analiza aiqbench
This research introduces Echo2ECG, a multimodal self-supervised learning framework that bridges the gap between electrical heart signals (ECG) and structural imaging data to improve diagnostic capabilities. By leveraging multi-view echocardiography to enrich ECG representations, the model achieves superior performance in classifying cardiac phenotypes while maintaining significantly lower computational overhead than existing baselines. The work advances machine learning applications in medical diagnostics by demonstrating how integrating distinct physiological modalities can overcome inherent representational limitations in single-modality models.
Echo2ECG: Enhancing ECG Representations with Cardiac Morphology from Multi-View Echos
arXiv:2603.08505v2 Announce Type: replace-cross Abstract: Electrocardiography (ECG) is a low-cost, widely used modality for diagnosing electrical abnormalities like atrial fibrillation by capturing the heart's electrical activity. However, it cannot directly measure cardiac morphological phenotypes, such as left ventricular ejection fraction (LVEF), which typically require echocardiography (Echo). Predicting these phenotypes from ECG would enable early, accessible health screening. Existing self-supervised methods suffer from a representational mismatch by aligning ECGs to single-view Echos, which only capture local, spatially restricted anatomical snapshots. To address this, we propose Echo2ECG, a multimodal self-supervised learning framework that enriches ECG representations with the heart's morphological structure captured in multi-view Echos. We evaluate Echo2ECG as an ECG feature extractor on two clinically relevant tasks that fundamentally require morphological information: (1) classification of structural cardiac phenotypes across three datasets, and (2) retrieval of Echo studies with similar morphological characteristics using ECG queries. Our extracted ECG representations consistently outperform those of state-of-the-art unimodal and multimodal baselines across both tasks, despite being 18x smaller than the largest baseline. These results demonstrate that Echo2ECG is a robust, powerful ECG feature extractor. Our code is accessible at https://github.com/michelleespranita/Echo2ECG.
Abstract:Electrocardiography (ECG) is a low-cost, widely used modality for diagnosing electrical abnormalities like atrial fibrillation by capturing the heart's electrical activity. However, it cannot directly measure cardiac morphological phenotypes, such as left ventricular ejection fraction (LVEF), which typically require echocardiography (Echo). Predicting these phenotypes from ECG would enable early, accessible health screening. Existing self-supervised methods suffer from a representational mismatch by aligning ECGs to single-view Echos, which only capture local, spatially restricted anatomical snapshots. To address this, we propose Echo2ECG, a multimodal self-supervised learning framework that enriches ECG representations with the heart's morphological structure captured in multi-view Echos. We evaluate Echo2ECG as an ECG feature extractor on two clinically relevant tasks that fundamentally require morphological information: (1) classification of structural cardiac phenotypes across three datasets, and (2) retrieval of Echo studies with similar morphological characteristics using ECG queries. Our extracted ECG representations consistently outperform those of state-of-the-art unimodal and multimodal baselines across both tasks, despite being 18x smaller than the largest baseline. These results demonstrate that Echo2ECG is a robust, powerful ECG feature extractor. Our code is accessible at this https URL.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2603.08505 [cs.LG]
(or arXiv:2603.08505v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2603.08505 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 277 cuvinte
Subiecte conexe
Multi-Task Learning by using Contextualized Word Representations for Syntactic Parsing of a Morphologically Rich Language
arXiv · 25 sept. 2026
ECG-LENS: Lead-Aware Clinical Context Enriched ECG Report Generation and Evaluation
arXiv · 7 aug. 2026
HyperAMS-Net: Adaptive Multi-Scale Spatial Hypergraph Network for Brain Disorder Classification
arXiv · 18 sept. 2026
ReG-SAM: Reference Graph-Driven SAM for 2D Foundational Vessel Segmentation
arXiv · 28 sept. 2026