Bowness James S, Morse Robert, Lewis Owen, Lloyd James, Burckett-St Laurent David, Bellew Boyne, Macfarlane Alan J R, Pawa Amit, Taylor Alasdair, Noble J Alison, Higham Helen
Nuffield Department of Clinical Anaesthesia, University of Oxford, Oxford, UK; Department of Anaesthesia, Aneurin Bevan University Health Board, Newport, UK.
Intelligent Ultrasound, Cardiff, UK.
Br J Anaesth. 2023 Oct 26;132(5):1063-72. doi: 10.1016/j.bja.2023.09.023.
ScanNavAnatomy Peripheral Nerve Block (ScanNav™) is an artificial intelligence (AI)-based device that produces a colour overlay on real-time B-mode ultrasound to highlight key anatomical structures for regional anaesthesia. This study compares consistency of identification of sono-anatomical structures between expert ultrasonographers and ScanNav™.
Nineteen experts in ultrasound-guided regional anaesthesia (UGRA) annotated 100 structures in 30 ultrasound videos across six anatomical regions. These annotations were compared with each other to produce a quantitative assessment of the level of agreement amongst human experts. The AI colour overlay was then compared with all expert annotations. Differences in human-human and human-AI agreement are presented for each structure class (artery, muscle, nerve, fascia/serosal plane) and structure. Clinical context is provided through subjective assessment data from UGRA experts.
For human-human and human-AI annotations, agreement was highest for arteries (mean Dice score 0.88/0.86), then muscles (0.80/0.77), and lowest for nerves (0.48/0.41). Wide discrepancy exists in consistency for different structures, both with human-human and human-AI comparisons; highest for sartorius muscle (0.91/0.92) and lowest for the radial nerve (0.21/0.27).
Human experts and the AI system both showed the same pattern of agreement in sono-anatomical structure identification. The clinical significance of the differences presented must be explored; however the perception that human expert opinion is uniform must be challenged. Elements of this assessment framework could be used for other devices to allow consistent evaluations that inform clinical training and practice. Anaesthetists should be actively engaged in the development and adoption of new AI technology.
ScanNav解剖学周围神经阻滞系统（ScanNav™）是一种基于人工智能（AI）的设备，可在实时B超上生成彩色叠加图，以突出显示用于区域麻醉的关键解剖结构。本研究比较了专业超声检查人员与ScanNav™在识别超声解剖结构方面的一致性。
19名超声引导区域麻醉（UGRA）专家对六个解剖区域的30个超声视频中的100个结构进行了标注。将这些标注相互比较，以对人类专家之间的一致程度进行定量评估。然后将AI彩色叠加图与所有专家的标注进行比较。针对每个结构类别（动脉、肌肉、神经、筋膜/浆膜平面）和结构，呈现了人与人之间以及人与AI之间一致性的差异。通过UGRA专家的主观评估数据提供临床背景。
对于人与人之间以及人与AI之间的标注，动脉的一致性最高（平均Dice分数0.88/0.86），其次是肌肉（0.80/0.77），神经的一致性最低（0.48/0.41）。在人与人之间以及人与AI的比较中，不同结构的一致性存在很大差异；缝匠肌的一致性最高（0.91/0.92），桡神经的一致性最低（0.21/0.27）。
人类专家和AI系统在超声解剖结构识别方面表现出相同的一致模式。必须探讨所呈现差异的临床意义；然而，必须挑战认为人类专家意见一致的观念。该评估框架的要素可用于其他设备，以进行一致的评估，为临床培训和实践提供参考。麻醉医生应积极参与新AI技术的开发和应用。
Zotero 插件