arXiv:2606. 02634v1 Announce Type: cross Abstract: We introduce Echo-POSED, a self-supervised framework for real-time transthoracic echocardiography (TTE) guidance that recommends probe adjustments directly from 2D ultrasound images, without the need for expert-labelled views or tracked probe trajectories.
arXiv:2608. 07606v1 Announce Type: cross Abstract: Despite advances in 3D ultrasound, most percutaneous cardiac interventions still rely on 2D visualization, limiting depth perception and spatial understanding.
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.
The paper introduces a self‑supervised method for detecting end‑diastole (ED) and end‑systole (ES) in echocardiography by constraining the latent motion to a single‑parameter orbit, effectively modeling cardiac phase as a one‑dimensional signal. This approach yields an interpretable representation that directly identifies ED and ES, improving ED localisation and matching ES performance compared to prior state‑of‑the‑art methods, while using fewer training epochs and a more constrained model. The method is trained on EchoNet‑Dynamic without annotations and the code is publicly available.
arXiv:2608.28715v1 Announce Type: cross Abstract: Ultrasound-guided interventions can require localization of an untracked 2D frame within a 3D anatomical reference. Rigid slice-to-volume registratio...
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.
X-ray coronary angiography is the clinical gold standard for coronary artery disease during real-time cardiac interventions, but provides only 2D projections of inherently 3D vessels. Existing learnin...
arXiv:2607. 24553v1 Announce Type: cross Abstract: Standardized echocardiography conclusions provide meaningful supervision for learning ECG representations of echocardiography-derived cardiac findings.
arXiv:2609.09577v1 Announce Type: cross Abstract: Myocardial strain from echocardiography is a key biomarker for cardiac function. Recent deep learning methods show strong performance for myocardial...
UBone3D is a new framework that completes 3D anatomical shapes from partial ultrasound point clouds using physics-rectified conditional flow matching. It models ultrasound artifacts with a simulated physics proxy and applies test-time physics rectification to guide the completion. The method combines a CT-trained generative shape prior and a physics consistency network, achieving higher reconstruction accuracy and anatomical fidelity than existing baselines.
Developing robust artificial intelligence models for 4D (3D + time) medical imaging is constrained by limited annotated data, inter-device domain shifts, and privacy restrictions. To address this, we propose a 4D controllable generative framework for anatomically consistent data augmentation.
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.
MIGA is a scan‑specific framework for accelerated 3D multi‑echo MRI that uses shared anisotropic Gaussian geometry, a coordinate‑conditioned multi‑output amplitude network, and explicit echo‑specific phase variables. The method jointly optimizes all components from undersampled multi‑coil k‑space data without requiring fully sampled training data. Experiments demonstrate that MIGA outperforms existing methods across various imaging tasks and acceleration factors, especially under stronger undersampling, and offers a favorable quality‑cost balance among full‑volume multi‑echo reconstruction techniques.