Abstract
Background
Ultrasonound is used to identify anatomical structures during regional anaesthesia and to guide needle insertion and injection of local anaesthetic. ScanNav Anatomy Peripheral Nerve Block (Intelligent Ultrasound, Cardiff, UK) is an artificial intelligence-based device that produces a colour overlay on real-time B-mode ultrasound to highlight anatomical structures of interest. We evaluated the accuracy of the artificial-intelligence colour overlay and its perceived influence on risk of adverse events or block failure.
Methods
Ultrasound-guided regional anaesthesia experts acquired 720 videos from 40 volunteers (across nine anatomical regions) without using the device. The artificial-intelligence colour overlay was subsequently applied. Three more experts independently reviewed each video (with the original unmodified video) to assess accuracy of the colour overlay in relation to key anatomical structures (true positive/negative and false positive/negative) and the potential for highlighting to modify perceived risk of adverse events (needle trauma to nerves, arteries, pleura, and peritoneum) or block failure.
Results
The artificial-intelligence models identified the structure of interest in 93.5% of cases (1519/1624), with a false-negative rate of 3.0% (48/1624) and a false-positive rate of 3.5% (57/1624). Highlighting was judged to reduce the risk of unwanted needle trauma to nerves, arteries, pleura, and peritoneum in 62.9–86.4% of cases (302/480 to 345/400), and to increase the risk in 0.0–1.7% (0/160 to 8/480). Risk of block failure was reported to be reduced in 81.3% of scans (585/720) and to be increased in 1.8% (13/720).
Conclusions
Artificial intelligence-based devices can potentially aid image acquisition and interpretation in ultrasound-guided regional anaesthesia. Further studies are necessary to demonstrate their effectiveness in supporting training and clinical practice.
Clinical trial registration
Keywords: anatomy, artificial intelligence, machine learning, regional anaesthesia, translational AI, ultrasonography, ultrasound
Editor's key points.
-
•
Ultrasound-guided regional anaesthesia facilitates precision, safety, and effectiveness of peripheral nerve block, but it is technically challenging without advanced training.
-
•
The use of ScanNav™ (Intelligent Ultrasound, Cardiff, UK), an artificial intelligence-based device that produces a colour overlay on real-time ultrasound images to highlight anatomical structures of interest, was evaluated.
-
•
Experts reviewed 720 ultrasound videos, with and without ScanNavTM highlighting, to assess accuracy and perceived effect on regional anaesthesia safety and efficacy.
-
•
The device showed high true-positive/true-negative and low false-positive/false-positive rates in identifying key anatomical structures for the performance of nine peripheral nerve blocks.
-
•
Further studies are necessary to demonstrate its effectiveness in supporting training and clinical practice.
The use of ultrasound as image guidance for regional anaesthesia was first described in 19891 and is now the predominant technique used to guide needle insertion and local anaesthetic deposition.2 Ultrasound-guided regional anaesthesia (UGRA) can be used to avoid risks associated with general anaesthesia,3 enhance operating theatre efficiency, and reduce hospital length of stay.4 Evidence also supports a role in improving outcomes after surgery4,5 and in mitigating the need for systemic analgesia with dangerous side-effects, such as opioids.2,4
However, patient access to UGRA can be limited by the availability of a specialist with prerequisite knowledge and skills.6 Fundamental skills are the acquisition and interpretation of optimal ultrasound images, which involves identification of key sono-anatomical structures.7 Assistive artificial intelligence (AI) technology could play a role in the future practice of UGRA through supporting ultrasound scanning.8,9 ScanNav Anatomy Peripheral Nerve Block (Intelligent Ultrasound, Cardiff, UK) uses deep learning based on the U-Net architecture10 to produce a colour overlay on real-time B-mode ultrasound and highlight structures of interest in UGRA (Fig 1; Supplementary files A–E). The AI models in this system have been trained on more than 800,000 ultrasound images.11 Training data are presented to the algorithm as paired unmodified ultrasound image and labelled colour overlay (highlighting the relevant structures on that image). Over time, the algorithm learns to make associations between the labelled region and data in the image. When deployed, it is thus able to make predictions on data in new images and provide a colour overlay on real-time ultrasound. (Further information on the training data is available in Supplementary file F.) It is envisaged that a real-time colour overlay will draw attentional gaze of the operator to the key anatomical structures. Previous work supports the concept that it can aid in acquisition of the correct ultrasound view and correct identification of structures of interest on that view.12
Fig 1.
Example of the colour overlay produced by ScanNav when scanning during a supraclavicular-level brachial plexus block. Blue, first rib; purple, pleura; red, subclavian artery; and yellow, supraclavicular-level brachial plexus nerves (trunks/divisions).
