Liu Yuxuan, Zhou Jiasheng, Luo Yating, Li Jinkai, Chen Sung-Liang, Guo Yao, Yang Guang-Zhong
Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China.
University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai, 200240, China.
Photoacoustics. 2024 Apr 25;38:100608. doi: 10.1016/j.pacs.2024.100608. eCollection 2024 Aug.
Photoacoustic microscopy (PAM) has gained increasing popularity in biomedical imaging, providing new opportunities for tissue monitoring and characterization. With the development of deep learning techniques, convolutional neural networks have been used for PAM image resolution enhancement and denoising. However, there exist several inherent challenges for this approach. This work presents a nified hotocoustic icroscopy image reconstruction work (UPAMNet) for both PAM image super-resolution and denoising. The proposed method takes advantage of deep image priors by incorporating three effective attention-based modules and a mixed training constraint at both pixel and perception levels. The generalization ability of the model is evaluated in details and experimental results on different PAM datasets demonstrate the superior performance of the method. Experimental results show improvements of 0.59 dB and 1.37 dB, respectively, for 1/4 and 1/16 sparse image reconstruction, and 3.9 dB for image denoising in peak signal-to-noise ratio.
光声显微镜（PAM）在生物医学成像中越来越受欢迎，为组织监测和表征提供了新的机会。随着深度学习技术的发展，卷积神经网络已被用于增强PAM图像分辨率和去噪。然而，这种方法存在几个固有挑战。这项工作提出了一种用于PAM图像超分辨率和去噪的统一光声显微镜图像重建工作（UPAMNet）。所提出的方法通过合并三个基于有效注意力的模块以及像素和感知层面的混合训练约束来利用深度图像先验。详细评估了模型的泛化能力，在不同PAM数据集上的实验结果证明了该方法的优越性能。实验结果表明，对于1/4和1/16稀疏图像重建，峰值信噪比分别提高了0.59 dB和1.37 dB，对于图像去噪提高了3.9 dB。
