1
|
Artificial Intelligence: Innovation to Assist in the Identification of Sono-anatomy for Ultrasound-Guided Regional Anaesthesia. ADVANCES IN EXPERIMENTAL MEDICINE AND BIOLOGY 2022; 1356:117-140. [PMID: 35146620 DOI: 10.1007/978-3-030-87779-8_6] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/09/2022]
Abstract
Ultrasound-guided regional anaesthesia (UGRA) involves the targeted deposition of local anaesthesia to inhibit the function of peripheral nerves. Ultrasound allows the visualisation of nerves and the surrounding structures, to guide needle insertion to a perineural or fascial plane end point for injection. However, it is challenging to develop the necessary skills to acquire and interpret optimal ultrasound images. Sound anatomical knowledge is required and human image analysis is fallible, limited by heuristic behaviours and fatigue, while its subjectivity leads to varied interpretation even amongst experts. Therefore, to maximise the potential benefit of ultrasound guidance, innovation in sono-anatomical identification is required.Artificial intelligence (AI) is rapidly infiltrating many aspects of everyday life. Advances related to medicine have been slower, in part because of the regulatory approval process needing to thoroughly evaluate the risk-benefit ratio of new devices. One area of AI to show significant promise is computer vision (a branch of AI dealing with how computers interpret the visual world), which is particularly relevant to medical image interpretation. AI includes the subfields of machine learning and deep learning, techniques used to interpret or label images. Deep learning systems may hold potential to support ultrasound image interpretation in UGRA but must be trained and validated on data prior to clinical use.Review of the current UGRA literature compares the success and generalisability of deep learning and non-deep learning approaches to image segmentation and explains how computers are able to track structures such as nerves through image frames. We conclude this review with a case study from industry (ScanNav Anatomy Peripheral Nerve Block; Intelligent Ultrasound Limited). This includes a more detailed discussion of the AI approach involved in this system and reviews current evidence of the system performance.The authors discuss how this technology may be best used to assist anaesthetists and what effects this may have on the future of learning and practice of UGRA. Finally, we discuss possible avenues for AI within UGRA and the associated implications.
Collapse
|
2
|
Sztain JF, Finneran JJ, Monahan AM, Khatibi B, Nguyen PL, Madison SJ, Bellars RH, Gabriel RA, Ahmed SS, Schwartz AK, Kent WT, Donohue MC, Padwal JA, Ilfeld BM. Continuous Popliteal-Sciatic Blocks for Postoperative Analgesia: Traditional Proximal Catheter Insertion Superficial to the Paraneural Sheath Versus a New Distal Insertion Site Deep to the Paraneural Sheath. Anesth Analg 2019; 128:e104-e108. [PMID: 31094804 DOI: 10.1213/ane.0000000000003693] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Abstract
We tested the hypothesis that during a continuous popliteal-sciatic nerve block, postoperative analgesia is improved with the catheter insertion point "deep" to the paraneural sheath immediately distal to the bifurcation between the tibial and common peroneal branches, compared with the traditional approach "superficial" to the paraneural sheath proximal to the bifurcation. The needle tip location was determined to be accurately located with a fluid bolus visualized with ultrasound; however, catheters were subsequently inserted without a similar fluid injection and visualization protocol (visualized air injection was permitted and usually implemented, but not required per protocol). The average pain (0-10 scale) the morning after surgery for subjects with a catheter inserted at the proximal subparaneural location (n = 31) was a median (interquartile) of 1.5 (0.0-3.5) vs 1.5 (0.0-4.0) for subjects with a catheter inserted at the distal supraparaneural location (n = 32; P = .927). Secondary outcomes were similarly negative.
Collapse
Affiliation(s)
- Jacklynn F Sztain
- From the Department of Anesthesiology, University of California, San Diego, California
| | - John J Finneran
- From the Department of Anesthesiology, University of California, San Diego, California
- OUTCOMES RESEARCH Consortium, Cleveland, Ohio
| | - Amanda M Monahan
- Department of Anesthesiology, University of Pittsburgh, Pittsburgh, Pennsylvania
| | - Bahareh Khatibi
- From the Department of Anesthesiology, University of California, San Diego, California
| | - Patrick L Nguyen
- From the Department of Anesthesiology, University of California, San Diego, California
| | - Sarah J Madison
- Department of Anesthesiology, Stanford University, Stanford, California
| | - Richard H Bellars
- From the Department of Anesthesiology, University of California, San Diego, California
| | - Rodney A Gabriel
- From the Department of Anesthesiology, University of California, San Diego, California
- OUTCOMES RESEARCH Consortium, Cleveland, Ohio
| | - Sonya S Ahmed
- Department of Orthopedics, University of California, San Diego, California
| | | | - William T Kent
- Department of Orthopedics, University of California, San Diego, California
| | - Michael C Donohue
- Department of Neurology, University of Southern California, Los Angeles, California
| | - Jennifer A Padwal
- School of Medicine, University of California, San Diego, San Diego, California
| | - Brian M Ilfeld
- From the Department of Anesthesiology, University of California, San Diego, California
- OUTCOMES RESEARCH Consortium, Cleveland, Ohio
| |
Collapse
|
3
|
Extrafasicular and Intraperineural, but No Endoneural, Spread after Deliberate Intraneural Injections in a Cadaveric Study. Anesthesiology 2019; 130:1007-1016. [DOI: 10.1097/aln.0000000000002647] [Citation(s) in RCA: 17] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
Abstract
Editor’s Perspective
What We Already Know about This Topic
What This Article Tells Us That Is New
Background
There is confusion regarding the spread of intraneurally injected local anesthetic agents during regional anesthesia. The aim of this research was to deliberately inject a marker that does not leave the neural compartment into which it is injected, and then to study the longitudinal and circumferential spread and possible pathways of intraneural spread.
Methods
After institutional review board approval, we intraneurally injected 20 and 5 ml of heparinized blood solution under ultrasound guidance into 12 sciatic nerves in the popliteal fossa and 10 median nerves, respectively, of eight fresh, unembalmed cadavers using standard 22-gauge “D” needles, mimicking the blocks in clinical conditions. Ultrasound evidence of nerve swelling confirmed intraneural injection. Samples of the nerves were then examined under light and scanning electron microscopy.
Results
Extrafascicular spread was observed in all the adipocyte-containing neural compartments of the 664 cross-section samples we examined, but intrafascicular spread was seen in only 6 cross-sections of two nerves. None of the epineurium, perineurium, or neural components were disrupted in any of the samples. Spread between the layers of the perineurium was a route of spread that included the perineurium surrounding the fascicles and the perineurium that formed incomplete septa in the fascicles. Similar to the endoneurium proper, subepineural compartments that did not contain any fat cells did not reveal any spread of heparinized blood solution cells. No “perineural” spaces were observed within the endoneurium. We also did not observe any true intrafascicular spread.
Conclusions
After deliberate intraneural injection, longitudinal and circumferential extrafascicular spread occurred in all instances in the neural compartments that contained adipocytes, but not in the relatively solid endoneurium of the fascicles.
Collapse
|
5
|
Safety and Subepineural Injections. Reg Anesth Pain Med 2017; 42:126-127. [DOI: 10.1097/aap.0000000000000536] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
6
|
Affiliation(s)
- Paul E Bigeleisen
- Department of Anesthesiology, University of Maryland School of Medicine, Baltimore, MD
| |
Collapse
|