从共识到标准化:评估深度学习在超声图像神经阻滞分割中的表现
本研究从公开来源收集3594张原始超声图像,覆盖9个神经阻滞区域,另纳入908张阴性图像,采用10种卷积神经网络架构进行神经结构识别。R2U-Net模型获得最高平均Dice评分0.7619,优于其他模型(0.7123-0.7619);仅在腹横肌平面神经区域观察到模型性能的统计学显著差异(χ²=26.4,df=9,P=.002,ε²=0.267)。10名医学专家评估认为模型预测准确性高,尤其在腘窝神经区域,专家同意基于全部100个模型生成预测进行穿刺。
要点
- R2U-Net在9个神经阻滞区域的平均Dice评分为0.7619,为10种模型中最高。
- 仅腹横肌平面神经区域模型间性能差异有统计学意义(χ²=26.4,df=9,P=.002,ε²=0.267)。
- 腘窝神经区域专家对全部100个模型预测均同意进行穿刺。
核心结论
- 深度学习模型如R2U-Net在超声引导神经阻滞中可提供一致的分割结果。
研究设计与样本
- 从公开GitHub仓库和YouTube视频收集3594张原始超声图像,覆盖9个神经阻滞区域(腹横肌平面、股神经、后直肌鞘、正中神经和尺神经、胸肌平面、坐骨神经、锁骨下臂丛、锁骨上臂丛、肌间沟臂丛)。每个神经区域保留10张图像用于测试,由10名麻醉科专家标注;其余3504张由一名麻醉科住院医师标注并增强,每个神经区域生成25000张训练图像。另纳入908张不含目标神经结构的阴性超声图像。选用10种基于卷积神经网络的深度学习架构,采用5折交叉验证在EVGA GeForce RTX 3090 GPU上训练,调整批次大小、轮数和Adam优化器。训练后每个神经区域用10张图像以Dice评分(范围0-1,1表示完全一致,0表示无重叠)比较模型预测与专家标注。另由10名医学专家评估是否会在模型预测上插入穿刺针,并进行统计学分析探索Dice评分与专家回答的关系。
诊断标准与关键数值
- R2U-Net模型在所有神经区域的平均Dice评分为0.7619,其他模型为0.7123-0.7619。
- 模型性能仅在腹横肌平面神经区域差异有统计学意义(χ²=26.4,df=9,P=.002,ε²=0.267)。
- 腘窝神经区域专家对全部100个模型生成预测均同意插入穿刺针。
- 逻辑回归模型提示,在锁骨上区域,较高的Dice重叠可能增加专家接受的概率(OR=8.59×10⁴,95%CI 0.33-2.25×10¹⁰;P=.073)。
临床应用与阅片要点
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND: Deep learning can automate nerve identification by learning from expert-labeled examples to detect and highlight nerves in ultrasound images. This study aims to evaluate the performance of deep-learning models in identifying nerves for ultrasound-guided nerve blocks.
METHODS: A total of 3594 raw ultrasound images were collected from public sources-an open GitHub repository and publicly available YouTube videos-covering 9 nerve block regions: Transversus Abdominis Plane (TAP), Femoral Nerve, Posterior Rectus Sheath, Median and Ulnar Nerves, Pectoralis Plane, Sciatic Nerve, Infraclavicular Brachial Plexus, Supraclavicular Brachial Plexus, and Interscalene Brachial Plexus. Of these, 10 images per nerve region were kept for testing, with each image labeled by 10 expert anesthesiologists. The remaining 3504 were labeled by a medical anesthesia resident and augmented to create a diverse training dataset of 25,000 images per nerve region. Additionally, 908 negative ultrasound images, which do not contain the targeted nerve structures, were included to improve model robustness. Ten convolutional neural network-based deep-learning architectures were selected to identify nerve structures. Models were trained using a 5-fold cross-validation approach on an Extended Video Graphics Array (EVGA) GeForce RTX 3090 GPU, with batch size, number of epochs, and the Adam optimizer adjusted to enhance the models' effectiveness. Posttraining, models were evaluated on a set of 10 images per nerve region, using the Dice score (range: 0 to 1, where 1 indicates perfect agreement and 0 indicates no overlap) to compare model predictions with expert-labeled images. Further validation was conducted by 10 medical experts who assessed whether they would insert a needle into the model's predictions. Statistical analyses were performed to explore the relationship between Dice scores and expert responses.
RESULTS: The R2U-Net model achieved the highest average Dice score (0.7619) across all nerve regions, outperforming other models (0.7123-0.7619). However, statistically significant differences in model performance were observed only for the TAP nerve region (χ² = 26.4, df = 9, P = .002, ε² = 0.267). Expert evaluations indicated high accuracy in the model predictions, particularly for the Popliteal nerve region, where experts agreed to insert a needle based on all 100 model-generated predictions. Logistic modeling suggested that higher Dice overlap might increase the odds of expert acceptance in the Supraclavicular region (odds ratio [OR] = 8.59 × 10⁴, 95% confidence interval [CI], 0.33-2.25 × 10¹⁰; P = .073).
CONCLUSIONS: The findings demonstrate the potential of deep-learning models, such as R2U-Net, to deliver consistent segmentation results in ultrasound-guided nerve block procedures.
引用
- Pelletier ED, Jeffries SD, Suissa N, et al. From Consensus to Standardization: Evaluating Deep Learning for Nerve Block Segmentation in Ultrasound Imaging. A A Pract. 2025. PMID: 40844859. doi:10.1213/XAA.0000000000002040
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。