Development of novel machine learning model for right ventricular quantification on echocardiography—A multimodality validation study
Autor: | Ines Sherifi, Jonathan W. Weinsaft, Jiwon Kim, Brian Yum, Ashley Beecy, Mukund Das, Alex Bratt, Richard B. Devereux, Razia Sultana |
---|---|
Rok vydání: | 2020 |
Předmět: |
Validation study
Heart Ventricles Ventricular Dysfunction Right Population Automated segmentation Original Investigations Magnetic Resonance Imaging Cine right ventricle 030204 cardiovascular system & hematology Machine learning computer.software_genre Best Paper Machine Learning 03 medical and health sciences 0302 clinical medicine Humans Medicine Radiology Nuclear Medicine and imaging cardiovascular diseases 030212 general & internal medicine education Original Investigation Reproducibility education.field_of_study business.industry Reproducibility of Results Predictive value right ventricular function Echocardiography Rv function Ventricular Function Right cardiovascular system Manual segmentation Artificial intelligence Cardiology and Cardiovascular Medicine Cardiac magnetic resonance business computer |
Zdroj: | Echocardiography (Mount Kisco, N.y.) |
ISSN: | 1540-8175 0742-2822 |
Popis: | Purpose Echocardiography (echo) is widely used for right ventricular (RV) assessment. Current techniques for RV evaluation require additional imaging and manual analysis; machine learning (ML) approaches have the potential to provide efficient, fully automated quantification of RV function. Methods An automated ML model was developed to track the tricuspid annulus on echo using a convolutional neural network approach. The model was trained using 7791 image frames, and automated linear and circumferential indices quantifying annular displacement were generated. Automated indices were compared to an independent reference of cardiac magnetic resonance (CMR) defined RV dysfunction (RVEF |
Databáze: | OpenAIRE |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |