文献速递技术与安全骨肌US

BPSegSys:基于深度学习的臂丛神经干分割系统

BPSegSys: A Brachial Plexus Nerve Trunk Segmentation System Using Deep Learning.
PubMed 文献 · Ultrasound Med Biol · 2024-01-04

研究建立含320幅臂丛超声图像的公开数据集,由三名经验丰富医生共同制作分割金标准并标注臂丛神经干,设计基于深度学习的臂丛分割系统BPSegSys。在三个数据组中BPSegSys的IoU分别为0.5350、0.4763和0.5043,均超过经验丰富医生的0.5205、0.4704和0.4979,并可将医生识别臂丛神经干的IoU最高提升27%。

要点

  • BPSegSys在三个数据组的IoU均高于经验丰富医生,达到医生级神经识别性能。
  • BPSegSys可辅助医生更准确识别臂丛神经干,IoU最高提升27%。
  • 研究建立了含320幅臂丛超声图像的公开数据集并标注臂丛神经干。

核心结论

  • 研究建立了臂丛神经干识别的数据集并设计BPSegSys识别臂丛神经干,该系统达到医生级识别水平,提高医生识别臂丛神经干的准确性和效率。

研究设计与样本

  • 研究论文;建立含320幅臂丛超声图像的公开数据集,由三名经验丰富医生共同制作臂丛分割金标准并标注臂丛神经干,设计基于深度学习的臂丛分割系统BPSegSys。

诊断标准与关键数值

  • BPSegSys在三个数据组的IoU分别为0.5350、0.4763和0.5043。
  • 经验丰富医生在三个数据组的IoU分别为0.5205、0.4704和0.4979。
  • BPSegSys辅助医生识别臂丛神经干的IoU提升最高达27%。

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

OBJECTIVE: Ultrasound-guided nerve block anesthesia (UGNB) is a high-tech visual nerve block anesthesia method that can be used to observe the target nerve and its surrounding structures, the puncture needle's advancement and local anesthetics spread in real time. The key in UGNB is nerve identification. With the help of deep learning methods, the automatic identification or segmentation of nerves can be realized, assisting doctors in completing nerve block anesthesia accurately and efficiently.

METHODS: We established a public data set containing 320 ultrasound images of brachial plexus (BP). Three experienced doctors jointly produced the BP segmentation ground truth and labeled brachial plexus trunks. We designed a brachial plexus segmentation system (BPSegSys) based on deep learning.

RESULTS: BPSegSys achieves experienced-doctor-level nerve identification performance in various experiments. We evaluated BPSegSys performance in terms of intersection-over-union (IoU). Considering three data set groups in our established public data set, the IoUs of BPSegSys were 0.5350, 0.4763 and 0.5043, respectively, which exceed the IoUs 0.5205, 0.4704 and 0.4979 of experienced doctors. In addition, we determined that BPSegSys can help doctors identify brachial plexus trunks more accurately, with IoU improvement up to 27%, which has significant clinical application value.

CONCLUSION: We establish a data set for brachial plexus trunk identification and designed a BPSegSys to identify the brachial plexus trunks. BPSegSys achieves the doctor-level identification of the brachial plexus trunks and improves the accuracy and efficiency of doctors' identification of the brachial plexus trunks.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Wang Y, Zhu B, Kong L, et al. BPSegSys: A Brachial Plexus Nerve Trunk Segmentation System Using Deep Learning. Ultrasound Med Biol. 2024. PMID: 38176984. doi:10.1016/j.ultrasmedbio.2023.11.009

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。