This work creates the first publicly available resource for predicting left ventricular ejection fraction (EF) from parasternal long-axis (PLAX) echocardiography by leveraging a time-based correlation between clinical notes and echocardiographic videos and fine-tuning view classifiers and proxy labeling.
This work creates the first publicly available resource for predicting left ventricular ejection fraction (EF) from parasternal long-axis (PLAX) echocardiography by leveraging a time-based correlation between clinical notes and echocardiographic videos and fine-tuning view classifiers and proxy labeling.
The findings support controlled external validation under explicit image and target harmonization, while further prospective validation, calibration, and quality-control mechanisms are needed before clinical deployment.
Adrian Krenzer, Viktoria Wieser, Tobias Friedetzki· BMC Medical Imaging· 0 citations
Echocardiography is the most widely used cardiac imaging modality, yet interpretation demands integrating visual evidence across global anatomy, localized structures and dynamic cardiac motion, and Motion-biased Entropy Maximization Sampling (MEMS) to select the most informative frames for video-level analysis is intro...
Cheng Sheng, Donnchadh M. O'Sullivan, Daniel J. Penny et al.· 0 citations
Multimodal pretraining improved frozen DINO models over the uni-modal baseline, but its benefits diminished after fine-tuning, suggesting that encoder initialization and down-stream adaptation were more influential than increasingly complex echocardiographic supervision.
Jad Haidamous, Laura Valeria Perez-Herrera, Miriam Guti'errez et al.· 0 citations
The limited availability of imaging data for uncommon cardiovascular phenotypes constrains the development of robust imaging models. We evaluated whether class-conditional diffusion models can generate synthetic transthoracic echocardiograms that improve downstream cardiac imaging tasks. The primary application was car...
Pengfei Lyu, Ricardo Henao, L. Kwee et al.· medRxiv· 0 citations
Deep video networks estimate left ventricular ejection fraction from echocardiograms with expert-level accuracy, but the compute cost of running them is rarely reported, so this work sets a practical floor for how inexpensive this task can be.
A. Pandey, K. Sharma, A. Shah· medRxiv· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
