Ultrasound images acquired during axillary nerve block procedures can be difficult to interpret.Highlighting the important structures, such as nerves and blood vessels, may be useful for the training of inexperienced users. A deep convolutional neural network is used to identify the musculocutaneous, median, ulnar, and radial nerves, as well as the blood vessels in ultrasound images. A dataset of 49 subjects is collected and used for training and evaluation of the neural network. Several image augmentations, such as rotation, elastic deformation, shadows, and horizontal flipping, are tested. The neural network is evaluated using cross validation. The results showed that the blood vessels were the easiest to detect with a precision and recall above 0.8. Among the nerves, the median and ulnar nerves were the easiest to detect with an F -score of 0.73 and 0.62, respectively. The radial nerve was the hardest to detect with an F -score of 0.39. Image augmentations proved effective, increasing F -score by as much as 0.13. A Wilcoxon signed-rank test showed that the improvement from rotation, shadow, and elastic deformation augmentations were significant and the combination of all augmentations gave the best result. The results are promising; however, there is more work to be done, as the precision and recall are still too low. A larger dataset is most likely needed to improve accuracy, in combination with anatomical and temporal models.

No abstract

Images from ultrasound-guided regional anesthesia procedures can be difficult to interpret, especially by non-experts.In this work, deep convolutional neural networks were used to segment blood vessels, nerves and bone from two different nerve block procedures; the axillary nerve block and the femoral nerve block, which are commonly used to block sensation of pain from arms and legs respectively.The results show that the detection performance vary a lot for different nerves, with the best F1 and Dice scores of 0.84 and 0.67 for the median nerve, and the worst score of 0.54 and 0.51 for the ulnar nerve. Blood vessels and bone are generally easy to detect, but small veins can be difficult to segment accurately.Using the trained neural networks, a portable prototype system able to stream, process and visualize the results in real-time was created using a laptop, the FAST framework, and a Clarius L15 HD scanner. The runtime was measured to be about 31 milliseconds per frame.