Publications by authors named "Camelia D Demetrescu"
Article Synopsis
- The study focuses on developing and validating an open machine-learning method for calculating Global Longitudinal Strain (GLS), which is deemed more reliable than traditional measures like ejection fraction.
- Using a neural network trained on over 6,800 echocardiogram images, researchers were able to accurately identify key cardiac landmarks and compute GLS values.
- The open-source methodology demonstrated comparable accuracy to expert measurements and proprietary solutions, with data and resources available freely online for further research.
Doppler echocardiography is a widely utilised non-invasive imaging modality for assessing the functionality of heart valves, including the mitral valve. Manual assessments of Doppler traces by clinicians introduce variability, prompting the need for automated solutions. This study introduces an innovative deep learning model for automated detection of peak velocity measurements from mitral inflow Doppler images, independent from Electrocardiogram information.
View Article and Find Full Text PDFBackground: requires training and validation to standards expected of humans. We developed an online platform and established the Unity Collaborative to build a dataset of expertise from 17 hospitals for training, validation, and standardization of such techniques.
Methods: The training dataset consisted of 2056 individual frames drawn at random from 1265 parasternal long-axis video-loops of patients undergoing clinical echocardiography in 2015 to 2016.