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
The paper introduces a leakage‑controlled multimodal learning framework for diagnosing and predicting the progression of Alzheimer’s disease. It combines an adapted SFCN MRI encoder, four causal clinical Transformers, shared fusion, and task‑specific ODE‑GRU dynamics, with fine‑tuning and LoRA for MRI blocks. Across 2,649 subjects and 17,317 visits, the model achieves high AUROCs for diagnosis and progression, and demonstrates strong external validation on OASIS‑3 data.
By Akeem Temitope Otapo, Ghazaleh Khodabandelou, Zuheng Ming, Alice Othmani
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
The paper introduces TAFNet, a temporal attention fusion network that uses both a baseline and a follow‑up T1‑weighted brain scan to predict which individuals with mild cognitive impairment (MCI) will progress to dementia. The model employs a pretrained Siamese encoder for each scan and fuses the two scans through anatomical difference, cross‑temporal attention, joint context, and a learned per‑patient gate. Evaluated on paired scans from the Alzheimer’s Disease Neuroimaging Initiative, TAFNet outperforms single‑scan networks and a simple scan‑difference model, achieving significant gains in cross‑validation and maintaining high sensitivity at clinically reasonable specificity.
By Sara Fin, Alireza Moayedikia, David J. White, Uffe Kock Wiil, Alicia Troncoso
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.
By Victor Solomon, Zening Fu, Rafal Angryk, Vince D. Calhoun, Jingyu Liu
The paper introduces Explainable Graph-theoretical Machine Learning (XGML) to build individual metabolic brain graphs from FDG-PET data and identify subgraphs predictive of multivariate Alzheimer’s disease outcomes. Using ADNI data, the best model—kernel density estimation with Hellinger distance and random forest—achieved a Pearson correlation of 0.595 across eight cognitive scores, with the highest performance on ADAS13, ADAS11, and ADASQ4. Key edges were found to be jointly but differentially predictive, indicating potential network biomarkers for cognitive decline, though external validation on OASIS3 showed weaker performance likely due to cohort differences.
By Narmina Baghirova, Duy-Thanh V\~u, Duy-Cat Can, Christelle Schneuwly Diaz, Julien Bodlet, Guillaume Blanc, Georgi Hrusanov, Bernard Ries, Oliver Y. Ch\'en
The paper introduces a Bayesian framework that models BOLD dynamics as coupled Ornstein‑Uhlenbeck processes and uses Sequential Neural Posterior Estimation to produce connectivity posteriors while accounting for measurement noise. Applied to 28 healthy controls scanned at 7T, the method quantifies uncertainty from scanner noise, subject variability, and scan length, revealing that about 46 voxels per ROI and 7 minutes of 7T data suffice for 90% of asymptotic precision. It also shows that 7T achieves within‑session precision 40% faster than 3T and requires roughly 37 times less per‑subject scan time to reach population‑level convergence, offering concrete, scanner‑specific guidance for protocol optimization.
By Simon Carter, Zeming Kuang, Lilianne R. Mujica-Parodi, Helmut H. Strey
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.
By Harshiddhi Pathak, Gowtham Reddy N, Mrinal Acharya, Manjunatha Mahadevappa
arXiv:2607. 28681v1 Announce Type: cross Abstract: Functional magnetic resonance imaging (fMRI) is a widely used technique for studying the brain.
By Yang Zhang, Xiao Zhou, Jonathan Warrell, Avram Holmes, Xuan Zhang, Mark Gerstein
Brain networks exhibit a modular community structure that varies across individuals and neurological conditions. However, existing self-supervised learning (SSL) methods often overlook this heterogeneity, relying on generic masking strategies that fail to capture subject-specific functional organization.
BrainPFN is a Prior Data Fitted Network that predicts behavioral phenotypes from functional MRI data without needing per-score or per-cohort refitting. It is meta-trained on a domain-specific prior derived from about 7,000 real functional connectivity matrices, generating one billion synthetic training samples. In tests across four independent cohorts, BrainPFN outperforms Kernel Ridge Regression on small-sample predictions and rivals larger foundation models, all while using a modest, publicly available training pool.
By Carlo Alberto Barbano (MIND), Demian Wassermann (MIND)
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...
By Paul-Gabriel Nicolae, Irina Georgiana Mocanu