Photoacoustic tomography (PAT) is an emerging biomedical imaging technology that can realize high contrast imaging with a penetration depth of the acoustic. Recently, deep learning (DL) methods have also been successfully applied to PAT for improving the image reconstruction quality. However, the current DL-based PAT methods are implemented by the supervised learning strategy, and the imaging performance is dependent on the available ground-truth data. To overcome the limitation, this work introduces a new image domain transformation method based on cyclic generative adversarial network (CycleGAN), termed as PA-GAN, which is used to remove artifacts in PAT images caused by the use of the limited-view measurement data in an unsupervised learning way. A series of data from phantom and in vivo experiments are used to evaluate the performance of the proposed PA-GAN. The experimental results show that PA-GAN provides a good performance in removing artifacts existing in photoacoustic tomographic images. In particular, when dealing with extremely sparse measurement data (e.g., 8 projections in circle phantom experiments), higher imaging performance is achieved by the proposed unsupervised PA-GAN, with an improvement of ∼14% in structural similarity (SSIM) and ∼66% in peak signal to noise ratio (PSNR), compared with the supervised-learning U-Net method. With an increasing number of projections (e.g., 128 projections), U-Net, especially FD U-Net, shows a slight improvement in artifact removal capability, in terms of SSIM and PSNR. Furthermore, the computational time obtained by PA-GAN and U-Net is similar (∼60 ms/frame), once the network is trained. More importantly, PA-GAN is more flexible than U-Net that allows the model to be effectively trained with unpaired data. As a result, PA-GAN makes it possible to implement PAT with higher flexibility without compromising imaging performance.

中文翻译：

---

使用无监督方法去除光声层析成像中的伪影

光声断层扫描（PAT）是一种新兴的生物医学成像技术，可以实现声波穿透深度的高对比度成像。最近，深度学习 (DL) 方法也已成功应用于 PAT 以提高图像重建质量。然而，目前基于 DL 的 PAT 方法是通过监督学习策略实现的，成像性能取决于可用的地面实况数据。为了克服这个限制，这项工作引入了一种新的基于循环生成对抗网络（CycleGAN）的图像域变换方法，称为 PA-GAN，用于去除 PAT 图像中由于使用有限视图测量数据而引起的伪影以无监督学习的方式。来自体模和体内的一系列数据实验用于评估所提出的 PA-GAN 的性能。实验结果表明，PA-GAN 在去除光声断层图像中存在的伪影方面具有良好的性能。特别是，在处理极其稀疏的测量数据时（例如，圆形体模实验中的 8 个投影），所提出的无监督 PA-GAN 实现了更高的成像性能，结构相似性（SSIM）提高了约 14%，约 66与监督学习 U-Net 方法相比，峰值信噪比 (PSNR) 的百分比。随着投影数量的增加（例如，128 个投影），U-Net，尤其是 FD U-Net，在 SSIM 和 PSNR 方面的伪影去除能力略有提高。此外，PA-GAN 和 U-Net 获得的计算时间相似（~60 ms/帧），一旦网络被训练。更重要的是，PA-GAN 比 U-Net 更灵活，可以使用未配对的数据有效地训练模型。因此，PA-GAN 可以在不影响成像性能的情况下以更高的灵活性实现 PAT。