The paper introduces a two-stage multi‑modal MRI framework that processes different MRI modalities independently before integrating them through late fusion. First, the model estimates a probability distribution over six developmental stages, then it predicts age using probability‑weighted, stage‑specialized experts. Experiments across nine datasets—from fetal to elderly—show the method outperforms existing baselines, reducing mean absolute error by 13% and 78% in in‑domain and out‑of‑domain settings, and multi‑modal integration yields 12‑13% performance gains. Analysis on ADNI clinical groups indicates that the predicted brain age gap could help characterize Alzheimer’s‑related brain aging.
arXiv:2512. 10966v3 Announce Type: replace-cross Abstract: Accurate and early diagnosis of Alzheimer's disease (AD) is critical for effective intervention and requires integrating complementary information from multimodal neuroimaging data.
In longitudinal Alzheimer's disease (AD) diagnosis support, clinical and imaging information is often collected at irregular visits. Integrating these multimodal observations may improve diagnostic assessment, but naive fusion can degrade performance when MRI is noisy or intermittently unavailable.
arXiv:2607. 07091v1 Announce Type: cross Abstract: In longitudinal Alzheimer's disease (AD) diagnosis support, clinical and imaging information is often collected at irregular visits.
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.
Brain-PACE is a deep Siamese MRI framework that directly estimates the pace of structural brain ageing from paired T1‑weighted MRI scans, extending the LILAC model with spatial attention, soft label distribution learning, and a Cramér distance objective. In a study of participants with mild cognitive impairment, 42.6 % showed accelerated ageing, and faster Brain‑PACE scores correlated with greater functional and cognitive impairment as well as higher regional tau burden in key brain regions. The method improves probabilistic performance, reduces prediction bias, and provides predictive uncertainty, offering a complementary longitudinal imaging phenotype sensitive to early neurodegeneration.
BrainNorm is a normative foundation model trained on about 66,000 T1-weighted structural MRI scans. It uses language‑image style contrastive pretraining to create a Semantic Atlas Latent space (SAL), where each scan is encoded as atlas‑parcel embeddings that capture healthy aging trajectories. The model supports age‑consistent template matching, localized deviation scoring, and zero‑shot disease prediction, outperforming nine baselines across multiple downstream tasks and aligning its deviation patterns with known neurodegeneration pathology.
arXiv:2606. 17867v1 Announce Type: cross Abstract: Despite increasing adoption of multimodal approaches in Alzheimer's Disease (AD) research -- aimed at integrating molecular, structural, clinical, and genetic biomarkers to enhance disease characterization -- the relationships among these modalities remain poorly understood.
Alzheimer's disease (AD) progression is highly heterogeneous and is typically observed through sparse and irregular longitudinal data, posing challenges for prediction and personalised monitoring. Existing machine learning approaches have improved AD prediction using multimodal data, yet often focus on static classification or cohort-level risk estimation, providing limited support for subject-specific modelling and uncertainty-aware reasoning.
arXiv:2606. 09671v1 Announce Type: cross Abstract: Alzheimer's disease (AD) progression is highly heterogeneous and is typically observed through sparse and irregular longitudinal data, posing challenges for prediction and personalised monitoring.
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.
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.
The paper introduces MSR-IVA, a state-aware fusion method that combines a shared structural representation with state‑specific residual adaptations and masks for incomplete state expression. Applied to an Alzheimer’s Disease Neuroimaging Initiative cohort, MSR-IVA increased matched source coupling by 6.5% and decreased unmatched dependence by 15.7% compared to a baseline IVA approach. For subjects expressing both states, the method achieved a mean absolute cross‑state structural source correlation of 0.9177, far higher than the 0.2978 obtained without sharing, indicating effective preservation of source correspondence while allowing state‑specific adaptation.