Reconstructing physiological signals from fMRI across the adult lifespan

2024-08-26

arXiv.org

AI Summary

Simultaneous acquisition of physiological signals in older adults is challenging and prone to artifacts. Method: We propose a novel fMRI-based approach to reconstruct low-frequency respiratory volume (RV) and heart rate (HR) fluctuations, introducing the Transformer architecture for the first time to physiological signal reconstruction from fMRI across the full adult lifespan (36–89 years). We design an age-transfer training strategy leveraging young-adult data to enhance prediction accuracy in older participants, integrated with multi-stage training, fMRI time-series modeling, and physiology-aware regression optimization. Results: Our method achieves significantly improved reconstruction accuracy in older adults—RV (r = 0.698) and HR (r = 0.618)—outperforming state-of-the-art approaches. This work establishes a new paradigm for non-invasive, high-compatibility physiological monitoring in aging populations.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Bio-inspired Learning
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Interactions between the brain and body are of fundamental importance for human behavior and health. Functional magnetic resonance imaging (fMRI) captures whole-brain activity noninvasively, and modeling how fMRI signals interact with physiological dynamics of the body can provide new insight into brain function and offer potential biomarkers of disease. However, physiological recordings are not always possible to acquire since they require extra equipment and setup, and even when they are, the recorded physiological signals may contain substantial artifacts. To overcome this limitation, machine learning models have been proposed to directly extract features of respiratory and cardiac activity from resting-state fMRI signals. To date, such work has been carried out only in healthy young adults and in a pediatric population, leaving open questions about the efficacy of these approaches on older adults. Here, we propose a novel framework that leverages Transformer-based architectures for reconstructing two key physiological signals - low-frequency respiratory volume (RV) and heart rate (HR) fluctuations - from fMRI data, and test these models on a dataset of individuals aged 36-89 years old. Our framework outperforms previously proposed approaches (attaining median correlations between predicted and measured signals of r ~ .698 for RV and r ~ .618 for HR), indicating the potential of leveraging attention mechanisms to model fMRI-physiological signal relationships. We also evaluate several model training and fine-tuning strategies, and find that incorporating young-adult data during training improves the performance when predicting physiological signals in the aging cohort. Overall, our approach successfully infers key physiological variables directly from fMRI data from individuals across a wide range of the adult lifespan.

Problem

• Reconstruct physiological signals from fMRI data
• Overcome limitations in physiological signal acquisition
• Model fMRI-physiological signal relationships across adult lifespan

Innovation

• Transformer-based architectures for signal reconstruction
• Machine learning models extract physiological features
• Incorporating young-adult data enhances aging cohort predictions