Deep Learning on Ultrasound Images Visualizes the Femoral Nerve with Good Precision

Abstract

The number of hip fractures per year worldwide is estimated to reach 6 million by the year 2050. Despite the many advantages of regional blockades when managing pain from such a fracture, these are used to a lesser extent than general analgesia. One reason is that the opportunities for training and obtaining clinical experience in applying nerve blocks can be a challenge in many clinical settings. Ultrasound image guidance based on artificial intelligence may be one way to increase nerve block success rate. We propose an approach using a deep learning semantic segmentation model with U-net architecture to identify the femoral nerve in ultrasound images. The dataset consisted of 1410 ultrasound images that were collected from 48 patients. The images were manually annotated by a clinical professional and a segmentation model was trained. After training the model for 350 epochs, the results were validated with a 10-fold cross-validation. This showed a mean Intersection over Union of 74%, with an interquartile range of 0.66–0.81.

Artificial intelligence for ultrasound scanning in regional anaesthesia: a scoping review of the evidence from multiple disciplines

“…Early approaches, most published before 2016–17, typically involved steps of feature extraction from the ultrasound image, followed by classification of these features, for both PNB 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 and CNB. 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 Around this point, there has been an increase in published data where the dominant technique was deep learning for both PNB 9 , 11 , 12 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 and CNB, 7 , 74 , 75 , …”

“…In the available sources, a variety of human image interpretation was used as the ground truth. This included a range in the number of humans used in the ground truth from one, 7 , 23 , 24 , 25 , 31 , 32 , 34 , 35 , 36 , 38 , 46 , 49 , 58 , 60 , 67 , 72 , 77 two, 8 , 9 , 19 , 21 , 26 , 30 , 33 , 44 , 61 three, 51 , 52 , 53 , 63 , 65 and up to 15. 48 Some sources cited ‘multiple’ humans, used a plural term (e.g.…”

“…In addition to the varying number of humans contributing to the ground truth in model development, there was variation in the specialty and experience of those contributing. Sources described their ground truth human(s) as a volunteer, 64 doctor/physician, 48 , 52 , 63 , 65 sonographer, 7 , 30 , 31 , 32 , 33 , 34 , 35 , 60 , 75 , 77 clinical professional, 27 , 38 or (regional) anaesthetist. 8 , 17 , 18 , 19 , 20 , 21 , 23 , 25 , 26 , 36 , 44 , 45 , 46 , 49 , 51 , 53 , 54 , 58 , 61 , 62 , 67 , 69 The level of expertise of those providing the ground truth was described as trained, 64 experienced, 21 , 30 , 31 , 32 , 33 , 34 , 46 , 48 , 52 , 65 expert, 7 , 8 , 17 , 18 , 19 , 20 , 25 , ...…”

“…The most common output for models processing PNB ultrasound images was segmentation (the outline/colour overlay of features in the image). 9 , 11 , 12 , 19 , 20 , 22 , 23 , 25 , 27 , 36 , 38 , 39 , 40 , 41 , 42 , 43 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 57 , 58 , 59 , 60 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 71 , 72 , 78 , 79 Less common outputs included the use of bounding boxes to identify the location of the structure, 8 , 17 , 18 , 26 , 61 attempting to locate the centre of a nerve and placing expanding circular rings from the centre, 21 or placing name tags over structures in question. 9 , 43 , 45 , 47 , 50 …”

“…the outline of a blood vessel) were intersection over union (IoU; Jaccard similarity coefficient) and the Dice similarity coefficient. 8 , 17 , 18 , 19 , 20 , 23 , 25 , 27 , 28 , 38 , 42 , 46 , 49 , 51 , 52 , 53 , 54 , 55 , 57 , 58 , 59 , 60 , 62 , 63 , 64 , 65 , 66 , 68 , 69 , 71 , 79 The Hausdorff metric/distance was used to compare the proximity of lines (e.g. a fascial plane).…”