乳腺全波形反演的多尺度梯度平滑策略实现与验证
本研究提出一种改进的全波形反演(FWI)算法,利用高斯梯度滤波(GGF)提取低波数梯度并进行多尺度策略以减轻周期跳跃。数值实验显示GGF+FWI较传统FWI降低声速重建均方根误差并提高结构相似性指数;在体乳腺实验证实其稳健性,多尺度GGF获得最高对比噪声比。
要点
- 多尺度GGF策略通过逐步降低低通滤波标准差来稳定反演更新。
- GGF+FWI较传统FWI降低声速重建均方根误差并提高结构相似性指数。
- 在体乳腺实验中多尺度GGF获得最高对比噪声比。
核心结论
- 所提方法可改善优化算法的收敛性能并减轻伪影。
研究设计与样本
- 数值实验采用传统FWI与所提方法进行对比;在体乳腺实验比较FWI、基于频移包络的全局相关范数、基于频移包络的全局相关范数+FWI以及多尺度GGF。
关键影像表现/征象
- 多尺度GGF策略在逐步降低低通滤波标准差的过程中驱动稳定更新。
- 在体乳腺实验证实所提方法具有稳健性。
- 多尺度GGF在比较中获得最高对比噪声比。
诊断标准与关键数值
- GGF+FWI较传统FWI降低声速重建均方根误差并提高结构相似性指数。
- 多尺度GGF在FWI、基于频移包络的全局相关范数、基于频移包络的全局相关范数+FWI和多尺度GGF的比较中对比噪声比最高。
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: Full waveform inversion (FWI) is an advanced technique for reconstructing high-resolution sound speed images, offering quantitative measurements of tissue sound speed in ultrasound computed tomography. However, FWI is susceptible to the issue of cycle skipping, which frequently causes the inversion to converge to a local minimum. To help mitigate cycle skipping, this paper proposes a modified FWI algorithm.
METHODS: Our approach incorporated low-wavenumber extraction in the image domain, capitalizing on the inherent large-scale background information in the gradient. Within a Gaussian gradient filtering (GGF) framework, we extract a robust low-wavenumber gradient-referred to as gradient smoothing-to drive stable updates and we extend this into a multi-scale GGF strategy by progressively reducing the standard deviation of the low-pass filter over the inversion.
RESULTS: A comparative analysis between the proposed method and conventional FWI was conducted in numerical experiments. Compared with conventional FWI, the GGF + FWI reduced the sound-speed reconstruction root mean square error and improved the structural similarity index measure. In vivo breast experiments confirmed the robustness of our method. In the comparison of FWI, frequency-shifted envelope-based global correlation norm, frequency-shifted envelope-based global correlation norm + FWI and multi-scale GGF, the effectiveness of multi-scale GGF was confirmed by the highest contrast-to-noise ratio.
CONCLUSION: These results demonstrate that the proposed approach can improve the convergence properties of the optimization algorithm and mitigate artefacts.
引用
- Wu Y, Zhang Q, Yan W, et al. Implementation and Validation of the Multi-scale Gradient Smoothing Strategy for Breast Full Waveform Inversion. Ultrasound Med Biol. 2026. PMID: 41876345. doi:10.1016/j.ultrasmedbio.2026.02.020
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。