In this prospective external validation study, experts in UGRA acquired ultrasound scans (without use of ScanNav), and further experts evaluated performance of the AI models. Accuracy of the colour overlay was assessed in relation to key anatomical structures. The perceived potential for highlighting to modify the risk of adverse events (i.e. risk of needle trauma to nerves, arteries, pleura, and peritoneum) and block failure was also evaluated.
Methods
Ethical approval for the collection of ultrasonography scans from healthy volunteers was granted by the Oregon Health & Science University (OHSU) Institutional Review Board (STUDY00022920). The study was registered with ClinicalTrials.gov (NCT04906018).
Ultrasonography scan collection
The process of scan acquisition and review is summarised in Fig 2. Four UGRA experts were recruited from the anaesthesia faculty at OHSU after providing written informed consent. All were board-certified attending anaesthesiologists who had completed advanced training in UGRA (fellowship or equivalent) and regularly use these techniques in their clinical practice.
Fig 2.
Summary of study workflow. AI, artificial intelligence; PNB, peripheral nerve block; UGRA, ultrasound-guided regional anaesthesia.
Forty healthy adult subjects were recruited for scanning after providing written informed consent. Exclusion criteria were age <18 yr and known pathology affecting the areas scanned. Scanning was performed using the SonoSite X-Porte (HFL50xp and L38xp linear probes or C60xp curvilinear probe) and PX (L15–5 and L12-3 linear probes or C5-1 curvilinear probe) ultrasound machines (FUJIFILM SonoSite, Bothell, WA, USA).
Each expert scanned 10 subjects (bilaterally) without ScanNav over anatomical regions relevant to nine specific peripheral nerve blocks (PNBs). Upper-limb block regions scanned included the interscalene-level brachial plexus, upper trunk of the brachial plexus, supraclavicular-level brachial plexus (SC), and the axillary-level brachial plexus (AxBP) blocks. Thoracoabdominal block regions included the erector spinae plane (ESP) and rectus sheath (RSB) blocks. Lower-limb block regions comprised the suprainguinal fascia iliaca, adductor canal/distal femoral triangle, and popliteal-level sciatic nerve blocks.
A total of 720 scans were performed. For each scan, the scanner stated when they had acquired what they felt to be the optimal view. This frame and the preceding 10 s of the scan were used for later review. Predictive colour overlay, derived by ScanNavTM, was subsequently applied to the ultrasound clips obtained in the acquisition protocol.
Key anatomical structures and adverse events
Nerves, arteries, pleura, and peritoneum were considered as safety-critical structures (although the pleura, in the context of the ESP block, is not typically in view when the needle is inserted,13 and thus, risk of pneumothorax is low). Target structures for UGRA include peripheral nerves and fascial planes. Therefore, highlighting of the rectus sheath and fascia iliaca and the transverse process of thoracic vertebrae were assessed. The structures for each PNB are detailed in Table 1.
Table 1.
Key anatomical structures for ultrasonography-guided regional anaesthesia safety and block success.
| Peripheral nerve block region | Nerve | Artery | Serosal plane | Bone | Fascia |
|---|---|---|---|---|---|
| Interscalene-level brachial plexus block | C5 and C6 nerve roots | ||||
| Upper-trunk block | Upper trunk of brachial plexus | ||||
| Supraclavicular-level brachial plexus block | Trunks/divisions of brachial plexus | Subclavian artery | Pleura | ||
| Axillary-level brachial plexus block | Musculocutaneous, median, ulnar, and radial nerves | Axillary artery | |||
| Erector spinae plane block | Pleura | Transverse process | |||
| Rectus sheath block | Peritoneum | Rectus sheath | |||
| Suprainguinal fascia iliaca block | Deep circumflex iliac artery | Fascia iliaca | |||
| Adductor canal block | Saphenous nerve | Femoral artery | |||
| Popliteal-level sciatic nerve block | Sciatic nerve | Popliteal artery |
Expert reviewer evaluation
Six additional UGRA experts were recruited for analysis of the highlighting on the recorded scans. Three were based in the USA (board-certified attending anaesthesiologists) and three in Europe (consultant anaesthetist or equivalent). All had completed advanced training in UGRA (fellowship or equivalent) and regularly use these techniques in their clinical practice.
Unmodified ultrasound scans and colour-highlighted scan pairs were presented to expert reviewers via an online platform. Videos in the pair played simultaneously with the expert reviewers at liberty to play/pause at their discretion and view multiple times. Scans were labelled with the subject age, sex, and BMI. Three expert reviewers assessed each scan independently: none knew the scans allocated to other expert reviewers or the outcome of their evaluation. A consensus view was taken for each assessment; in cases where no majority was reached, this was classified as ‘no consensus’.
For the relevant structures in each scan, reviewers were asked to appraise highlighting accuracy and associated adverse events through the following statements:
-
(i)
The [colour] highlighting for the [anatomical structure]
-
(a)
Correctly identifies the [anatomical structure] (true positive; TP)
-
(b)
Is in the wrong location (false positive; FP)
-
(c)
Is not present and the [anatomical structure] is not present (true negative; TN)
-
(d)
Is not present but the [anatomical structure] is present (false negative; FN)
-
(ii)
Regarding the risk of [specific adverse event], the highlighting seen in this clip
-
(a)
Increases the risk of [specific adverse event]
-
(b)
Does not change the risk of [specific adverse event]
-
(c)
Reduces the risk of [specific adverse event]
-
(iii)
Regarding the risk of block failure, the highlighting seen in this clip
-
(a)
Increases the risk of block failure
-
(b)
Does not change the risk of block failure
-
(c)
Reduces the risk of block failure
Statistical analysis
As this study used a clinical and subjective assessment of the AI models, descriptive statistics of both accuracy and efficacy (perceived influence on risk of adverse event or block failure) have been reported in a manner that reflects clinical use. As all structures for a block region can be present or absent on any single scan, the reported accuracy is presented for each PNB and overall. Accuracy was defined as the sum of the true-positive rate (TPr; TP/total structures) and true-negative rate (TNr; TN/total structures). Rates of false positive (FPr) and false negative (FNr) were similarly calculated but reported independently because of the clinical implications of discriminating between FP and FN.
Results
Mean age of the scan subjects was 41.2 (min–max: 23–64; standard deviation [sd] 13.4) yr, and mean BMI was 28.9 (19.7–40.4; 6.1) kg m−2, with an equal male:female ratio.
Accuracy
Table 2 shows a summary of the accuracy assessments made by the expert reviewers. Twenty-one key anatomical structures were considered across nine PNBs. Each PNB region was scanned 80 times; thus, a total of 1680 key anatomical structures were assessed, each one by three expert reviewers. A majority view of expert opinion was determined in 1624 structures (96.7%); no consensus was reached in 56 (3.3%).
Table 2.
Perceived accuracy assessment by peripheral nerve block. FNr, false-negative rate; FPr, false-positive rate; TNr, true-negative rate; TPr, true-positive rate.
| Peripheral nerve block | True positive |
True negative |
False positive |
False negative |
Accuracy (TPr+TNr) | Total structures | ||||
|---|---|---|---|---|---|---|---|---|---|---|
| TPr | Structures | TNr | Structures | FPr | Structures | FNr | Structures | |||
| Interscalene-level brachial plexus block | 0.908 | 139 | 0.033 | 5 | 0.013 | 2 | 0.046 | 7 | 0.941 | 153 |
| Upper-trunk block | 0.896 | 69 | 0.013 | 1 | 0.052 | 4 | 0.039 | 3 | 0.909 | 77 |
| Supraclavicular-level brachial plexus block | 0.958 | 226 | 0.025 | 6 | 0.008 | 2 | 0.008 | 2 | 0.983 | 236 |
| Axillary-level brachial plexus block | 0.951 | 366 | 0.026 | 10 | 0.003 | 1 | 0.021 | 8 | 0.977 | 385 |
| Erector spinae plane block | 0.638 | 97 | 0.250 | 38 | 0.000 | 0 | 0.112 | 17 | 0.888 | 152 |
| Rectus sheath block | 0.968 | 149 | 0.000 | 0 | 0.032 | 5 | 0.000 | 0 | 0.968 | 154 |
| Suprainguinal fascia iliaca block | 0.702 | 106 | 0.060 | 9 | 0.219 | 33 | 0.020 | 3 | 0.762 | 151 |
| Adductor canal block | 0.872 | 136 | 0.032 | 5 | 0.000 | 0 | 0.096 | 15 | 0.904 | 156 |
| Popliteal-level sciatic nerve block | 0.875 | 140 | 0.106 | 17 | 0.006 | 1 | 0.013 | 2 | 0.981 | 160 |
| Average/total | 0.879 | 1428 | 0.056 | 91 | 0.030 | 48 | 0.035 | 57 | 0.935 | 1624 |
Mean accuracy (TPr+TNr) was 93.5% (1519/1624; TPr 87.9% and TNr 5.6%; min–max accuracy: 76.2–98.3; sd 6.7; 95% confidence interval [CI]: 89.1–97.9). Rate of structure misidentification (FPr) was 3.0% (48/1624; 0–21.9; sd 6.6; 95% CI: 0.0–7.3) and non-identification of a structure (FNr) was 3.5% (57/1624; 0–11.2; sd 3.7; 95% CI: 1.1–5.9). Further detail for each block and structure is presented in Supplementary file F.
Adverse events and block failure
Table 3 shows a summary of the influence of device highlighting on perceived adverse events according to assessments made by remote experts. Examples of this highlighting are shown in Fig 3 and Supplementary files A–E. Further information is presented in Supplementary file F.
Table 3.
Influence of highlighting on risk of adverse events and block failure.
| Peripheral nerve block | Increase |
No change |
Reduce |
No consensus |
Total structures | ||||
|---|---|---|---|---|---|---|---|---|---|
| % | Structures | % | Structures | % | Structures | % | Structures | ||
| Nerve injury/postoperative neurological symptoms (where nerves highlighted) | |||||||||
| Interscalene-level brachial plexus block | 5.0 | 4 | 10.0 | 8 | 73.8 | 59 | 11.2 | 9 | 80 |
| Upper-trunk block | 0.0 | 0 | 62.5 | 50 | 37.5 | 30 | 0.0 | 0 | 80 |
| Supraclavicular-level brachial plexus block | 2.5 | 2 | 2.5 | 2 | 93.8 | 75 | 1.2 | 1 | 80 |
| Axillary-level brachial plexus block | 0.0 | 0 | 33.8 | 27 | 56.2 | 45 | 10.0 | 8 | 80 |
| Adductor canal block | 0.0 | 0 | 72.5 | 58 | 21.2 | 17 | 6.2 | 5 | 80 |
| Popliteal-level sciatic nerve block | 2.5 | 2 | 0.0 | 0 | 95.0 | 76 | 2.5 | 2 | 80 |
| Average/total |
1.7 |
8 |
30.2 |
145 |
62.9 |
302 |
5.2 |
25 |
480 |
| Local anaesthetic systemic toxicity (where arteries highlighted) | |||||||||
| Supraclavicular-level brachial plexus block | 2.5 | 2 | 2.5 | 2 | 92.5 | 74 | 2.5 | 2 | 80 |
| Axillary-level brachial plexus block | 2.5 | 2 | 1.2 | 1 | 91.2 | 73 | 5.0 | 4 | 80 |
| Suprainguinal fascia iliaca block | 0.0 | 0 | 8.8 | 7 | 81.2 | 65 | 10.0 | 8 | 80 |
| Adductor canal block | 0.0 | 0 | 2.5 | 2 | 96.2 | 77 | 1.2 | 1 | 80 |
| Popliteal-level sciatic nerve block | 1.2 | 1 | 25.0 | 20 | 70.0 | 56 | 3.8 | 3 | 80 |
| Average/total |
1.2 |
5 |
8.0 |
32 |
86.2 |
345 |
4.5 |
18 |
400 |
| Pneumothorax (only where pleura highlighted) | |||||||||
| Supraclavicular-level brachial plexus block | 0.0 | 0 | 1.2 | 1 | 97.5 | 78 | 1.2 | 1 | 80 |
| Erector spinae plane block | 0.0 | 0 | 25.0 | 20 | 55.0 | 44 | 20.0 | 16 | 80 |
| Average/total |
0.0 |
0 |
13.1 |
21 |
76.2 |
122 |
10.6 |
17 |
160 |
| Peritoneum violation (only where peritoneum highlighted) | |||||||||
| Rectus sheath block | 1.2 | 1 | 13.8 | 11 | 82.5 | 66 | 2.5 | 2 | 80 |
| Average/total |
1.25 |
1 |
13.75 |
11 |
82.50 |
66 |
2.5 |
2 |
80 |
| Block failure (all blocks) | |||||||||
| Interscalene-level brachial plexus block | 3.8 | 3 | 10.0 | 8 | 78.8 | 63 | 7.5 | 6 | 80 |
| Upper-trunk block | 2.5 | 2 | 8.8 | 7 | 81.2 | 65 | 7.5 | 6 | 80 |
| Supraclavicular-level brachial plexus block | 1.2 | 1 | 1.2 | 1 | 93.8 | 75 | 3.8 | 3 | 80 |
| Axillary-level brachial plexus block | 0.0 | 0 | 8.8 | 7 | 70.0 | 56 | 21.5 | 17 | 80 |
| Erector spinae plane block | 3.8 | 3 | 15.0 | 12 | 68.8 | 55 | 12.5 | 10 | 80 |
| Rectus sheath block | 2.5 | 2 | 10.0 | 8 | 83.8 | 67 | 3.8 | 3 | 80 |
| Suprainguinal fascia iliaca block | 1.2 | 1 | 0.0 | 0 | 97.5 | 78 | 1.2 | 1 | 80 |
| Adductor canal block | 0.0 | 0 | 30.0 | 24 | 62.5 | 50 | 7.5 | 6 | 80 |
| Popliteal-level sciatic nerve block | 1.2 | 1 | 0.0 | 0 | 95.0 | 76 | 3.8 | 3 | 80 |
| Average/total | 1.8 | 13 | 9.3 | 67 | 81.2 | 585 | 7.6 | 55 | 720 |
Fig 3.
Examples of the artificial-intelligence colour overlay for each peripheral nerve block studied. ALM, adductor longus muscle; AS, anterior scalene; BPN, brachial plexus nerves (trunks/divisions); CPN, common peroneal (fibular) nerve; CTf, fascia overlying conjoint tendon; C5, C5 nerve root; C6, C6 nerve root; DCIA, deep circumflex iliac artery; ESM, erector spinae muscle group (and overlying muscles); FA, femoral artery; FI, fascia iliaca; H, humerus; I, ilium; IM, iliacus/iliopsoas muscle; McN, musculocutaneous nerve; MN, median nerve; Pe, peritoneum and contents; Pl, pleura; R, first rib; RA, rectus abdominis muscle; RN, radial nerve; RSa, anterior layer of rectus sheath; RSp, posterior layer of rectus sheath; SaN, saphenous nerve/nerve complex; ScA, subclavian artery; SCM, sternocleidomastoid muscle; SM, sartorius muscle; TN, tibial nerve; TP, transverse process; UN, ulnar nerve; UT, upper trunk of the brachial plexus.
Nerve highlighting was considered to reduce the risk of nerve injury in 62.9% of cases (302/480; min–max range: 21.2–93.8%), with no change in 30.21% (145/480; 0–72.5%) and an increase in 1.7% (8/480; 0–5.0%). Artery highlighting was considered to reduce the risk of vascular injection in 86.2% (345/400; 70.0–96.25%), with no change in 8.0% (32/400; 1.25–25.0%) and an increase in 1.2% (5/399; 0–2.5%). Pleura highlighting (present in SC and ESP) was considered to reduce the risk of pneumothorax in 76.25% (122/160; 55.0–97.5%), with no change in 13.1% (21/160; 1.25–25.0%), with no reported cases of increased risk. Peritoneum is only visible in the RSB; highlighting was considered to reduce the risk of peritoneum violation in 82.5% (66/80), make no difference in 13.8% (11/80), and increase the risk in 1.2% (1/80).
Highlighting was considered to reduce the risk of block failure in 81.2% (585/720; min–max range: 62.5–97.5%), make no difference in 9.3% (67/720; 0–30.0%), and increase the risk in 1.8% (13/720; 0–3.8%).
Discussion
This study is reported according to the Consolidated Standards of Reporting Trials-Artificial Intelligence guidelines.14 Most prior AI studies of anatomical structure recognition from UGRA images or videos have consisted of data sets from fewer subjects, assessing fewer structures or on fewer videos/images. Of those published, other than this report, only Gungor and colleagues15 assessed a commercially available clinical device with clinically relevant endpoints.
We found that ScanNavTM identified anatomical structures essential to safe and efficacious UGRA on real-time ultrasound in 93.5% of cases. The acquisition and interpretation of optimal ultrasound images are fundamental to the practice of UGRA and are a limiting step for non-experts.3,11 Medical image interpretation is known to be fallible and subjective, even amongst experts.16, 17, 18 Data gathered in this study demonstrate the opportunity to augment human interpretation of ultrasound images during UGRA scanning. The structures highlighted by the AI models closely match those that an international consensus of expert opinion recommends that non-experts identify when performing these procedures.13
Subjective expert opinion was that highlighting would reduce the risk of recognised complications in 62.9–86.2% of scans. The potential for unintentional needle trauma of a safety critical structure is another limiting factor in the practice of UGRA. Despite the known benefits of UGRA, the majority of patients undergoing surgery amenable to UGRA techniques are not offered a PNB.6 Such assistive technology has the potential to reduce complications of UGRA and remove a barrier to clinical practice.
