Volumetric Bioimaging via Dual-Resonant Scanning Multiphoton Microscopy with 3D-Generator U-Net

Multiphoton microscopy is a powerful technique for in-vivo bioimaging. Many high-speed volumetric methods have been integrated with multiphoton microscopy to achieve dynamic signal imaging. In this study, we have developed a dual-resonant scanning multiphoton (DRSM) microscope that a frame rate of around 8,000 Hz and a volumetric imaging rate of over 30 Hz can be obtained for a big image volume of 343×343×120 μm³ with a large image size of 256×256×80 voxels. The practical feasibility of the DRSM microscope is demonstrated by observing the mushroom bodies of a drosophila brain and performing 3D dynamic observations of moving 10-μm fluorescent beads. However, the volumetric images have a severe negative signal-to-noise ratio (SNR) as a result of a large number of missing voxels for a large scanning volume and the presence of Lissajous patterning residuals. Due to this drawback and a large number of missing voxels in DRSM, a 3D-generator U-Net model is used to inpaint and denoise the images. The results show that the model achieves dynamic volumetric imaging to be performed with significant SNR improvement. The performance of the 3D U-Net model for bioimaging applications is enhanced by training the model with high-SNR in-vitro drosophila brain images captured using a conventional point scanning multiphoton microscope. Through the assistance of transfer learning, the model can be extended to the restoration of in-vivo drosophila brain images with a high image quality and a rapid training time.