动态感知超声图像活检针识别:时间先验引导的U-Net交叉Transformer
本研究提出UXFormer混合架构,将经典背景减除与U-Net×Vision Transformer融合,用于超声图像中活检针的动态识别。在有限训练数据下,该方法在Jaccard指数、Dice分数、召回率、精确率及针尖位置误差等指标上均优于多个对比方法。结论表明,该框架通过桥接信号处理与深度学习,增强归纳偏置并降低Transformer对大数据的需求。
要点
- 结合背景减除时间先验与U-Net交叉Transformer,提升小样本下针道检测鲁棒性。
- 针尖位置误差改善44.0%,轨迹角度误差改善17.7%,助力穿刺路径评估。
- 在针体可见度变化条件下仍保持性能优势,适合实时超声引导场景。
核心结论
- UXFormer通过融合经典背景减除与U-Net×Vision Transformer,在有限训练数据下实现更可靠的超声活检针检测。
研究设计与样本
- 方法学研究,提出UXFormer混合架构,包含零子空间时间先验提取、时间到空间交叉注意力编码及全局到局部交叉卷积解码三个组件。
- 训练数据量有限,具体样本量、中心数及设备/序列信息原文未报告。
- 参考标准及评估数据集来源原文未报告。
关键影像表现/征象
- 模型利用时间先验信息增强针体与组织背景的区分,在针体可见度变化条件下仍能定位针尖和轨迹。
诊断标准与关键数值
- 与竞争方法相比,Jaccard指数提高14.2%,Dice分数提高9.0%,召回率提高8.5%,精确率提高5.5%。
- 95百分位Hausdorff距离改善63.5%,针尖位置误差改善44.0%,轨迹角度误差改善17.7%。
临床应用与阅片要点
- 可用于超声引导下活检、区域麻醉等穿刺过程的针体自动识别与针尖定位辅助。
- 在训练数据有限时仍具较好性能,适合数据稀缺场景的模型部署。
- 需注意针体可见度变化对检测的影响,模型通过时间先验提升鲁棒性。
局限性
- 原文未明确报告训练数据规模、中心数及外部验证情况。
- 方法依赖背景减除时间先验,对静态或运动模式复杂的场景可能受限。
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 needle placement has been commonly used for minimally invasive clinical procedures, including biopsy, regional anesthesia and localized drug administration. This study aimed to enhance existing deep learning frameworks by incorporating a classical background subtraction, which enriches the inductive bias and thereby enables more reliable needle detection even when the available training dataset is small.
METHODS: Although deep learning methods such as U-Net and its derivatives have substantially advanced needle localization performance, they remain constrained by a limited receptive field that prevents effective modeling of long-range spatial dependencies. Although Vision Transformer overcomes this limitation through self-attention mechanisms, it demands large-scale training data and tends to sacrifice fine-grained spatial locality. To overcome these limitations, we propose U-Net Cross Transformer (UXFormer), a dynamic-aware hybrid architecture that combines classical background subtraction with an integrated U-Net × Vision Transformer fusion framework. The model comprises three key components: (i) null subspace-based extraction of temporal prior information, (ii) a temporal-to-spatial cross-attention module during encoding and (iii) a global-to-local cross-convolutional block attention module during decoding, enabling continuous bidirectional communication between localized temporal dynamics and globally contextualized spatial representations.
RESULTS: Experimental results demonstrate that the proposed method outperforms multiple competing approaches, achieving significant improvements: a 14.2% increase in Jaccard index, a 9.0% increase in Dice score, 8.5% increase in recall, 5.5% increase in precision, and 63.5% increase in the 95th percentile Hausdorff distance, thus leading to a 44.0% improvement in tip position error and a 17.7% improvement in trajectory angle error, even under varying needle visibility conditions.
CONCLUSION: By explicitly bridging classical signal processing and deep learning within a unified framework, this work strengthens inductive bias while substantially reducing the massive data requirements inherent in transformer-based models, yielding superior detection performance across diverse needle-tissue interaction conditions, even when training data are limited in volume.
引用
- Lee M, Beom DG, Bae EH, et al. Dynamic Aware Biopsy Needle Identification in Ultrasound Images Using Temporal Prior Guided U-Net Cross Transformer With Limited Training Data. Ultrasound Med Biol. 2026. PMID: 42486749. doi:10.1016/j.ultrasmedbio.2026.06.024
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。