arXiv:2512. 08462v2 Announce Type: replace Abstract: Decoding brain states from functional magnetic resonance imaging (fMRI) data is vital for advancing neuroscience and clinical applications.
arXiv:2608.23936v1 Announce Type: new Abstract: We present a dynamical-systems based model for resting-state functional magnetic resonance imaging (rs-fMRI), trained on a dataset of roughly 40K rs-fM...
arXiv:2607.11295v2 Announce Type: replace Abstract: Biomedical imaging data exhibit substantial acquisition variability, where identical biological structures can appear markedly different due to dif...
arXiv:2606. 11107v1 Announce Type: cross Abstract: Clinicians diagnose brain tumors by synthesizing patient symptoms, medical history, and quantitative imaging data from modalities such as MRI and CT scans into a unified clinical judgement.
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.
arXiv:2505. 06945v5 Announce Type: replace Abstract: Multimodal data modeling has emerged as a powerful approach in clinical research, enabling the integration of diverse data types such as imaging, genomics, wearable sensors, and electronic health records.
arXiv:2607. 26746v1 Announce Type: cross Abstract: Accurate identification of Alzheimers disease (AD) using resting-state functional magnetic resonance imaging (rs-fMRI) remains challenging due to the high dimensionality, noise, and complex inter-regional dependencies inherent in functional brain connectivity, which limit the effectiveness of traditional approaches based on handcrafted connectivity features or conventional machine learning models.
arXiv:2604. 27277v3 Announce Type: replace-cross Abstract: Brain MRI underpins a wide range of neuroscientific and clinical applications, yet most learning-based methods remain task-specific and require substantial labeled data.
arXiv:2606. 11500v1 Announce Type: cross Abstract: The success of large-scale deep learning models in neuroscience is fundamentally constrained by severe data heterogeneity.
This study introduces a self‑supervised, physics‑guided deep‑learning framework that converts standard clinical T1‑, T2‑, and FLAIR MRIs into quantitative T1, T2, and proton‑density maps. Trained on 4,121 scan sessions from four different 3 T scanners over six years, the method produces maps whose white‑ and gray‑matter values fall within literature ranges and shows minimal variation across scanner hardware and acquisition protocols (coefficients of variation ≤ 1.1 %). Voxel‑wise reproducibility is high, with Pearson and concordance correlation coefficients above 0.82 for T1 and T2 and mean relative differences below 6 % for T2.
arXiv:2506.20354v3 Announce Type: replace-cross Abstract: Learning from multi-variate time-series with heterogeneous channel configurations remains a fundamental challenge for deep neural networks, p...
Multimodal fusion learning (MFL) has shown great potential in the medical domain, where we are faced with disparate data modalities such as imaging, clinical records, and omics. However, existing MFL strategies face several major challenges.
The paper introduces CoMA-DiT, a bidirectional cross‑modal Diffusion Transformer that uses paired modalities as mutual generative supervision for latent augmentation rather than just inputs for fusion. By conditioning velocity prediction on the paired modality through cross‑modal attention and injecting variation via a reliability‑gated residual mechanism, CoMA‑DiT improves multimodal brain state decoding. Experiments on auditory attention decoding and emotion recognition show consistent gains over 20 baselines, with absolute accuracy and macro‑F1 improvements of 4.28% and 6.70% respectively, and extensive analyses confirm its robustness and interpretability.