Echo-Path: Pathology-Conditioned Echo Video Generation

2025-09-21

AI Summary

Cardiovascular disease remains the leading global cause of mortality; however, the scarcity of echocardiographic data for rare cardiac conditions severely impairs the robustness and generalizability of automated diagnostic models. To address this, we propose a pathology-condition-driven echocardiographic video generation framework. Our method introduces a pathology feature embedding module that jointly encodes anatomical structure and dynamic motion patterns, enabling controllable, clinically grounded synthesis. Integrated within a state-of-the-art video generation architecture, it combines adversarial training with distribution alignment to produce high-fidelity, pathology-specific echocardiographic videos. Crucially, this is the first approach to leverage fine-grained, interpretable pathological representations as explicit generative guidance—effectively mitigating dataset bias. Evaluated on real-world clinical data, downstream classification tasks demonstrate consistent performance gains of 7–8% in accuracy. The proposed framework establishes a scalable, pathology-aware data augmentation paradigm for intelligent diagnosis of rare cardiomyopathies.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Cardiovascular diseases (CVDs) remain the leading cause of mortality globally, and echocardiography is critical for diagnosis of both common and congenital cardiac conditions. However, echocardiographic data for certain pathologies are scarce, hindering the development of robust automated diagnosis models. In this work, we propose Echo-Path, a novel generative framework to produce echocardiogram videos conditioned on specific cardiac pathologies. Echo-Path can synthesize realistic ultrasound video sequences that exhibit targeted abnormalities, focusing here on atrial septal defect (ASD) and pulmonary arterial hypertension (PAH). Our approach introduces a pathology-conditioning mechanism into a state-of-the-art echo video generator, allowing the model to learn and control disease-specific structural and motion patterns in the heart. Quantitative evaluation demonstrates that the synthetic videos achieve low distribution distances, indicating high visual fidelity. Clinically, the generated echoes exhibit plausible pathology markers. Furthermore, classifiers trained on our synthetic data generalize well to real data and, when used to augment real training sets, it improves downstream diagnosis of ASD and PAH by 7% and 8% respectively. Code, weights and dataset are available here https://github.com/Marshall-mk/EchoPathv1

Problem

• Generating realistic echocardiogram videos for rare cardiac pathologies
• Addressing data scarcity that hinders automated cardiac diagnosis models
• Creating pathology-specific synthetic data to improve disease classification

Innovation

• Pathology-conditioned echocardiogram video generation framework
• Introduces disease-specific structural and motion pattern control
• Synthetic data improves downstream diagnosis by augmenting training sets