Why the study?
The PISA method for MR quantification exhibits high inter-observer variability and inaccuracies in cases of non-hemispherical flow convergence and non-holosystolic MR.
Does the EasyPISA deep learning framework provide accurate automated integrated PISA measurements of mitral regurgitation compared to manual PISA and cMRI?
Population
54 patients for model training and 26 MR patient examinations for retrospective testing
Comparison
EasyPISA automated measurements vs reference PISA and cMRI measurements
Design
Retrospective deep learning model development and validation study
Authors
Loading...
May reduce interobserver variability in mitral regurgitation assessment; leaves open prospective validation before routine adoption.
Does the EasyPISA deep learning framework provide accurate automated integrated PISA measurements of mitral regurgitation compared to manual PISA and cMRI?
EasyPISA provides a fully automated deep learning approach for quantifying mitral regurgitation from 2-D color-Doppler, showing good correlation with manual PISA and cMRI, which may reduce workload and inter-observer variability.
Wifstad et al. (2024) studied this question.