Yeh Cheng-Liang, Wu Chueh-Hung, Hsiao Ming-Yen, Kuo Po-Ling
Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan.
Department of Physical Medicine and Rehabilitation, National Taiwan University Hospital, Taipei, Taiwan; College of Medicine, National Taiwan University, Taipei, Taiwan.
Ultrasound Med Biol. 2023 May;49(5):1129-1136. doi: 10.1016/j.ultrasmedbio.2022.12.014. Epub 2023 Feb 3.
The morphological dynamics of the median nerve across the level extracted from dynamic ultrasonography are valuable for the diagnosis and evaluation of carpal tunnel syndrome (CTS), but the data extraction requires tremendous labor to manually segment the nerve across the image sequence. Our aim was to provide visually real-time, automated median nerve segmentation and subsequent data extraction in dynamic ultrasonography.
We proposed a deep-learning model modified from SOLOv2 and tailored for median nerve segmentation. Ensemble strategies combining several state-of-the-art models were also employed to examine whether the segmentation accuracy could be improved. Image data were acquired from nine normal participants and 59 patients with idiopathic CTS.
Our model outperformed several state-of-the-art models with respect to inference speed, whereas the segmentation accuracy was on a par with that achieved by these models. When evaluated on a single 1080Ti GPU card, our model achieved an intersection over union score of 0.855 and Dice coefficient of 0.922 at 28.9 frames/s. The ensemble models slightly improved segmentation accuracy.
Our model has great potential for use in the clinical setting, as the real-time, automated extraction of the morphological dynamics of the median nerve allows clinicians to diagnose and treat CTS as the images are acquired.
动态超声检查中提取的正中神经在不同层面的形态动力学对腕管综合征（CTS）的诊断和评估具有重要价值，但数据提取需要耗费大量人力手动在图像序列中分割神经。我们的目的是在动态超声检查中提供视觉上实时的、自动化的正中神经分割及后续数据提取。
我们提出了一种基于SOLOv2修改并专门用于正中神经分割的深度学习模型。还采用了结合几种先进模型的集成策略来检验分割准确性是否能得到提高。图像数据取自9名正常参与者和59名特发性CTS患者。
我们的模型在推理速度方面优于几种先进模型，而分割准确性与这些模型相当。在单张1080Ti GPU卡上进行评估时，我们的模型在28.9帧/秒的速度下实现了交并比分数为0.855，骰子系数为0.922。集成模型略微提高了分割准确性。
我们的模型在临床应用中有很大潜力，因为正中神经形态动力学的实时、自动提取使临床医生能够在获取图像时对CTS进行诊断和治疗。
