Machine learning in robotic ultrasound imaging: Challenges and perspectives

Y Bi, Z Jiang, F Duelmer, D Huang… - Annual Review of …, 2024 - annualreviews.org
This article reviews recent advances in intelligent robotic ultrasound imaging systems. We
begin by presenting the commonly employed robotic mechanisms and control techniques in …

Explainable artificial intelligence and cardiac imaging: toward more interpretable models

A Salih, I Boscolo Galazzo, P Gkontra… - Circulation …, 2023 - Am Heart Assoc
Artificial intelligence applications have shown success in different medical and health care
domains, and cardiac imaging is no exception. However, some machine learning models …

[HTML][HTML] Attri-VAE: Attribute-based interpretable representations of medical images with variational autoencoders

I Cetin, M Stephens, O Camara… - … Medical Imaging and …, 2023 - Elsevier
Deep learning (DL) methods where interpretability is intrinsically considered as part of the
model are required to better understand the relationship of clinical and imaging-based …

Cyclical self-supervision for semi-supervised ejection fraction prediction from echocardiogram videos

W Dai, X Li, X Ding, KT Cheng - IEEE Transactions on Medical …, 2022 - ieeexplore.ieee.org
Left-ventricular ejection fraction (LVEF) is an important indicator of heart failure. Existing
methods for LVEF estimation from video require large amounts of annotated data to achieve …

GUDU: Geometrically-constrained Ultrasound Data augmentation in U-Net for echocardiography semantic segmentation

C Sfakianakis, G Simantiris, G Tziritas - Biomedical Signal Processing and …, 2023 - Elsevier
Echocardiography is a very important medical examination that helps in the computation of
critical heart functions. Boundary identification, segmentation and estimation of the volume …

DSANet: Dual-branch shape-aware network for echocardiography segmentation in apical views

GQ Zhou, WB Zhang, ZQ Shi, ZR Qi… - IEEE Journal of …, 2023 - ieeexplore.ieee.org
Echocardiography is an essential examination for cardiac disease diagnosis, from which
anatomical structures segmentation is the key to assessing various cardiac functions …

[HTML][HTML] Multi-granularity learning of explicit geometric constraint and contrast for label-efficient medical image segmentation and differentiable clinical function …

Y Meng, Y Zhang, J Xie, J Duan, M Joddrell… - Medical Image …, 2024 - Elsevier
Automated segmentation is a challenging task in medical image analysis that usually
requires a large amount of manually labeled data. However, most current supervised …

Phase unwrapping of color doppler echocardiography using deep learning

HJ Ling, O Bernard, N Ducros… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Color Doppler echocardiography is a widely used noninvasive imaging modality that
provides real-time information about intracardiac blood flow. In an apical long-axis view of …

MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation

X Deng, H Wu, R Zeng, J Qin - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
We propose a novel echocardiographical video segmentation model by adapting SAM to
medical videos to address some long-standing challenges in ultrasound video segmentation …

Super-efficient echocardiography video segmentation via proxy-and kernel-based semi-supervised learning

H Wu, J Lin, W Xie, J Qin - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Automatic segmentation of left ventricular endocardium in echocardiography videos is
critical for assessing various cardiac functions and improving the diagnosis of cardiac …