Key result
A convolutional neural network for automatic characterization of carotid plaque composition achieved a correlation of about 0.90 with expert clinical assessment for estimating plaque constituents.
Why the study?
Does a convolutional neural network accurately characterize plaque composition in carotid ultrasound compared to expert clinical assessment?
Population
Approximately 90,000 patches extracted from a database of carotid ultrasound images with corresponding…
Comparison
Convolutional neural network for automatic… vs Expert clinical assessment
Design
Other
Authors
Loading...
May enable automated plaque analysis in research; leaves open clinical utility pending prospective validation.
Does a convolutional neural network accurately characterize plaque composition in carotid ultrasound compared to expert clinical assessment?
Effect estimate: Correlation ~0.90
A convolutional neural network can automatically characterize carotid plaque composition from ultrasound images with high correlation to expert assessment.
Lekadir et al. (2016) studied Carotid plaque. Convolutional neural network (CNN) vs. Expert clinical assessment was evaluated on Correlation with clinical assessment for the estimation of lipid core, fibrous cap, and calcified tissue areas (Correlation ~0.90). A convolutional neural network for automatic characterization of carotid plaque composition achieved a correlation of about 0.90 with expert clinical assessment for estimating plaque constituents.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: