Three-dimensional-generator U-net for dual-resonant scanning multiphoton microscopy image inpainting and denoising

Abstract

A dual-resonant scanning multiphoton (DRSM) microscope incorporating a tunable acoustic gradient index of refraction lens and a resonant mirror is developed for rapid volumetric bioimaging. It is shown that the microscope achieves a volumetric imaging rate up to 31.25 volumes per second (vps) for a scanning volume of up to 200 × 200 × 100 µm3 with 256 × 256 × 128 voxels. 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. Thus, a modified three-dimensional (3D)-generator U-Net model trained using simulated microbead images is proposed and used to inpaint and denoise the images. 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. The trained model shows the ability to produce clear in-vitro drosophila brain images at a rate of 31.25 vps with a SNR improvement of approximately 20 dB over the original images obtained by the DRSM microscope. The training convergence time of the modified U-Net model is just half that of a general 3D U-Net model. The model thus has significant potential for 3D in-vivo bioimaging transfer learning. 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.