in high-level structure beyond voxel-wise intensity sim...
arXiv:2607. 18283v1 Announce Type: cross Abstract: Accurate localization of the corpus callosum (CC) in fetal ultrasound (US) images is crucial for the early identification of neurodevelopmental abnormalities.
The study benchmarks foundation models for chest X‑ray classification across a domain shift from adult to pediatric patients. Six foundation models and two CNN baselines were evaluated on a harmonized five‑label task using adult data for adaptation and tested on both adult and pediatric sets. Results show all models experience a substantial performance drop—over 10 percentage points—when applied to pediatric data, and deeper adaptation does not markedly improve cross‑population generalization.
arXiv:2609.16032v1 Announce Type: cross Abstract: Diffusion-based artifact detectors score whole-slide image patches by reconstruction error under a model fine-tuned on clean tissue. We show that con...
BrainFedFM is a structural brain MRI foundation model that was federatively pretrained on 164,707 3‑D scans from 42 sites using a dual‑priority approach that emphasizes informative anatomical regions locally and prioritizes site contributions globally. The model outperformed seven baseline models—including four centralized foundation models—across 20 downstream tasks (classification, regression, segmentation), achieving a mean rank of 1.68 and a 50% performance gain, especially in classification and regression and among underrepresented populations. These results demonstrate the model’s generalizability and show that federated pretraining can effectively develop neuroimaging foundation models without pooling raw images.