Deep learning-assisted wavefront correction with sparse data for holographic tomography

In this paper, a novel approach using deep learning-assisted wavefront correction in beam rotation holographic tomography to acquire three-dimensional images of native biological cell samples is described. With digitally recorded holograms, the aberration contained reconstructed phases. However, there are large computation costs for compensating phase during reconstruction. aid convolution network, we present an effective algorithm on phases with sparse data active correction. To accomplish this, developed Res-Unet scheme segment region from its background and regression network representation Zernike orthonormal basis. Moreover, fitting was used predict coefficients whole scanning angles collected data. As result, proposed capable accurately correcting much faster than original plain algorithm.