Explainable and Controllable Motion Curve Guided Cardiac Ultrasound Video Generation

TL;DR

This paper introduces an explainable, controllable method for generating echocardiography videos using motion curves and structure-to-motion alignment, improving fidelity and consistency over previous models.

Contribution

It presents a novel approach that extracts motion from cardiac substructures, aligns semantic features with motion curves, and employs position-aware attention for enhanced video quality.

Findings

Outperforms existing methods in fidelity and consistency

Enables flexible control over cardiac structure movements

Demonstrates effectiveness across three datasets

Abstract

Echocardiography video is a primary modality for diagnosing heart diseases, but the limited data poses challenges for both clinical teaching and machine learning training. Recently, video generative models have emerged as a promising strategy to alleviate this issue. However, previous methods often relied on holistic conditions during generation, hindering the flexible movement control over specific cardiac structures. In this context, we propose an explainable and controllable method for echocardiography video generation, taking an initial frame and a motion curve as guidance. Our contributions are three-fold. First, we extract motion information from each heart substructure to construct motion curves, enabling the diffusion model to synthesize customized echocardiography videos by modifying these curves. Second, we propose the structure-to-motion alignment module, which can map semantic features onto motion curves across cardiac structures. Third, The position-aware attention mechanism is designed to enhance video consistency utilizing Gaussian masks with structural position information. Extensive experiments on three echocardiography datasets show that our method outperforms others regarding fidelity and consistency. The full code will be released at https://github.com/mlmi-2024-72/ECM.