VibNet: Vibration-Boosted Needle Detection in Ultrasound Images
作者: Dianye Huang, Chenyang Li, Angelos Karlas, Xiangyu Chu, K. W. Samuel Au, Nassir Navab, Zhongliang Jiang
分类: eess.IV, cs.CV
发布日期: 2024-03-21 (更新: 2025-02-22)
备注: Accepted by IEEE TMI
🔗 代码/项目: GITHUB
💡 一句话要点
提出VibNet以解决超声图像中针头检测难题
🎯 匹配领域: 支柱八：物理动画 (Physics-based Animation)
关键词: 超声图像 针头检测 机器学习 短时傅里叶变换 霍夫变换 医疗影像 振动增强 鲁棒性
📋 核心要点
- 现有方法在超声图像中针头检测面临斑点干扰和低分辨率等挑战，导致检测准确性不足。
- VibNet通过外部施加周期性振动，结合短时傅里叶变换和霍夫变换，提升了针头检测的鲁棒性和准确性。
- 实验结果显示，VibNet在猪组织样本中实现了1.61±1.56mm的针尖误差，显著优于UNet和WNet的表现。
📝 摘要（中文）
精确的经皮针头检测对于超声引导的介入治疗至关重要。然而，由于超声图像中的斑点、针状伪影和低分辨率等固有限制，针头的检测变得极具挑战性。为了解决这一问题，本文提出了VibNet，一个基于学习的框架，通过对针杆施加周期性振动来增强针头检测的鲁棒性和准确性。VibNet集成了神经短时傅里叶变换和霍夫变换模块，实现了运动特征提取、频率特征聚合和霍夫空间中的针头检测。实验结果表明，VibNet在可见性严重降低的情况下仍能有效检测针头，显示出其优于传统基于强度的方法。
🔬 方法详解
问题定义：本文旨在解决超声图像中针头检测的困难，现有方法受到图像斑点、伪影和低分辨率的影响，导致检测效果不理想。
核心思路：VibNet的核心思路是通过对针杆施加周期性振动，增强图像中针头的可检测性，从而在频率域中提取更为鲁棒的特征。
技术框架：VibNet的整体架构包括三个主要模块：运动特征提取模块（短时傅里叶变换）、频率特征聚合模块和针头检测模块（霍夫变换）。该框架通过逐步实现子目标，提升针头检测的准确性。
关键创新：VibNet的主要创新在于利用外部振动增强针头在频率域中的特征表现，这一方法与传统的基于图像强度的检测方法有本质区别。
关键设计：在网络设计中，VibNet采用了特定的损失函数以优化针头检测精度，同时在短时傅里叶变换中设置了适当的参数，以确保运动特征的有效提取。实验中使用的样本包括不同类型的猪和牛组织，以验证方法的通用性和有效性。
🖼️ 关键图片
📊 实验亮点
实验结果表明，VibNet在猪组织样本中实现了1.61±1.56mm的针尖误差，相较于UNet的8.15±9.98mm和WNet的6.63±7.58mm，显示出显著的性能提升。同时，针头方向误差为1.64±1.86°，也优于其他基线方法。
🎯 应用场景
VibNet在超声引导的介入治疗中具有广泛的应用潜力，尤其是在针头检测精度要求高的医疗场景。其创新的振动增强特征提取方法，能够有效提升在低可见性条件下的针头检测能力，未来有望在临床实践中得到推广，改善患者的治疗效果。
📄 摘要（原文）
Precise percutaneous needle detection is crucial for ultrasound (US)-guided interventions. However, inherent limitations such as speckles, needle-like artifacts, and low resolution make it challenging to robustly detect needles, especially when their visibility is reduced or imperceptible. To address this challenge, we propose VibNet, a learning-based framework designed to enhance the robustness and accuracy of needle detection in US images by leveraging periodic vibration applied externally to the needle shafts. VibNet integrates neural Short-Time Fourier Transform and Hough Transform modules to achieve successive sub-goals, including motion feature extraction in the spatiotemporal space, frequency feature aggregation, and needle detection in the Hough space. Due to the periodic subtle vibration, the features are more robust in the frequency domain than in the image intensity domain, making VibNet more effective than traditional intensity-based methods. To demonstrate the effectiveness of VibNet, we conducted experiments on distinct \textit{ex vivo} porcine and bovine tissue samples. The results obtained on porcine samples demonstrate that VibNet effectively detects needles even when their visibility is severely reduced, with a tip error of $1.61\pm1.56~mm$ compared to $8.15\pm9.98~mm$ for UNet and $6.63\pm7.58~mm$ for WNet, and a needle direction error of $1.64\pm1.86^{\circ}$ compared to $9.29\pm15.30^{\circ}$ for UNet and $8.54\pm17.92^{\circ}$ for WNet. Code: https://github.com/marslicy/VibNet.