Creation and Testing of a Deep Learning Algorithm to Automatically Identify and Label Vessels, Nerves, Tendons, and Bones on Cross-sectional Point-of-Care Ultrasound Scans for Peripheral Intravenous Catheter Placement by Novices.
Michael BlaivasRobert ArntfieldMatthew WhitePublished in: Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine (2020)
Our DL algorithm proved accurate at identifying 4 common structures on cross-sectional US imaging of the UE, which would allow novice POCUS providers to more confidently and accurately target vessels for cannulation, avoiding other structures. Overall, the algorithm outperformed 2 blinded POCUS experts.
Keyphrases
- deep learning
- cross sectional
- high resolution
- ultrasound guided
- machine learning
- artificial intelligence
- convolutional neural network
- magnetic resonance imaging
- computed tomography
- neural network
- extracorporeal membrane oxygenation
- clinical trial
- low dose
- randomized controlled trial
- study protocol
- magnetic resonance
- fluorescence imaging
- photodynamic therapy