IEEE J Biomed Health Inform. 2020 Feb;24(2):568-576. doi: 10.1109/JBHI.2019.2912935. Epub 2019 Apr 23.
Photoacoustic imaging is an emerging imaging modality that is based upon the photoacoustic effect. In photoacoustic tomography (PAT), the induced acoustic pressure waves are measured by an array of detectors and used to reconstruct an image of the initial pressure distribution. A common challenge faced in PAT is that the measured acoustic waves can only be sparsely sampled. Reconstructing sparsely sampled data using standard methods results in severe artifacts that obscure information within the image. We propose a modified convolutional neural network (CNN) architecture termed fully dense UNet (FD-UNet) for removing artifacts from two-dimensional PAT images reconstructed from sparse data and compare the proposed CNN with the standard UNet in terms of reconstructed image quality.
光声成像是一种新兴的成像模式，它基于光声效应。在光声断层扫描（PAT）中，通过探测器阵列测量诱导的声压波，并用于重建初始压力分布的图像。PAT 中面临的一个常见挑战是，测量的声波只能稀疏采样。使用标准方法重建稀疏采样数据会导致严重的伪影，从而模糊图像中的信息。我们提出了一种修改后的卷积神经网络（CNN）架构，称为全密集 U 型网络（FD-UNet），用于从稀疏数据重建的二维 PAT 图像中去除伪影，并在重建图像质量方面将提出的 CNN 与标准 U 型网络进行比较。
