Why the study?
Do state-of-the-art deep learning methods accurately segment cardiac structures and diagnose pathologies on CMRI compared to expert analysis?
Population
150 multi-equipments CMRI recordings with reference measurements and classification from two medical experts
Comparison
State-of-the-art deep learning methods for… vs Expert analysis
Design
Other
Authors
Loading...
Supports automated CMRI analysis in research; leaves open prospective clinical validation before adoption.
Do state-of-the-art deep learning methods accurately segment cardiac structures and diagnose pathologies on CMRI compared to expert analysis?
Deep learning methods demonstrate high accuracy and correlation with expert analysis for automated cardiac MRI segmentation and diagnosis, opening the door to fully automatic analysis.
Bernard et al. (2018) studied this question.