文献速递神经技术与安全US

基于深度学习的经颅多普勒超声大脑中动脉自动检测

Deep Learning-Based Automated Detection of the Middle Cerebral Artery in Transcranial Doppler Ultrasound Examinations.
PubMed 文献 · Ultrasound Med Biol · 2025-06-29

本研究收集41名受试者(31名神经健康者、10名卒中患者)的365段经颅多普勒彩色多普勒视频共61,611帧,由临床专家标注大脑中动脉边界框,比较YOLOv10与RT-DETR两种目标检测模型的自动检测性能。两种模型帧水平F1均为0.884,YOLOv10实例级定位AP为0.817优于RT-DETR的0.780,桌面CPU推理速度11.6 ms快于91.14 ms,平板设备平均每帧36 ms。结论认为实时自动检测大脑中动脉可行且可部署于移动平台。

要点

  • YOLOv10与RT-DETR帧水平检测大脑中动脉存在的F1均为0.884,实例级定位YOLOv10更优。
  • YOLOv10桌面CPU推理11.6 ms、平板每帧36 ms,具备实时移动部署潜力。
  • 模型与读者间个体等效系数IEC为-1.08,提示AI预测与读者偏差小于读者间偏差。

核心结论

  • 实时自动检测大脑中动脉是可行的,并可部署于移动平台,可能使受训较少的操作者在床旁场景中更广泛地应用。

研究设计与样本

  • 研究为方法学开发与验证研究,采用YOLOv10与RT-DETR两种目标检测模型进行实时大脑中动脉自动检测。
  • 数据来自41名受试者(神经健康者31名、卒中患者10名)的365段经颅多普勒彩色多普勒视频,共61,611帧,全部帧由临床专家标注大脑中动脉边界框。
  • 模型训练先利用大型腹部超声数据集预训练,再在采集的经颅多普勒数据上微调。
  • 采用四折交叉验证评估实例级与帧级检测性能及推理速度,并以边界框间距离和个体等效系数(IEC)评估模型与两名人类专家读者间的一致性。

诊断标准与关键数值

  • YOLOv10帧水平检测大脑中动脉存在的F1为0.884±0.023,RT-DETR为0.884±0.019。
  • YOLOv10实例级定位平均精度AP为0.817,RT-DETR为0.780。
  • YOLOv10在桌面CPU上推理速度为11.6 ms,RT-DETR为91.14 ms;YOLOv10在平板设备上平均每帧推理时间为36 ms。
  • 个体等效系数IEC为-1.08(95%CI:-1.45至-0.19),提示AI预测与各读者间的偏差小于读者彼此标注间的偏差。

临床应用与阅片要点

  • 作者认为实时自动检测大脑中动脉可行且可部署于移动平台,可能使受训较少的操作者在床旁场景中更广泛地应用。

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: Transcranial Doppler (TCD) ultrasound has significant clinical value for assessing cerebral hemodynamics, but its reliance on operator expertise limits broader clinical adoption. In this work, we present a lightweight real-time deep learning-based approach capable of automatically identifying the middle cerebral artery (MCA) in TCD Color Doppler images.

METHODS: Two state-of-the-art object detection models, YOLOv10 and Real-Time Detection Transformers (RT-DETR), were investigated for automated MCA detection in real-time. TCD Color Doppler data (41 subjects; 365 videos; 61,611 frames) were collected from neurologically healthy individuals (n = 31) and stroke patients (n = 10). MCA bounding box annotations were performed by clinical experts on all frames. Model training consisted of pretraining utilizing a large abdominal ultrasound dataset followed by subsequent fine-tuning on acquired TCD data. Detection performance at the instance and frame levels, and inference speed were assessed through four-fold cross-validation. Inter-rater agreement between model and two human expert readers was assessed using distance between bounding boxes and inter-rater variability was quantified using the individual equivalence coefficient (IEC) metric.

RESULTS: Both YOLOv10 and RT-DETR models showed comparable frame level accuracy for MCA presence, with F1 scores of 0.884 ± 0.023 and 0.884 ± 0.019 respectively. YOLOv10 outperformed RT-DETR for instance-level localization accuracy (AP: 0.817 vs. 0.780) and had considerably faster inference speed on a desktop CPU (11.6 ms vs. 91.14 ms). Furthermore, YOLOv10 showed an average inference time of 36 ms per frame on a tablet device. The IEC was -1.08 with 95 % confidence interval: [-1.45, -0.19], showing that the AI predictions deviated less from each reader than the readers' annotations deviated from each other.

CONCLUSION: Real-time automated detection of the MCA is feasible and can be implemented on mobile platforms, potentially enabling wider clinical adoption by less-trained operators in point-of-care settings.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Lee H, Shi W, Mukaddim RA, et al. Deep Learning-Based Automated Detection of the Middle Cerebral Artery in Transcranial Doppler Ultrasound Examinations. Ultrasound Med Biol. 2025. PMID: 40582894. doi:10.1016/j.ultrasmedbio.2025.05.028

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。