Photoacoustic microscopy (PAM) is a non-invasive, label-free functional imaging technique that provides high absorption contrast with high spatial resolution. Spatial sampling density and data size are key determinants of PAM imaging speed. Therefore, undersampling methods that reduce the number of scan points are usually employed to improve the imaging speed of PAM by increasing the scan step size. Because undersampling techniques sacrifice spatial sampling density, deep learning-based reconstruction techniques have been explored as alternatives. However, these methods have been applied to reconstruct two-dimensional PAM images related to spatial sampling density. Therefore, by considering the number of data points, the data size, and the characteristics of PAM to provide three-dimensional (3D) volume data, this study proposes a deep-learning-based complete reconstruction of undersampled 3D PAM data. newly reported to Obtained from real experiments (i.e. not manually generated). Quantitative analysis results show that the proposed method exhibits robustness and outperforms interpolation-based reconstruction methods at various undersampling ratios, resulting in 80x faster imaging speed and 800x smaller data. Improves PAM system performance with size. Furthermore, the applicability of this method is experimentally verified by enlarging a sparsely sampled test dataset. His proposed deep learning-based PAM data reconstruction has been demonstrated to be the closest model available under experimental conditions, significantly reducing the data size for processing and effectively reducing the imaging time.

Photoacoustic microscopy (PAM) is a non-invasive, label-free functional imaging technique that provides high absorption contrast with high spatial resolution. Spatial sampling density and data size are important determinants of the imaging speed of PAM. Therefore, undersampling methods that reduce the number of scanning points are typically adopted to enhance the imaging speed of PAM by increasing the scanning step size. For the reason that undersampling methods sacrifice spatial sampling density, deep learning-based reconstruction methods have been considered as an alternative; however, these methods have been applied to reconstruct the two-dimensional PAM images, which is related to the spatial sampling density. Therefore, by considering the number of data points, data size, and the characteristics of PAM that provides three-dimensional (3D) volume data, in this study, we newly reported deep learning-based fully reconstructing the undersampled 3D PAM data, which is obtained at the actual experiment (i.e., not manually generated). The results of quantitative analyses demonstrate that the proposed method exhibits robustness and outperforms interpolation-based reconstruction methods at various undersampling ratios, enhancing the PAM system performance with 80-times faster-imaging speed and 800-times lower data size. Moreover, the applicability of this method is experimentally verified by upscaling the sparsely sampled test dataset. The proposed deep learning-based PAM data reconstructing is demonstrated to be the closest model that can be used under experimental conditions, effectively shortening the imaging time with significantly reduced data size for processing.