Real-time segmentation of blood vessels, nerves and bone in ultrasound-guided regional anesthesia using deep learning

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.