Highlighting by ScanNav in this study was perceived to reduce block failure in 81.2% of scans (according to subjective expert opinion). Ultrasound guidance is associated with improved success rates of PNB, faster onset of sensory block, and reduced incidence of vascular injury and local anaesthetic systemic toxicity.2,19 However, there is still a failure rate to each technique, and the downturn in elective operations conducted during the recent pandemic has led to a commonly held concern over a lack of opportunities to acquire the necessary skills. Medical societies are attempting to promote widespread adoption and standardisation of UGRA.6,13,20,21 To support the implementation of these aims, innovation is needed to support clinicians in the delivery of safe and efficacious UGRA.
We show that ScanNavTM holds potential to support ultrasound scanning in UGRA and mitigate the risk of complications or block failure. The device has gained regulatory approval for clinical use in Europe (April 2021), and data from this study contribute to evidence submitted for regulatory review in the USA. This and other similar devices could in time support the widespread practice by non-experts or even novices for ultrasound-guided procedures throughout medicine. For example, emergency-department physicians are often familiar with point-of-care ultrasound and interventional procedures,22 and such assistive technology may aid the practice of UGRA in this setting. Its use for painful interventions currently carried out under sedation obviates the risk of airway compromise, reduces the burden of monitoring, and provides a prolonged pain-free period to facilitate hospital discharge or act as a bridge to definitive treatment (e.g. for hip fractures). Beyond UGRA, use of AI in image interpretation has broader implications across medicine and potentially all of ultrasonography,23 from screening for developmental dysplasia of the hip24 to diagnosis of breast cancer.25 The democratisation of ultrasonography will help ensure that patients have access to the most appropriate interventions, supporting the performance of ultrasound-based interventions by non-experts whilst maintaining relevant clinical standards.26
The authors recognise limitations to this study. Firstly, our findings must be followed by clinical studies to determine if the predicted benefits are realised in patient outcomes. In particular, use of ultrasound itself has not been shown to reduce the incidence of nerve injury or postoperative neurological symptoms.2 Assessing the impact of any ultrasound augmentation technology will require rigorous evaluation. Secondly, the remote expert panels reviewing the videos and highlighting were not present when the subject was scanned. Contemporaneous viewing and interpretation of the ultrasound image provide a richer source of information for the operator, and the expert-panel assessments may have been different with this additional knowledge. However, this limitation is attenuated by the fact that three remote experts assessed each video and could play/pause/review them at any point, changing their assessment if required. Multiple practitioners and the luxury of time or changing clinical opinion are often not afforded to physicians in clinical practice. Thirdly, this study is a subjective assessment of the device according to expert opinion. This is particularly true for findings relating to efficacy and safety. Additional studies are in progress to conduct an objective and pixel-by-pixel assessment of AI highlighting accuracy for structure boundaries (compared with expert interpretation). Whilst this will be useful, it should be noted that such assessments may not always correlate with clinical usefulness, and there is a need for measures of performance beyond accuracy.27 The current assessment has been chosen to be consistent with requirements for reporting device performance for regulatory approval published by the US Food and Drug Administration,28 which recommends that definitions (e.g. accuracy and FPr/FNr) should be consistent with the intended use of the device. However, it should be noted that there are multiple methods of reporting accuracy of medical devices or tests.29 Finally, multiple investigators in this study have been involved with the development and regulatory evaluation of this device. The authors hope that, as the technology becomes more widely available, more anaesthetists will engage in detailed study of this and similar devices to determine their true value to our clinical practice.
Whilst further clinical data on patient outcomes are required to confirm the predicted benefits, these data present the case for the accuracy of ScanNavTM and the potential safety and efficacy benefits in UGRA. This study marks a shift in ultrasonography-guided regional anaesthesia, where technological progress is not restricted to image generation but also to image interpretation.
Authors' contributions
Study concept/design: JSB, DB-SL, SM, AV, NS
Participant recruitment: JSB, NH, CL, SM, EM, AP, MR, NS, AT, AV, GW
Data collection: JSB, NH, CL, SM, EM, AP, MR, NS, AT, AV, GW
Article preparation: all authors
Article editing: all authors
Funding
Intelligent Ultrasound Limited (Cardiff, UK) via a grant to JSB administered by the University of Oxford (R70327/CN002).
