基于深度学习的超声声速断层成像重建:Tikhonov伪逆先验方法
本研究将传统线性近似作为先验知识引入深度神经网络,把超声声速断层成像重建这一复杂非线性映射分解为线性映射与非线性映射的结合,线性映射用全连接层实现并以Tikhonov伪逆矩阵初始化,非线性映射用U-Net实现,提出了TU-Net与UT-Net两种网络结构。数值仿真中UT-Net与TU-Net的均方根误差分别为6.49和4.29 m/s,峰值信噪比分别为49.01和52.90 dB,结构相似性分别为0.9436和0.9761,重建时间分别为10.8和11.3 ms。两种方法均获得了高声速精度的声速图像,实现了高质量与低计算成本。
要点
- TU-Net与UT-Net在仿真中均实现高声速精度与低计算成本。
- TU-Net的均方根误差4.29 m/s、峰值信噪比52.90 dB、结构相似性0.9761,优于UT-Net。
- 重建时间分别为TU-Net 11.3 ms、UT-Net 10.8 ms,满足低计算成本需求。
诊断标准与关键数值
- UT-Net仿真重建均方根误差为6.49 m/s,峰值信噪比为49.01 dB,结构相似性为0.9436,重建时间为10.8 ms。
- TU-Net仿真重建均方根误差为4.29 m/s,峰值信噪比为52.90 dB,结构相似性为0.9761,重建时间为11.3 ms。
临床应用与阅片要点
- 该方法重建的声速图像具有高声速精度,可用于乳腺成像与乳腺癌检测的声速断层成像重建。
- 线性映射先于非线性映射(TU-Net)比非线性映射先于线性映射(UT-Net)获得更优的仿真重建指标。
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
Ultrasound sound-speed tomography (USST) is a promising technology for breast imaging and breast cancer detection. Its reconstruction is a complex non-linear mapping from the projection data to the sound-speed image (SSI). The traditional reconstruction methods include mainly the ray-based methods and the waveform-based methods. The ray-based methods with linear approximation have low computational cost but low reconstruction quality; the full wave-based methods with the complex non-linear model have high quality but high cost. To achieve both high quality and low cost, we introduced traditional linear approximation as prior knowledge into a deep neural network and treated the complex non-linear mapping of USST reconstruction as a combination of linear mapping and non-linear mapping. In the proposed method, the linear mapping was seamlessly implemented with a fully connected layer and initialized using the Tikhonov pseudo-inverse matrix. The non-linear mapping was implemented using a U-shape Net (U-Net). Furthermore, we proposed the Tikhonov U-shape net (TU-Net), in which the linear mapping was done before the non-linear mapping, and the U-shape Tikhonov net (UT-Net), in which the non-linear mapping was done before the linear mapping. Moreover, we conducted simulations and experiments for evaluation. In the numerical simulation, the root-mean-squared error was 6.49 and 4.29 m/s for the UT-Net and TU-Net, the peak signal-to-noise ratio was 49.01 and 52.90 dB, the structural similarity was 0.9436 and 0.9761 and the reconstruction time was 10.8 and 11.3 ms, respectively. In this study, the SSIs obtained with the proposed methods exhibited high sound-speed accuracy. Both the UT-Net and the TU-Net achieved high quality and low computational cost.
引用
- Qu, Ren, Yan, et al. Deep-Learning-Based Ultrasound Sound-Speed Tomography Reconstruction with Tikhonov Pseudo-Inverse Priori. Ultrasound Med Biol. 2022. PMID: 35922265. doi:10.1016/j.ultrasmedbio.2022.05.033
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。