Optimal Adaptive Microscopic Imaging Method and Device Based on Machine Learning

Abstract

The invention discloses a machine learning-based optimized self-adaptive microscopic imaging method and device, wherein the method includes the following steps: using ultrashort pulse laser to collect image data through a point scanning method; constructing a convolutional neural network to input The simulation results obtained from the image data to the physical model train the network; apply the trained training network to the adaptive method, optimize the imaging result, and eliminate image distortion, and use the model fitting method to find the optimal phase of the system and sample distortion correction compensate. This method can obtain imaging results with high optimization performance, high image quality, and high imaging speed, and has the advantages of high speed, high image quality, and good scalability, and realizes high-speed wavefront distortion compensation based on machine learning. It has great application prospects in deep tissue imaging.

Description

technical field [0001] The present invention relates to the technical field of microscopic imaging, in particular to an optimized self-adaptive microscopic imaging method and device based on machine learning. Background technique [0002] AO (Adaptive Optical, Adaptive Optics) was originally a method applied to astronomical telescopes, and it has been applied to optical microscopes due to its ability to correct the aberrations introduced by optical systems and biological samples. It works by dynamically measuring the distortion accumulated by light in a non-homogeneous sample and correcting for the distortion with active optical elements, thereby restoring diffraction-limited imaging performance deep in scattering tissue. To restore ideal imaging performance, the AO method measures the wavefront distortion present during image formation and corrects the wavefront accordingly to compensate for the inherent distortion of the optical system or sample. There are many AO methods...

AI Technical Summary

Problems solved by technology

However, there are two problems in the existing AO method: 1. When the aberration distortion is larger than the range that the modulator can change, especially under the long-wavelength laser for nonlinear optical imaging, it is often difficult to achieve the optimal AO compensation distortion phase; 2. .The compensation algorithm is complex and the imaging speed is slow

Images