Declarations of interest
JSB is a senior clinical advisor for Intelligent Ultrasound, receiving research funding and honoraria. DB-SL is a clinical advisor for Intelligent Ultrasound, receiving honoraria. PAK has acted as a consultant for DeepMind, Roche, Novartis, Apellis, and Bitfount, and he is an equity owner in Big Picture Medical. He has received speaker fees from Heidelberg Engineering, Topcon, Allergan, and Bayer. PAK is supported by a Moorfields Eye Charity Career Development Award (R190028A) and a UK Research and Innovation Future Leaders Fellowship (MR/T019050/1). CL and EM are members of the Executive Board of the European Society of Regional Anaesthesia & Pain Therapy. AP declares honoraria from GE Healthcare, Butterfly Network, Sintetica UK Ltd, and Pacira, and he is the immediate past president of Regional Anaesthesia UK. MR is on the Board of Directors of the American Society of Regional Anesthesia and Pain Medicine. NS is the chief technical officer of Intelligent Ultrasound. AT has received honoraria from Intelligent Ultrasound. JAN is a senior scientific advisor for Intelligent Ultrasound.
Handling editor: Hugh C Hemmings Jr
Footnotes
Data from this study have been included in medical device regulatory approval submissions in the USA.
Supplementary data to this article can be found online at https://doi.org/10.1016/j.bja.2022.06.031.
Appendix A. Supplementary data
The following are the Supplementary data to this article:
References
- 1.Ting P.L., Sivagnanaratnam V. Ultrasonographic study of the spread of local anaesthetic during axillary brachial plexus block. Br J Anaesth. 1989;63:326–329. doi: 10.1093/bja/63.3.326. [DOI] [PubMed] [Google Scholar]
- 2.Neal J.M., Brull R., Horn J.L., et al. The second American Society of Regional Anesthesia and Pain Medicine evidence-based medicine assessment of ultrasound-guided regional anesthesia: executive summary. Reg Anesth Pain Med. 2016;41:181–194. doi: 10.1097/AAP.0000000000000331. [DOI] [PubMed] [Google Scholar]
- 3.Bowness J., Taylor A. Ultrasound-guided regional anaesthesia: visualising the nerve and needle. Adv Exp Med Biol. 2020;1235:19–34. doi: 10.1007/978-3-030-37639-0_2. [DOI] [PubMed] [Google Scholar]
- 4.Hutton M., Brull R., Macfarlane A.J.R. Regional anaesthesia and outcomes. BJA Educ. 2018;18:52–56. doi: 10.1016/j.bjae.2017.10.002. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 5.Aitken E., Jackson A., Kearns R., et al. Effect of regional versus local anaesthesia on outcome after arteriovenous fistula creation: a randomised controlled trial. Lancet. 2016;388:1067–1074. doi: 10.1016/S0140-6736(16)30948-5. [DOI] [PubMed] [Google Scholar]
- 6.Turbitt L.R., Mariano E.R., El-Boghdadly K. Future directions in regional anaesthesia: not just for the cognoscenti. Anaesthesia. 2020;75:293–297. doi: 10.1111/anae.14768. [DOI] [PubMed] [Google Scholar]
- 7.Sites B.D., Chan V.W., Neal J.M., et al. The American society of regional anesthesia and pain medicine and the European society of regional anaesthesia and pain Therapy joint committee recommendations for education and training in ultrasound-guided regional anesthesia. Reg Anesth Pain Med. 2009;34:40–46. doi: 10.1097/AAP.0b013e3181926779. [DOI] [PubMed] [Google Scholar]
- 8.Bowness J., El-Boghdadly K., Burckett-St Laurent D. Artificial intelligence for image interpretation in ultrasound-guided regional anaesthesia. Anaesthesia. 2021;76:602–607. doi: 10.1111/anae.15212. [DOI] [PubMed] [Google Scholar]
- 9.Bowness J.S., El-Boghdadly K., Woodworth G., Noble J.A., Higham H., Burckett-St Laurent D. Exploring the utility of assistive artificial intelligence for ultrasound scanning in regional anesthesia. Reg Anesth Pain Med. 2022;47:375–379. doi: 10.1136/rapm-2021-103368. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 10.Ronneberger O., Fischer P., Brox T. 2015. U-Net: convolutional neural networks for biomedical image segmentation. arXiv 2015, 1505.04597. [Google Scholar]
- 11.Bowness J., Macfarlane A.J.R., Noble J.A., Higham H.A., Burckett-St Laurent D. Anaesthesia, nerve blocks and artificial intelligence. Anaesth News. 2021;408:4–6. [Google Scholar]
- 12.Bowness J., Varsou O., Turbitt L., Burkett-St Laurent D. Identifying anatomical structures on ultrasound: assistive artificial intelligence in ultrasound-guided regional anesthesia. Clin Anat. 2021;34:802–809. doi: 10.1002/ca.23742. [DOI] [PubMed] [Google Scholar]
