深度学习自动分割动态锁骨上超声中的肩胛上神经及邻近结构
本研究纳入42名健康成人的80段动态锁骨上超声视频,人工标注肩胛上神经、臂丛、锁骨下动脉和肩胛舌骨肌,开发并评估了基于Double U-Net的多类分割方法。结果显示,Double U-Net在全部标注结构上均优于基线U-Net,肩胛上神经平均Dice系数从0.51±0.19提升至0.68±0.11(p=0.03)。研究表明该方法可实现肩胛上神经及周围结构的可靠多类分割,有潜力用于肩胛上神经病变的临床场景。
要点
- 肩胛上神经在超声上细小、对比度低且与周围结构回声相似,自动分割可帮助定位。
- Double U-Net对肩胛上神经的分割稳定性优于基线U-Net,Dice提升至0.68。
- 动态超声视频中同时标注四个结构进行多结构监督,可获得最优分割表现。
核心结论
- Double U-Net在动态锁骨上超声中可对肩胛上神经及邻近结构实现可靠多类分割,性能显著优于基线U-Net。
- 预训练VGG-19编码器获得的Dice评分高于其他编码器,但差异无统计学意义(p=0.12)。
- 两阶段结构的贡献互补,第二阶段添加未改善到具有统计学意义的程度(p=0.52)。
研究设计与样本
- 前瞻性收集42名健康成人的80段动态锁骨上超声视频作为研究样本。
- 采用Double U-Net架构,第一阶段使用VGG-19预训练编码器,第二阶段使用随机初始化编码器,并加入Atrous Spatial Pyramid Pooling与Squeeze-and-Excitation模块。
- 在独立测试集上以Dice相似系数评估分割性能。
- 通过消融实验比较编码器选择、架构设计、标注策略、损失函数和输出权重的影响。
关键影像表现/征象
- 标注及分割目标为肩胛上神经、臂丛、锁骨下动脉和肩胛舌骨肌四个超声可见结构。
- 肩胛上神经因尺寸小、对比度低且邻近回声纹理相似的结构,在超声上识别困难。
诊断标准与关键数值
- 肩胛上神经分割的平均Dice系数由基线U-Net的0.51±0.19提升至Double U-Net的0.68±0.11(p=0.03)。
- 预训练VGG-19编码器的Dice评分高于替代编码器,但无统计学意义(p=0.12)。
- 同时标注全部四个结构时获得最优性能,Dice系数为0.68±0.11。
- Focal loss获得最高平均Dice评分。
- 强调最终输出并限制中间监督(α:β = 0.1:0.9)时获得最优性能。
临床应用与阅片要点
- 该自动分割方法有潜力辅助锁骨上超声中肩胛上神经的定位,用于肩胛上神经病变相关评估。
- 多结构同时分割可提供肩胛上神经与臂丛、锁骨下动脉、肩胛舌骨肌的相对位置信息,帮助阅片解剖定位。
- 动态超声视频中的分割稳定性优于静态单帧,提示临床应用时可依托动态扫查序列。
局限性
- 研究对象为42名健康成人,未包含肩胛上神经病变患者,其病理状态下的泛化能力尚不明确。
- 样本量为80段动态超声视频,数据规模有限。
- 仅来自单一研究设置,未说明多中心采集。
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: The suprascapular nerve (SSN) provides major motor and sensory innervation to the shoulder. Its accurate identification on ultrasound is challenging because of its small size, low contrast and proximity to structures with similar echotexture. This study aimed to develop and evaluate a deep learning-based approach for multi-class segmentation of the SSN and adjacent structures in dynamic supraclavicular ultrasound.
METHODS: Dynamic ultrasound videos (n = 80) from 42 healthy adults were manually annotated for the SSN, brachial plexus, subclavian artery and omohyoid muscle. A Double U-Net architecture was implemented, incorporating a VGG-19 pre-trained encoder in the first stage and a randomly initialized encoder in the second stage, together with Atrous Spatial Pyramid Pooling and Squeeze-and-Excitation blocks. Ablation experiments examined the effects of encoder choice, architectural design, annotation strategy, loss function and output weighting. Segmentation performance was evaluated using Dice similarity coefficients on an independent test set.
RESULTS: The Double U-Net significantly outperformed the baseline U-Net across all annotated structures. For SSN segmentation, the mean Dice coefficient improved from 0.51 ± 0.19 to 0.68 ± 0.11 (p = 0.03), with greater stability across test videos. A pre-trained VGG-19 encoder showed higher Dice scores than alternative encoders, without statistical significance (p = 0.12). Ablation analyses confirmed complementary contributions of both stages (p = 0.52). Multi-structure supervision yielded modest benefit, with optimal performance when all four structures were annotated (Dice 0.68 ± 0.11). Focal loss achieved the highest average Dice score, and optimal performance was obtained by emphasizing the final output with limited intermediate supervision (α:β = 0.1:0.9).
CONCLUSION: The proposed Double U-Net enables reliable multi-class segmentation of the SSN and surrounding structures in dynamic supraclavicular ultrasound, supporting its potential clinical application in suprascapular neuropathy.
引用
- Shu, Chang, Chung, et al. Deep Learning-Based Automated Segmentation of the Suprascapular Nerve and Adjacent Structures in Dynamic Supraclavicular Ultrasound. Ultrasound Med Biol. 2026. PMID: 42637642. doi:10.1016/j.ultrasmedbio.2026.07.027
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。