Adaptive optics has been widely used in biological science to recover high-resolution optical image deep into the tissue, where optical distortion detection with high speed and accuracy is strongly required. Here, we introduce convolutional neural networks, one of the most popular machine learning models, into Shack–Hartmann wavefront sensor (SHWS) to simplify optical distortion detection processes. Without image segmentation or centroid positioning algorithm, the trained network could estimate up to 36th Zernike mode coe±cients directly from a full SHWS image within 1.227 ms on a personal computer, and achieves prediction accuracy up to 97.4%. The simulation results show that the average root mean squared error in phase residuals of our method is 75.64% lower than that with the modal-based SHWS method. With the high detection accuracy and simplified detection processes, this work has the potential to be applied in wavefront sensor-based adaptive optics for in vivo deep tissue imaging.

Two-photon microscopy normally suffers from the scattering of the tissue in biological imaging. Multidither coherent optical adaptive technique (COAT) can correct the scattered wavefront in parallel. However, the determination of the corrective phases may not be completely accurate using conventional method, which undermines the performance of this technique. In this paper, we theoretically demonstrate a method that can obtain more accurate corrective phases by determining the phase values from the square root of the fluorescence signal. A numerical simulation model is established to study the performance of adaptive optics in two-photon microscopy by combining scalar diffraction theory with vector diffraction theory. The results show that the distortion of the wavefront can be corrected more thoroughly with our method in two-photon imaging. In our simulation, with the scattering from a 450-μm-thick mouse brain tissue, excitation focal spots with higher peak-to-background ratio (PBR) and images with higher contrast can be obtained. Hence, further enhancement of the multidither COAT correction performance in two-photon imaging can be expected.