Latent Motion Profiling for Annotation-free Cardiac Phase Detection in Adult and Fetal Echocardiography Videos

TL;DR

This paper introduces an unsupervised method for detecting cardiac phases in adult and fetal echocardiography videos by learning latent motion trajectories, eliminating the need for manual annotations and matching supervised methods in accuracy.

Contribution

The novel contribution is an unsupervised framework that encodes interpretable cardiac motion patterns to detect ED and ES phases without annotations.

Findings

Achieves MAE of 3 frames for ED and 2 frames for ES in adult echocardiography.

Demonstrates robust fetal cardiac phase detection with MAE around 1.5 frames.

Matches state-of-the-art supervised methods without requiring manual annotations.

Abstract

The identification of cardiac phase is an essential step for analysis and diagnosis of cardiac function. Automatic methods, especially data-driven methods for cardiac phase detection, typically require extensive annotations, which is time-consuming and labor-intensive. In this paper, we present an unsupervised framework for end-diastole (ED) and end-systole (ES) detection through self-supervised learning of latent cardiac motion trajectories from 4-chamber-view echocardiography videos. Our method eliminates the need for manual annotations, including ED and ES indices, segmentation, or volumetric measurements, by training a reconstruction model to encode interpretable spatiotemporal motion patterns. Evaluated on the EchoNet-Dynamic benchmark, the approach achieves mean absolute error (MAE) of 3 frames (58.3 ms) for ED and 2 frames (38.8 ms) for ES detection, matching state-of-the-art supervised methods. Extended to fetal echocardiography, the model demonstrates robust performance with MAE 1.46 frames (20.7 ms) for ED and 1.74 frames (25.3 ms) for ES, despite the fact that the fetal heart model is built using non-standardized heart views due to fetal heart positioning variability. Our results demonstrate the potential of the proposed latent motion trajectory strategy for cardiac phase detection in adult and fetal echocardiography. This work advances unsupervised cardiac motion analysis, offering a scalable solution for clinical populations lacking annotated data. Code will be released at https://github.com/YingyuYyy/CardiacPhase.