Imaging-anchored Multiomics in Cardiovascular Disease: Integrating Cardiac Imaging, Bulk, Single-cell, and Spatial Transcriptomics

2026-01-10

AI Summary

This study addresses the longstanding challenge in cardiovascular disease research where cardiac imaging and multi-omics data have been analyzed in isolation, hindering insights into the links between molecular mechanisms and tissue remodeling. To bridge this gap, the work proposes an image-anchored multimodal integration framework that unifies imaging phenotypes—from cardiac MRI, CT, and echocardiography—with bulk, single-cell, and spatial transcriptomic data. Leveraging techniques such as representation learning, multimodal fusion, and spatial molecular alignment, the approach tackles key challenges including missing data, small sample sizes, and batch effects. Beyond constructing joint imaging–omics representations to elucidate the molecular and structural underpinnings of disease, the study also provides a systematic synthesis of integration strategies and common failure modes, offering a methodological foundation for translational cardiovascular multi-omics research.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Cardiovascular disease arises from interactions between inherited risk, molecular programmes, and tissue-scale remodelling that are observed clinically through imaging. Health systems now routinely generate large volumes of cardiac MRI, CT and echocardiography together with bulk, single-cell and spatial transcriptomics, yet these data are still analysed in separate pipelines. This review examines joint representations that link cardiac imaging phenotypes to transcriptomic and spatially resolved molecular states. An imaging-anchored perspective is adopted in which echocardiography, cardiac MRI and CT define a spatial phenotype of the heart, and bulk, single-cell and spatial transcriptomics provide cell-type- and location-specific molecular context. The biological and technical characteristics of these modalities are first summarised, and representation-learning strategies for each are outlined. Multimodal fusion approaches are reviewed, with emphasis on handling missing data, limited sample size, and batch effects. Finally, integrative pipelines for radiogenomics, spatial molecular alignment, and image-based prediction of gene expression are discussed, together with common failure modes, practical considerations, and open challenges. Spatial multiomics of human myocardium and atherosclerotic plaque, single-cell and spatial foundation models, and multimodal medical foundation models are collectively bringing imaging-anchored multiomics closer to large-scale cardiovascular translation.

Problem

• cardiovascular disease
• imaging-anchored multiomics
• cardiac imaging
• spatial transcriptomics
• multimodal integration

Innovation

• imaging-anchored multiomics
• spatial transcriptomics
• multimodal fusion
• representation learning
• radiogenomics