EchoDiST is an unsupervised framework for estimating myocardial motion in echocardiography, combining self‑distillation joint learning of anatomical segmentation and motion estimation with a diffusion‑conditioned network. The method uses limited anatomical annotations and stochastic perturbations during training, yet requires only a single deterministic forward pass at inference. Evaluated on three datasets, EchoDiST consistently outperforms seven other learning‑based approaches in anatomical alignment, strain assessment, and functional metrics, with statistically significant improvements across cross‑view and cross‑dataset tests.
By Feiyue Qi, Xingyue Wei, Jianwen Luo
EchoDiST is an unsupervised framework for estimating myocardial motion in echocardiography. It combines self‑distillation joint learning of anatomical segmentation and motion estimation with a diffusion‑conditioned network, requiring only limited anatomical annotations. The method achieves statistically significant improvements in anatomical alignment, strain assessment, and functional metrics across three datasets, outperforming seven other learning‑based approaches.
arXiv:2609.08992v1 Announce Type: new
Abstract: False ventricular tachycardia (VT) alarms are a leading contributor to alarm fatigue in intensive care units. We propose a deep learning framework comb...
By Athanasios Papastathopoulos-Katsaros, Alexandra Stavrianidi, Zhandong Liu
Echo-E$^3$Net is an anatomy‑guided spatio‑temporal neural network designed to estimate left ventricular ejection fraction (LVEF) from ultrasound images. It uses a dual‑phase Endocardial Border Detector to locate end‑diastole and end‑systole landmarks and an Endocardial Feature Aggregator to fuse these landmarks with global deep‑feature descriptors for EF regression. The model achieves competitive accuracy on EchoNet‑Dynamic and EchoNet‑Pediatric datasets while using only 1.55 M parameters and 8.05 GFLOPs, enabling real‑time deployment on limited‑resource devices.
By Moein Heidari, Afshin Bozorgpour, AmirHossein Zarif-Fakharnia, Wenjin Chen, Dorit Merhof, David J. Foran, Jasmine Grewal, Ilker Hacihaliloglu
arXiv:2607. 00955v1 Announce Type: cross Abstract: Implicit neural representations (INRs) are well suited to cardiac motion estimation, providing continuous, compact representations of motion fields.
By Andrew Bell, George Webber, Andrew P King, Steffen E Petersen, Muhummad Sohaib Nazir, Alistair Young
Graph-based cardiac segmentation with implicit anatomical correspondences provides topological guarantees and population-level analysis capabilities, but models trained on independent frames of image sequences exhibit temporal discontinuities that affect reliable clinical measurements, particularly in cardiac ultrasound. In this work, we introduce self-supervised temporal regularization as a post-training refinement stage that exploits the temporal coherence in image sequences to enforce consistent cardiac segmentation and motion estimation over time, without requiring per-frame annotations.
The paper introduces ORBIT, a self‑supervised method for detecting end‑diastolic and end‑systolic cardiac phases in fetal echocardiography without manual annotations. ORBIT learns a latent motion trajectory through registration, enabling orientation‑robust identification of phase transitions across diverse fetal heart positions. Evaluated on normal and congenital heart disease cases, it achieves low mean absolute errors (≈1.9–2.4 frames) and outperforms prior annotation‑free approaches that assume fixed orientations.
By Yingyu Yang, Qianye Yang, Can Peng, Elena D'Alberti, Olga Patey, Aris T. Papageorghiou, J. Alison Noble
EchoXFlow is a new clinical echocardiography dataset that preserves ultrasound recordings in their native acquisition geometry, offering 35,377 recordings from 666 routine-care examinations of 622 patients. Unlike existing datasets, it retains separate modality streams—including temporally resolved 1D, 2D, and 3D data, multiple Doppler modalities, and synchronized ECG—along with clinical annotations ranging from guideline-defined measurements to dense 2D myocardial contours and 3D left‑ventricular endocardial meshes. The accompanying open‑source tooling enables cross‑modal, acquisition‑aware learning tasks that are impossible with conventional scan‑converted videos, positioning EchoXFlow as a testbed for 4D vision and physically grounded multi‑modal learning.
By Elias Stenhede, Joanna Sulkowska, Eivind Bj{\o}rkan Orstad, Henrik Schirmer, Arian Ranjbar
arXiv:2609.08043v1 Announce Type: cross
Abstract: Deep learning has achieved state-of-the-art performance in echocardiographic video segmentation, with an increasing number of models incorporating te...
By Jiyoo Noh, Jonathan H. Chan
arXiv:2610.05603v2 Announce Type: replace
Abstract: Echocardiography is the most widely used cardiac imaging modality, yet interpretation demands integrating visual evidence across global anatomy, lo...
By Sheng Cheng, Donnchadh M. O'Sullivan, Daniel J. Penny, Craig G. Rusin, Minh B. Nguyen, Devika Subramanian
arXiv:2606. 17437v1 Announce Type: cross Abstract: Automated classification of standard echocardiographic views is crucial for efficient clinical workflow but faces three main challenges.
By Bo Gou, Jicheng Zhang, Jianlong Xiong, Tao He, Bentian Liu, Hai Wu, Yijiao Wang, Yu Zhang, Yujia Yang, Yun Dai, Jian Liu, Jie Wang
arXiv:2608. 01677v1 Announce Type: cross Abstract: Myocardial strain analysis of cardiac magnetic resonance (CMR) images provides an important tool for evaluating cardiac function.
By Rishov Paul, Frederick H. Epstein, Miaomiao Zhang