Biology subjects

Gollo, L.

Publications and source records attributed to Gollo, L..

3 recordsLinked to original sources

bioRxiv2026

Attention-Guided Multimodal Neuroimaging Fusion Network for Modeling Brain Aging Pattern

Brain age prediction from neuroimaging data provides critical insights into neurodevelopmental trajectories and neurodegenerative processes. However, effectively leveraging complementary structural and functional brain information for accurate prediction remains a major challenge. In this study, we propose an Attention-guided Multimodal brain Age prediction Network (AMAge-Net), a novel framework that integrates resting-state functional MRI (fMRI) and structural MRI (sMRI) to enhance brain age estimation. In AMAge-Net, functional features are captured from fMRI through a hierarchical Graph Attention Network, while structural features are learned from sMRI via a 3D DenseNet architecture. To enable effective cross-modal integration, AMAge-Net incorporates a Multi-Head Cross-Attention mechanism followed by a Gated Fusion Module, allowing the model to dynamically prioritize the most informative features from each modality, thereby improving interpretability and predictive accuracy. Evaluation on the Cam-CAN dataset (652 participants, aged 18-89) demonstrates that AMAge-Net outperforms state-of-the-art unimodal and multimodal baselines, achieving a mean absolute error (MAE) of 5.09, root mean square error (RMSE) of 6.52, R2 of 0.87, and Pearson correlation (PCC) of 0.94. The proposed model further demonstrates robust generalization, achieving an MAE of 4.29, RMSE of 5.59, R2 of 0.58, and PCC of 0.77 on the independent OASIS-3 dataset. Comparative and ablation studies further confirm the effectiveness of the proposed fusion strategy and modality-specific encoders. Beyond predictive performance, AMAge-Net highlights interpretable brain regions that provide insights into the mechanisms of functional and structural brain aging, while gender-specific analyses reveal distinct aging trajectories between males and females. These findings establish AMAge-Net as a powerful and interpretable approach to brain age estimation, advancing efforts to characterize healthy aging and detect early deviations associated with neurological and psychiatric disorders. Author summaryEstimating the biological age of the brain from imaging data offers a window into normal development, healthy aging, and the early stages of disease. A major challenge is how to combine information from structural scans, which show brain anatomy, and functional scans, which capture brain activity. Here, we present a new computational framework that integrates both types of data to improve the accuracy and interpretability of brain age prediction. Applied to two independent, large-scale lifespan magnetic resonance imaging datasets of individuals spanning early adulthood to late life, our framework produced highly accurate predictions and consistently outperformed existing methods. Beyond predictive performance, the model highlighted brain regions that appear especially important for age-related changes, and it revealed distinct aging patterns between men and women. These findings provide a powerful and interpretable tool for studying how the brain changes across the lifespan, with potential applications in detecting early deviations linked to neurological and psychiatric disorders.

neuroscience↗

bioRxiv2021

On the intersection between data quality and dynamical modelling of large-scale fMRI signals

Large-scale dynamics of the brain are routinely modelled using systems of nonlinear dynamical equations that describe the evolution of population-level activity, with distinct neural populations often coupled according to an empirically measured structural connection matrix. This modelling approach has been used to generate insights into the neural underpinnings of spontaneous brain dynamics, as recorded with techniques such as resting state functional MRI (fMRI). In fMRI, researchers have many degrees of freedom in the way that they can process the data and recent evidence indicates that the choice of pre-processing steps can have a major effect on empirical estimates of functional connectivity. However, the potential influence of such variations on modelling results are seldom considered. Here we show, using three popular whole-brain dynamical models, that different choices during fMRI preprocessing can dramatically affect model fits and interpretations of findings. Critically, we show that the ability of these models to accurately capture patterns in fMRI dynamics is mostly driven by the degree to which they fit global signals rather than interesting sources of coordinated neural dynamics. We show that widespread deflections can arise from simple global synchronisation. We introduce a simple two-parameter model that captures these fluctuations and which performs just as well as more complex, multi-parameter biophysical models. From our combined analyses of data and simulations, we describe benchmarks to evaluate model fit and validity. Although most models are not resilient to denoising, we show that relaxing the approximation of homogeneous neural populations by more explicitly modelling inter-regional effective connectivity can improve model accuracy at the expense of increased model complexity. Our results suggest that many complex biophysical models may be fitting relatively trivial properties of the data, and underscore a need for tighter integration between data quality assurance and model development.

neuroscience↗

bioRxiv2017

Network structure of the human musculoskeletal system shapes neural interactions on multiple timescales

Human motor control requires the coordination of muscle activity under the anatomical constraints imposed by the musculoskeletal system. Interactions within the central nervous system are fundamental to motor coordination, but the principles governing functional integration remain poorly understood. We used network analysis to investigate the relationship between anatomical and functional connectivity amongst 36 muscles. Anatomical networks were defined by the physical connections between muscles and functional networks were based on intermuscular coherence assessed during postural tasks. We found a modular structure of functional networks that was strongly shaped by the anatomical constraints of the musculoskeletal system. Changes in postural tasks were associated with a frequency-dependent reconfiguration of the coupling between functional modules. These findings reveal distinct patterns of functional interactions between muscles involved in flexibly organising muscle activity during postural control. Our network approach to the motor system offers a unique window into the neural circuitry driving the musculoskeletal system.

neuroscience↗