Automated ultrasound doppler angle estimation using deep learning
This addresses a specific bottleneck in medical imaging for clinicians by automating a critical step in Doppler ultrasound workflows, though it is incremental as it applies existing deep learning methods to a known problem.
The paper tackled the problem of automated Doppler angle estimation in ultrasound to reduce errors in blood velocity measurements, achieving a mean absolute error as low as 3.9° with a deep learning approach that outperformed acceptable clinical thresholds.
Angle estimation is an important step in the Doppler ultrasound clinical workflow to measure blood velocity. It is widely recognized that incorrect angle estimation is a leading cause of error in Doppler-based blood velocity measurements. In this paper, we propose a deep learning-based approach for automated Doppler angle estimation. The approach was developed using 2100 human carotid ultrasound images including image augmentation. Five pre-trained models were used to extract images features, and these features were passed to a custom shallow network for Doppler angle estimation. Independently, measurements were obtained by a human observer reviewing the images for comparison. The mean absolute error (MAE) between the automated and manual angle estimates ranged from 3.9° to 9.4° for the models evaluated. Furthermore, the MAE for the best performing model was less than the acceptable clinical Doppler angle error threshold thus avoiding misclassification of normal velocity values as a stenosis. The results demonstrate potential for applying a deep-learning based technique for automated ultrasound Doppler angle estimation. Such a technique could potentially be implemented within the imaging software on commercial ultrasound scanners.