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

Bowness, James S.; Metcalfe, David; El-Boghdadly, Kariem; Thurley, Neal; Morecroft, Megan; Hartley, Thomas; Krawczyk, Joanna; Noble, J. Alison; Higham, Helen

doi:10.1016/j.bja.2024.01.036

Cited by 6 publications

(1 citation statement)

References 101 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous studies have explored the automated detection and segmentation of nerve tissues from ultrasound images [ 3 ]. To address noise and variability, Hadjerci et al [ 4 , 5 ] proposed combined approaches involving denoising preprocessing, machine learning, and active contour techniques for nerve segmentation in ultrasound images.…”

Section: Introductionmentioning

confidence: 99%

Investigation of Appropriate Scaling of Networks and Images for Convolutional Neural Network-Based Nerve Detection in Ultrasound-Guided Nerve Blocks

Sugino,

Onogi,

Oishi

et al. 2024

Sensors

View full text Add to dashboard Cite

Ultrasound imaging is an essential tool in anesthesiology, particularly for ultrasound-guided peripheral nerve blocks (US-PNBs). However, challenges such as speckle noise, acoustic shadows, and variability in nerve appearance complicate the accurate localization of nerve tissues. To address this issue, this study introduces a deep convolutional neural network (DCNN), specifically Scaled-YOLOv4, and investigates an appropriate network model and input image scaling for nerve detection on ultrasound images. Utilizing two datasets, a public dataset and an original dataset, we evaluated the effects of model scale and input image size on detection performance. Our findings reveal that smaller input images and larger model scales significantly improve detection accuracy. The optimal configuration of model size and input image size not only achieved high detection accuracy but also demonstrated real-time processing capabilities.

show abstract

Section: Introductionmentioning

confidence: 99%

Investigation of Appropriate Scaling of Networks and Images for Convolutional Neural Network-Based Nerve Detection in Ultrasound-Guided Nerve Blocks

Sugino,

Onogi,

Oishi

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

Celebrating the state of the art and innovations in regional anaesthesia in the British Journal of Anaesthesia

Hewson,

Ferry,

Macfarlane

2024

British Journal of Anaesthesia

View full text Add to dashboard Cite

Optimizing peripheral regional anaesthesia: strategies for single shot and continuous blocks

Johnstone,

Taylor,

Ferry

2024

Current Opinion in Anaesthesiology

View full text Add to dashboard Cite

Purpose of review Regional anaesthesia is increasingly prominent within anaesthesia, offering alternative analgesic options amidst concerns over opioid-based analgesia. Since Halsted's initial description, the field has burgeoned, with ultrasound visualization revolutionizing local anaesthetic spread assessment, leading to the development of numerous novel techniques. The benefits of regional anaesthesia have gained increasing evidence to support their application, leading to changes within training curricula. Consequently, regional anaesthesia is at a defining moment, embracing the development of core skills for the general anaesthesiologist, whilst also continuing the advancement of the specialty. Recent findings Recent priority setting projects have focussed attention on key aspects of regional anaesthesia delivery, including pain management, conduct and efficacy, education, and technological innovation. Developments in our current understanding of anatomy and pharmacology, combined with strategies for optimizing the conduct and maximizing efficacy of techniques, minimizing complications, and enhancing outcomes are explored. In addition, advancements in education and training methodologies and the integration of progress in novel technologies will be reviewed. Summary This review highlights recent scientific advances in optimizing both single-shot and continuous peripheral regional anaesthesia techniques. By synthesizing these developments, this review offers valuable insights into the evolving landscape of regional anaesthesia, aiming to improve clinical practice and patient care.

show abstract

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

Cited by 6 publications

References 101 publications

Investigation of Appropriate Scaling of Networks and Images for Convolutional Neural Network-Based Nerve Detection in Ultrasound-Guided Nerve Blocks

Investigation of Appropriate Scaling of Networks and Images for Convolutional Neural Network-Based Nerve Detection in Ultrasound-Guided Nerve Blocks

Celebrating the state of the art and innovations in regional anaesthesia in the British Journal of Anaesthesia

Optimizing peripheral regional anaesthesia: strategies for single shot and continuous blocks

Contact Info

Product

Resources

About