Multimodal Approaches to Cardiovascular Function: Bridging Imaging and Physiological Signal Analysis

Cardiovascular assessment has traditionally relied on either imaging-based diagnosis (echocardiography, MRI, CT, angiography) or signal-based physiological monitoring (ECG, hemodynamic and autonomic signals), developed and validated largely in parallel. Advances in computational methods—from classical signal processing to modern machine learning—now make it possible to extract richer, more precise information from each modality individually, and increasingly to integrate them into a unified picture of cardiac structure, function, and physiological regulation. Beyond method development, there is growing interest in translating these advances into clinical decision support systems that can assist diagnosis, risk stratification, and patient management in practice. This Research Topic brings together these strands—imaging, signal analysis, and their integration—to capture the current state of computer-driven cardiovascular diagnosis and chart a path toward genuinely multimodal, clinically actionable approaches.This Research Topic aims to examine computational approaches for cardiovascular diagnosis across imaging-based, signal-based, network-physiology, and multimodal methods. It will consider how these approaches can support the assessment of cardiac structure and function, physiological regulation, diagnosis, prognosis, and patient management, with particular emphasis on approaches that bridge imaging and signal analysis.This Research Topic welcomes original research, reviews, and methods articles across three connected strands:-Computational approaches for cardiac imaging-based diagnosis, including structural and functional assessment, segmentation, 3D/4D reconstruction, risk stratification, and digital twin approaches using echocardiography, MRI, CT, or angiography.-Signal and network physiology approaches to cardiovascular function, including ECG delineation and analysis, hemodynamic and autonomic signal processing, and network-physiology methods capturing inter-organ or inter-system coupling, whether based on classical or machine-learning techniques.-Multimodal and integrative approaches combining imaging and signal-based data, including fusion models, cross-modal validation, and clinical decision support systems that jointly leverage structural and electrophysiological information for diagnosis, prognosis, or patient management.We particularly encourage submissions that bridge the imaging and signal-analysis strands, as this integrative angle—including its translation into decision support tools—is where the Research Topic aims to make its strongest contribution. Topic editors: Alejandro Alcaine, Abhirup Banerjee Source: https://www.frontiersin.org/research-topics/85437/multimodal-approaches-to-cardiovascular-function-bridging-imaging-and-physiological-signal-analysis