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.
By Haoxu Huang, Long Chen, Jingyun Chen, Jinu Hyun, James Ryan Loftus, Kara Melmed, Daniel Orringer, Jennifer Frontera, Seena Dehkharghani, Arjun Masurkar, Narges Razavian
The paper introduces AGW-PBR, a brain MRI super‑resolution method that emphasizes tissue‑transition regions affected by the partial‑volume effect. It uses a low‑resolution backbone guided by Sobel edges, soft latent‑basis assignment, and grid‑anchored warping, while training‑time weights are derived from tissue‑mixture entropy computed from registered T1/T2/PD images. Experiments on IXI T2‑weighted scans at 2×, 4×, and 6× show improved full‑image reconstruction and regional fidelity, and the backbone also performs well on fastMRI data without PVE supervision.
By Xiao Tong, Wenyun Yang, Ziheng Zhang, Jingzhi Han, Zhaochu Luo, Jinbo Yang
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...
By Baris Imre, Aram Salehi, Levente Baljer, Andrew Webb, Marius Staring, Efe Ilicak
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.
By Jelmer van Lune, Miha Fuderer, Oscar van der Heide, Matteo Maspero, Martin B. Schilder, Jan Willem Dankbaar, Stefano Mandija, Alessandro Sbrizzi
arXiv:2610.17401v1 Announce Type: new
Abstract: Incomplete field-of-view (FOV) diffusion MRI (dMRI) acquisitions compromise whole-brain white matter analysis by excluding brain regions from tractogra...
By Gaurav Rudravaram, Lianrui Zuo, Ema Topolnjak, Michael E. Kim, Adam M. Saunders, Elyssa M. McMaster, Paula Trujillo, Ely E. Wesley, Colin D. McKnight, Pratik P. Pandharipande, Mayur B. Patel, Cayce Strength, Brenda T. Pund, Amelia W Maiga, Robert S. Dittus, David A. Bennett, Julie A. Schneider, Konstantinos Arfanakis, The HABS-HD Study Team, Derek B. Archer, Timothy J. Hohman, Yelena Bodien, Daniel C. Moyer, Kurt G. Schilling, Bennett A. Landman
CATCH is a conditional 3D diffusion model operating in an invertible Haar-wavelet domain designed to inpaint masked regions in T1‑weighted brain MRI with plausible, tumor‑free tissue while preserving observed anatomy. The model’s denoiser uses noisy target coefficients, voided‑image coefficients, and a signed mask, guided by tumor‑excluded wavelet reconstruction and a hole‑focused loss, and hard compositing ensures observed voxels remain unchanged. Experiments on BraTS data show that a weighted mixture of tumor‑derived, irregular‑blob, and ellipsoidal masks yields the best performance, achieving higher SSIM, PSNR, and lower MSE compared to fixed or random augmentation baselines.
By Simon Winther Albertsen, Hjalte Bjoernstrup, Said Djafar Said, Mostafa Mehdipour Ghazi
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.
By Zahra Karimaghaloo, Dumitru Fetco, Haz-Edine Assemlal, Hassan Rivaz, Douglas L. Arnold
The paper introduces MCNet, a neural network that assigns a Modality Contribution Score (MCS) to each patient, indicating how much structural MRI versus amyloid PET drives the diagnostic decision for Alzheimer’s disease. Across 327 ADNI-3 participants, MCNet achieved strong three‑class staging (AUC = 0.881) and the MCS showed a clear, statistically significant increase in PET dominance from cognitively normal to AD. The method was validated on an independent OASIS‑3 cohort and compared favorably to SHAP, suggesting it can guide personalized imaging and clinical trial decisions.
By Dawa Chyophel Lepcha, Aaliya Ali, Sophie A. Martin, Deepika Koundal, Pierrick Coupe, Shabbir Syed-Abdul
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...
By Changsheng Fang, Dayang Wang, T. Campbell Arnold, Enhao Gong, Srivathsa Pasumarthi
arXiv:2609.39083v1 Announce Type: new
Abstract: Super-resolution and quality enhancement of 1.5\,T brain MRI are normally validated with image-fidelity metrics, although their purpose is to improve d...
By Kavitha Viswanathan, Harsh Choudhary, Amit Sethi
CoPoE is a new multimodal fusion framework for Alzheimer’s disease diagnosis that maps diverse clinical, imaging, genomic, and biomarker data into a structured latent space divided into four biological and clinical axes: genetic Risk, molecular Pathology, Neurodegeneration, and clinical Stage. Each available modality contributes a diagonal Gaussian expert, and a masked Product-of-Experts architecture fuses only the observed modalities, avoiding synthetic imputation. In extensive experiments on the ADNI dataset, CoPoE outperforms standard missing-modality fusion baselines, achieving higher AUROC, better calibration metrics, and retaining pathology signals even when certain modalities are missing.
By Chihun An, Ikbeom Jang
The study presents an explainable multimodal deep‑learning framework that combines a 3D CNN for T1‑weighted MRI with a feedforward network for harmonized clinical and demographic data to diagnose Alzheimer’s disease. Using 6,479 ADNI records and 1,703 OASIS‑3 records, the authors compare various model configurations on three‑way and pairwise diagnostic tasks, finding that performance and explanations vary by task, modality, fusion strategy, and cohort. SHAP and Integrated Gradients consistently highlight the MMSE score as the most influential tabular feature, while CAM‑based explanations differ across model setups and cohorts, indicating that explainability is not a stable property under cohort shift.
By Yusuf Brima, Marcellin Atemkeng, Lakshmana Rao Namamula, Antoine Vacavant