Photoacoustic Source Detection and Reflection Artifact Removal Enabled by Deep Learning.
Photoacoustic Source Detection and Reflection Artifact Removal Enabled by Deep Learning.
复制标题
DOI：
10.1109/tmi.2018.2829662
复制
发表时间：
2018-06
影响因子：
10.6
通讯作者：
Bell MAL
中科院分区：
文献类型：
--
作者：
Allman D;Reiter A;Bell MAL
光声成像的介入应用通常需要点状目标的可视化，例如针、导管或近距离放射治疗种子的小的圆形横截面尖端。当这些点状目标在存在高回声结构的情况下成像时，所产生的光声波产生可能表现为真实信号的反射伪影。我们建议使用深度学习技术来识别这些类型的噪声伪影，以便在实验光声数据中去除。为了实现这一目标，首先训练卷积神经网络（CNN）来定位和分类使用k-Wave模拟的预波束形成数据中的源和伪影。模拟最初包含一个源和一个伪影，具有各种中等声速和2-D目标位置。基于3，468张测试图像，我们在对源和伪影进行分类方面实现了100%的成功率。在添加噪声以评估更真实成像环境中的潜在性能后，我们在通道信噪比（SNR）为-9dB或更高时实现了至少98%的成功率，而在低于-21dB通道SNR时性能严重下降。然后，我们探索了多个源和两种类型的声学接收器的训练，并在检测点源方面取得了类似的成功。然后将用模拟数据训练的网络转移到实验水浴和体模数据中，分别具有100%和96.67%的源分类准确度（特别是当在训练期间包括的深度处测试网络时）。水浴和体模实验数据的点源定位误差的相应平均值±一个标准差分别为0.40 ± 0.22 mm和0.38 ± 0.25 mm，这提供了我们新的基于CNN的成像系统的分辨率极限的一些指示。我们最终表明，基于CNN的信息可以以一种新的无伪影图像格式显示，使我们能够有效地去除光声图像中的反射伪影，这是传统的基于几何的波束成形所不可能实现的。
Interventional applications of photoacoustic imaging typically require visualization of point-like targets, such as the small, circular, cross-sectional tips of needles, catheters, or brachytherapy seeds. When these point-like targets are imaged in the presence of highly echogenic structures, the resulting photoacoustic wave creates a reflection artifact that may appear as a true signal. We propose to use deep learning techniques to identify these types of noise artifacts for removal in experimental photoacoustic data. To achieve this goal, a convolutional neural network (CNN) was first trained to locate and classify sources and artifacts in pre-beamformed data simulated with k-Wave. Simulations initially contained one source and one artifact with various medium sound speeds and 2-D target locations. Based on 3,468 test images, we achieved a 100% success rate in classifying both sources and artifacts. After adding noise to assess potential performance in more realistic imaging environments, we achieved at least 98% success rates for channel signal-to-noise ratios (SNRs) of −9dB or greater, with a severe decrease in performance below −21dB channel SNR. We then explored training with multiple sources and two types of acoustic receivers and achieved similar success with detecting point sources. Networks trained with simulated data were then transferred to experimental waterbath and phantom data with 100% and 96.67% source classification accuracy, respectively (particularly when networks were tested at depths that were included during training). The corresponding mean ± one standard deviation of the point source location error was 0.40 ± 0.22 mm and 0.38 ± 0.25 mm for waterbath and phantom experimental data, respectively, which provides some indication of the resolution limits of our new CNN-based imaging system. We finally show that the CNN-based information can be displayed in a novel artifact-free image format, enabling us to effectively remove reflection artifacts from photoacoustic images, which is not possible with traditional geometry-based beamforming.