MATrix LABoratory Algorithm in Ultrasound Image-Guided General Drug Anesthesia along with Lumbar and Sacral Plexus Block in Hip Replacement under

Abstract

Objective. The study aimed to explore the application of ultrasound image-guided general drug anesthesia combined with lumbar and sacral plexus block based on MATrix LABoratory (MATLAB) algorithm in hip arthroplasty and to study its clinical effect. Methods. The classic geodesic active contour (GAC) algorithm and the improved fuzzy clustering level set algorithm were used to segment ultrasound images of waist plexus, and then their segmentation effects were compared. Both algorithms are from the MATrix LABoratory (MATLAB) platform. A total of 60 patients undergoing hip arthroplasty were selected and randomly enrolled into control and experimental groups. The control group accepted general drug anesthesia, and the experimental group accepted ultrasound-guided lumbar and sacral plexus block combined with general anesthesia. The mean arterial pressure and heart rate at t0 (before anesthesia), t1 (before ventilation), t2 (when the skin was incised), t3 (when the prosthesis was implanted), t4 (when the incision was closed), and t5 (at the end of ventilation) were observed, and the intraoperative sufentanil dosage and 24 h analgesic dosage, the incidence of postoperative delirium, and the incidence of cognitive dysfunction were recorded. Results. The improved fuzzy clustering level set algorithm was better than the GAC model algorithm in image segmentation and running time. In contrast with the control group, the average arterial pressure and heart rate of the experimental group at the four time points of t1, t2, t3, and t5 were obviously reduced ( P < 0.05). In contrast with the control group, the amount of sufentanil and analgesics in the experimental group was obviously reduced ( P < 0.05), and the incidence of postoperative cognitive dysfunction and delirium was obviously reduced ( P < 0.05). Conclusion. The improved fuzzy clustering level set algorithm is superior to the GAC model in image segmentation and running time. Under its guidance, the lumbar and sacral plexus block combined with general anesthesia has a good clinical effect in hip arthroplasty, which is better than simple general anesthesia.

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

“… 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 , 76 , 77 though there are some exceptions. 78 , 79 , 80 A number of sources do not explicitly state the techniques used; these are typically clinical case reports or (external) validation studies describing accuracy or efficacy 81 , 82 , 83 , 84 , 85 , 86 , 87 ,…”

“…For some sources, it is not clear how the ground truth for training data was obtained. 9 , 11 , 12 , 28 , 29 , 39 , 40 , 41 , 42 , 43 , 45 , 47 , 50 , 55 , 57 , 59 , 60 , 68 , 70 , 72 , 73 , 74 , 75 , 76 , 78 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 , 93 …”

“…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 …”

“…supraclavicular level brachial plexus or thoracic paravertebral block). 22 , 23 , 27 , 44 , 46 , 49 , 53 , 58 , 62 , 67 , 78 Other sources used a single structure class (e.g. nerve) from multiple regions, 8 , 36 , 54 or a single structure in a single region, such as the median nerve in the forearm, 17 , 18 , 19 , 20 , 61 , 69 the femoral artery, 28 , 72 the femoral nerve, 38 , 65 or the sciatic nerve.…”

“… 56 Cai and colleagues 48 report reduced paraesthesia during the first month of performing sciatic nerve blocks after teaching with an AI-based nerve identification system, though there was no difference in the rate of pain during injection, perforation of blood vessels or block success. Wang and colleagues 78 report reduced postoperative analgesic requirement and cognitive dysfunction/delirium after AI-assisted lumbosacral plexus block compared with systemic analgesia for hip arthroplasty surgery.…”