Lu Mengyang, Liu Xin, Liu Chengcheng, Li Boyi, Gu Wenting, Jiang Jiehui, Ta Dean
School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China.
Academy for Engineering and Technology, Fudan University, Shanghai 200433, China.
Biomed Opt Express. 2021 Sep 15;12(10):6284-6299. doi: 10.1364/BOE.434172. eCollection 2021 Oct 1.
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 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.
光声断层扫描（PAT）是一种新兴的生物医学成像技术，它能够实现具有声学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，当前基于DL的PAT方法是通过监督学习策略实现的，其成像性能依赖于可用的真实数据。为了克服这一局限性，本研究引入了一种基于循环生成对抗网络（CycleGAN）的新图像域变换方法，称为PA-GAN，用于以无监督学习的方式去除PAT图像中因使用有限视角测量数据而产生的伪影。使用来自体模和实验的一系列数据来评估所提出的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，当处理极其稀疏的测量数据时（例如在圆形体模实验中的8个投影），与监督学习的U-Net方法相比，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%，峰值信噪比（PSNR）提高了约66%。随着投影数量的增加（例如128个投影），U-Net，特别是FD U-Net，在SSIM和PSNR方面的伪影去除能力略有提高。此外，一旦网络训练完成，PA-GAN和U-Net获得的计算时间相似（约60 ms/帧）。更重要的是，PA-GAN比U-Net更灵活，允许模型使用未配对的数据进行有效训练。因此，PA-GAN使得在不影响成像性能的情况下以更高的灵活性实现PAT成为可能。
