Orientation-Robust Latent Motion Trajectory Learning for Annotation-free Cardiac Phase Detection in Fetal Echocardiography

TL;DR

ORBIT tackles the challenge of automatic ED/ES detection in fetal 4CH echocardiography despite arbitrary heart orientation and without manual annotations. It combines reference-free deformation estimation with latent trajectory learning in a low-dimensional subspace, producing orientation-robust phase detection by identifying turning points in the latent motion trajectory. The method achieves strong accuracy on normal data and generalizes surprisingly well to CHD cases, while being independent of heart orientation and cropping strategy, though complex CHD morphologies can still pose challenges. Overall, ORBIT offers a practical, annotation-free tool for robust fetal cardiac phase detection with potential applications in CHD analysis and fetal echocardiography workflows.

Abstract

Fetal echocardiography is essential for detecting congenital heart disease (CHD), facilitating pregnancy management, optimized delivery planning, and timely postnatal interventions. Among standard imaging planes, the four-chamber (4CH) view provides comprehensive information for CHD diagnosis, where clinicians carefully inspect the end-diastolic (ED) and end-systolic (ES) phases to evaluate cardiac structure and motion. Automated detection of these cardiac phases is thus a critical component toward fully automated CHD analysis. Yet, in the absence of fetal electrocardiography (ECG), manual identification of ED and ES frames remains a labor-intensive bottleneck. We present ORBIT (Orientation-Robust Beat Inference from Trajectories), a self-supervised framework that identifies cardiac phases without manual annotations under various fetal heart orientation. ORBIT employs registration as self-supervision task and learns a latent motion trajectory of cardiac deformation, whose turning points capture transitions between cardiac relaxation and contraction, enabling accurate and orientation-robust localization of ED and ES frames across diverse fetal positions. Trained exclusively on normal fetal echocardiography videos, ORBIT achieves consistent performance on both normal (MAE = 1.9 frames for ED and 1.6 for ES) and CHD cases (MAE = 2.4 frames for ED and 2.1 for ES), outperforming existing annotation-free approaches constrained by fixed orientation assumptions. These results highlight the potential of ORBIT to facilitate robust cardiac phase detection directly from 4CH fetal echocardiography.

Figures (8)

• Figure 1: Orientation distribution in the training set. Fetal 4CH-view echocardiography exhibits greater orientation variability, primarily due to differences in fetal position and examination angle.
• Figure 2: Proposed ORBIT model for cardiac phase detection. (a) Video preprocessing with heart area cropping and rotation augmentation (Section \ref{['exp']}).(b) Latent decomposition for cardiac deformation representation learning (Section \ref{['method_rep']}) and (c) its self-supervision aim via registration (Section \ref{['method_aim']}). (d) Annotation-free cardiac phase detection from latent trajectory with latent subspace dimension $M=1$ and $M=2$ (Section \ref{['method_traj']}).
• Figure 3: Histogram of frames-per-second (FPS) distributions for normal and abnormal test videos. Blue and orange bars correspond to abnormal and normal cases, respectively; overlapping bins are shown in gray.
• Figure 4: Orientation distribution in train/validation set (normal), test (normal) set and test (abnormal) set.
• Figure 5: Cardiac phase detection MAE (ms) grouped by orientation using LMP (reconstruction self-supervision) and our ORBIT (deformation self-supervision) respectively.