- 13.Bowness J.S., Pawa A., Turbitt L., et al. International consensus on anatomical structures to identify on ultrasound for the performance of basic blocks in ultrasound-guided regional anesthesia. Reg Anesth Pain Med. 2022;47:106–112. doi: 10.1136/rapm-2021-103004. [DOI] [PubMed] [Google Scholar]
- 14.Liu X., Cruz Rivera S., Moher D., et al. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Lancet Digit Health. 2020;2:e537–e548. doi: 10.1016/S2589-7500(20)30218-1. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 15.Gungor I., Gunaydin B., Oktar S.O., et al. A real-time anatomy identification via tool based on artificial intelligence for ultrasound-guided peripheral nerve block procedures: an accuracy study. J Anesth. 2021;35:591–594. doi: 10.1007/s00540-021-02947-3. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 16.Williams L., Carrigan A., Auffermann W., et al. The invisible breast cancer: experience does not protect against inattentional blindness to clinically relevant findings in radiology. Psychon Bull Rev. 2021;28:503–511. doi: 10.3758/s13423-020-01826-4. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 17.Drew T., Vo M.L., Wolfe J.M. The invisible gorilla strikes again: sustained inattentional blindness in expert observers. Psychol Sci. 2013;24:1848–1853. doi: 10.1177/0956797613479386. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 18.Bowness J., Turnbull K., Taylor A., et al. Identifying variant anatomy during ultrasound-guided regional anaesthesia: opportunities for clinical improvement. Br J Anaesth. 2019;122:e75–e77. doi: 10.1016/j.bja.2019.02.003. [DOI] [PubMed] [Google Scholar]
- 19.Munirama S., McLeod G. A systematic review and meta-analysis of ultrasound versus electrical stimulation for peripheral nerve location and blockade. Anaesthesia. 2015;70:1084–1091. doi: 10.1111/anae.13098. [DOI] [PubMed] [Google Scholar]
- 20.El-Boghdadly K., Wolmarans M., Stengel A.D., et al. Standardizing nomenclature in regional anesthesia: an ASRA-ESRA Delphi consensus study of abdominal wall, paraspinal, and chest wall blocks. Reg Anesth Pain Med. 2021;46:571–580. doi: 10.1136/rapm-2020-102451. [DOI] [PubMed] [Google Scholar]
- 21.Royal College of Anaesthetists . 2021. Curriculum structure and learning syllabus 2021.https://rcoa.ac.uk/training-careers/training-anaesthesia/2021-anaesthetics-curriculum/2021-curriculum-structure Available from: accessed. [Google Scholar]
- 22.Ultrasound guidelines: emergency, point-of-care and clinical ultrasound guidelines in medicine. Ann Emerg Med. 2017;69:e27–e54. doi: 10.1016/j.annemergmed.2016.08.457. [DOI] [PubMed] [Google Scholar]
- 23.Diaz-Gomez J.L., Mayo P.H., Koenig S.J. Point-of-care ultrasonography. N Engl J Med. 2021;385:1593–1602. doi: 10.1056/NEJMra1916062. [DOI] [PubMed] [Google Scholar]
- 24.Hareendranathan A.R., Chahal B., Ghasseminia S., Zonoobi D., Jaremko J.L. Impact of scan quality on AI assessment of hip dysplasia ultrasound. J Ultrasound. 2022;25:145–153. doi: 10.1007/s40477-021-00560-4. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 25.Le E.P.V., Wang Y., Huang Y., Hickman S., Gilbert F.J. Artificial intelligence in breast imaging. Clin Radiol. 2019;74:357–366. doi: 10.1016/j.crad.2019.02.006. [DOI] [PubMed] [Google Scholar]
- 26.Kainz B., Heinrich M.P., Makropoulos A., et al. Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning. NPJ Digit Med. 2021;4:137. doi: 10.1038/s41746-021-00503-7. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 27.Qin Z.Z., Ahmed S., Sarker M.S., et al. Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms. Lancet Digit Health. 2021;3:e543–e554. doi: 10.1016/S2589-7500(21)00116-3. [DOI] [PubMed] [Google Scholar]
- 28.US Food and Drug Administration. Computer-assisted detection devices applied to radiology images and radiology device data—premarket notification [510(k)] submissions 2012. Available from: https://www.fda.gov/media/77635/download (accessed 18 May 2022).
- 29.Germanson T. Screening for HIV: can we afford the confusion of the false positive rate? J Clin Epidemiol. 1989;42:1235–1237. doi: 10.1016/0895-4356(89)90122-4. [DOI] [PubMed] [Google Scholar]
Associated Data
This section collects any data citations, data availability statements, or supplementary materials included in this article.