Weekly Digest
Weekly ToC Digest (week of 2026-02-11)
No papers directly related to the specified interests in brain aging, predicting brain age, or neuroimaging biomarkers for aging. Focus shifted towards computational models and neuroscience trends. Focus on brain aging models and computational contributions in neuroimaging. Prioritize research involving data science, modeling, and validation relevant to brain aging. No entries explicitly tied to brain-age or neuroimaging methods. Emphasized modeling innovations and relevance to brain aging where possible. All selected papers include relevant computational or modeling contributions related to neuroimaging, brain age modeling, or related data science methods relevant to brain aging.
Included: 8 (score ≥ 0.35)
Scored: 9 total items
Cortical traveling waves in time and space: Physics, physiology, and psychology
Neuron
Score: 0.75
Published: 2026-02-09T00:00:00+00:00 Tags: modeling, brain dynamics, neuroimaging
Explores modeling of cortical activity and dynamics which could be applied to brain aging models, particularly with the physics of brain waves.
RSS summary
Cruddas et al. reviewed how core concepts from wave physics relate to cortical wave physiology and psychology. They examined how cortical waves emerge, how they facilitate coordinated, hierarchical, and counterstream dynamics, and how they encode perceptual and behavioral signals.
MAMBAxBrain: A Multi-task Neural Framework Linking Brain Functional Dynamics to Individual Fingerprints, Cognitive and Disease States
bioRxiv
Score: 0.70
Published: 2026-02-10T00:00:00+00:00 Tags: fMRI, computational, modeling
Presents a multi-task neural framework for modeling fMRI data with potential applications in brain aging studies. Emphasizes computational modeling and functional dynamics.
RSS summary
Functional magnetic resonance imaging (fMRI) contains rich individual, cognitive, and pathological information, yet no universal model exists for multi-task modeling of these dimensions. Here, we introduce MAMBAxBrain, a multi-task neural framework that integrates Mamba architecture with functional connectivity analysis to jointly model the temporal dynamics and spatial coordination of neural activity. MAMBAxBrain achieves high accuracy across four distinct fMRI objectives - brain fingerprinting…
Cognitive rejuvenation through partial reprogramming of engram cells
Neuron
Score: 0.70
Published: 2026-02-10T00:00:00+00:00 Tags: brain age, neurobiology
This paper involves partial reprogramming techniques that counteract aging in neuronal cells, which may relate to the mechanistic underpinnings of brain aging, although it lacks specific computational methods.
RSS summary
Berdugo-Vega et al. combine partial reprogramming and engram technologies to achieve molecular rejuvenation of learning-associated neuronal ensembles. Engram reprogramming counteracts molecular, cellular, and electrophysiological signs of aging and disease and is associated with behavioral improvements that are consistent with a rejuvenation of learning and memory capacities.
Derivation and validation of a machine learning-driven score to predict the diagnostic yield of endomyocardial biopsy
npj Digital Med
Score: 0.70
Published: 2026-02-09T00:00:00+00:00 Tags: machine learning, modeling, validation
Includes machine learning-based score derivation and validation, indicating relevance for computational modeling in neuroimaging or similar domains.
RSS summary
npj Digital Medicine, Published online: 09 February 2026; doi:10.1038/s41746-026-02421-y
Derivation and validation of a machine learning-driven score to predict the diagnostic yield of endomyocardial biopsy
AI System Using Unsupervised Learning to Discover Novel Subtypes in Alzheimer’s Disease
bioRxiv
Score: 0.65
Published: 2026-02-10T00:00:00+00:00 Tags: machine learning, Alzheimer’s, MRI
Utilizes machine learning to identify Alzheimer’s subtypes, relevant to brain aging and neuroimaging. Highlights computational methods.
RSS summary
Early Alzheimer’s disease often evades timely detection because typical diagnostics are based on symptomatic thinking rather than intrinsic neurodegeneration. Here, we use unsupervised machine learning to identify latent Alzheimer’s phenotypes from structural MRI-derived volumetric features and neuropsychological scores, without using diagnosis labels or predefined subtype definitions. We analyzed participants (18-96 years) from the OASIS-1 study using intracranial, normalized, global, and regio…
Toward integrated sleep health: multimodal AI in Hang Hao Meng agent
npj Digital Med
Score: 0.65
Published: 2026-02-09T00:00:00+00:00 Tags: multimodal, AI, integration
Multimodal AI approach relevant for integrating various neuroimaging data and potentially applicable to brain aging studies.
RSS summary
npj Digital Medicine, Published online: 09 February 2026; doi:10.1038/s41746-026-02432-9
Toward integrated sleep health: multimodal AI in Hang Hao Meng agent
High spatial resolution 23Na-MRI for ischemic brain injury detection
bioRxiv
Score: 0.55
Published: 2026-02-10T00:00:00+00:00 Tags: MRI, multimodal, neuroimaging
Focuses on advanced MRI techniques; could have implications for neuroimaging biomarkers relevant to aging processes.
RSS summary
High spatial resolution sodium (23Na) imaging of brain lesions remains challenging due to the intrinsically low signal-to-noise ratio (SNR) of 23Na-MRI compared with conventional proton (1H) MRI. In this study, we established a high-resolution 23Na-MRI platform based on 14 T preclinical scanner using a dual-tuned head-implanted RF coil. This configuration enables the acquisition of 1H-based T2-weighted anatomical and diffusion-weighted imaging (DWI), as well as 23Na-MRI, from the same animal. Br…
NeuroVLM: A generative vision-language framework for human neuroimaging
bioRxiv
Score: 0.40
Published: 2026-02-09T00:00:00+00:00 Tags: neuroimaging, modeling, VLM
Presents NeuroVLM, a model architecture supporting learning from neuroimage-text pairs, relevant for cognitive neuroimaging studies.
RSS summary
Neuroimaging research has produced tens-of-thousands of articles that pair natural language and activation coordinate tables. Recent advances in vision-language models (VLMs) have provided methods to model text and images simultaneously. In this work, we present NeuroVLM, a model architecture for learning from 30,000 human neuroimage-text pairs. The architecture supports contrastive and generative objectives. The contrastive model ranks similarity between neuroimages and text. The generative mod…