BLSTM convolution and self-attention network enabled recursive and direct prediction for optical chaos.

Chaotic time series prediction has attracted much attention in recent years because of its important applications, such as security analysis for random number generators and chaos synchronization in private communications. Herein, we propose a BLSTM convolution and self-attention network model to predict the optical chaos. We validate the model's capability for direct and recursive prediction, and the model dramatically reduces the accumulation of errors. Moreover, the time duration prediction of optical chaos is increased with comparative accuracy where the predicted sequence length reaches 4 ns with normalized mean squared error (NMSE) of less than 0.01.

SASAN: Spectrum-Axial Spatial Approach Networks for Medical Image Segmentation.

Ophthalmic diseases such as central serous chorioretinopathy (CSC) significantly impair the vision of millions of people globally. Precise segmentation of choroid and macular edema is critical for diagnosing and treating these conditions. However, existing 3D medical image segmentation methods often fall short due to the heterogeneous nature and blurry features of these conditions, compounded by medical image clarity issues and noise interference arising from equipment and environmental limitations. To address these challenges, we propose the Spectrum Analysis Synergy Axial-Spatial Network (SASAN), an approach that innovatively integrates spectrum features using the Fast Fourier Transform (FFT). SASAN incorporates two key modules: the Frequency Integrated Neural Enhancer (FINE), which mitigates noise interference, and the Axial-Spatial Elementum Multiplier (ASEM), which enhances feature extraction. Additionally, we introduce the Self-Adaptive Multi-Aspect Loss ( LSM ), which balances image regions, distribution, and boundaries, adaptively updating weights during training. We compiled and meticulously annotated the Choroid and Macular Edema OCT Mega Dataset (CMED-18k), currently the world's largest dataset of its kind. Comparative analysis against 13 baselines shows our method surpasses these benchmarks, achieving the highest Dice scores and lowest HD95 in the CMED and OIMHS datasets. Our code is publicly available at https://github.com/IMOP-lab/SASAN-Pytorch.

Circular polarizers and their effect on partial coherence.

We examine the action of a circular polarizer on an incident beam that is spatially partially coherent and partially polarized. It is found that the beam's coherence area can be significantly increased or decreased by the polarizer. Furthermore, an expression for the transmission efficiency is derived.

One-to-all lightweight Fourier channel attention convolutional neural network for speckle reconstructions.

Speckle reconstruction is a classical inverse problem in computational imaging. Inspired by the memory effect of the scattering medium, deep learning methods reveal excellent performance in extracting the correlation of speckle patterns. Nowadays, advanced models generally include more than 10M parameters and mostly pay more attention to the spatial feature information. However, the frequency domain of images also contains precise hierarchical representations. Here we propose a one-to-all lightweight Fourier channel attention convolutional neural network (FCACNN) with Fourier channel attention and the res-connected bottleneck structure. Compared with the state-of-the-art model, i.e., self-attention armed convolutional neural network (SACNN), our architecture has better feature extraction and reconstruction ability. The Pearson correlation coefficient and Jaccard index scores of FCACNN increased by at least 5.2% and 13.6% compared with task-related models. And the parameter number of the lightweight FCACNN is only 1.15M. Furthermore, the validation results show that the one-to-all model, FCACNN, has excellent generalization capability on unseen speckle patterns such as handwritten letters and Quickdraws.

High-accuracy, direct aberration determination using self-attention-armed deep convolutional neural networks.

Optical microscopes have long been essential for many scientific disciplines. However, the resolution and contrast of such microscopic images are dramatically affected by aberrations. In this study, compacted with adaptive optics, we propose a machine learning technique, called the 'phase-retrieval deep convolutional neural networks (PRDCNNs)'. This aberration determination architecture is direct and exhibits high accuracy and certain generalisation ability. Notably, its performance surpasses those of similar, existing methods, with fewer fluctuations and greater robustness against noise. We anticipate future application of the proposed PRDCNNs to super-resolution microscopes.

High-generalization deep sparse pattern reconstruction: feature extraction of speckles using self-attention armed convolutional neural networks.

Light scattering is a pervasive problem in many areas. Recently, deep learning was implemented in speckle reconstruction. To better investigate the key feature extraction and generalization abilities of the networks for sparse pattern reconstruction, we develop the "one-to-all" self-attention armed convolutional neural network (SACNN). It can extract the local and global speckle properties of different types of sparse patterns, unseen glass diffusers, and untrained detection positions. We quantitatively analyzed the performance and generalization ability of the SACNN using scientific indicators and found that, compared with convolutional neural networks, the Pearson correlation coefficient, structural similarity measure, and Jaccard index for the validation datasets increased by more than 10% when SACNN was used. Moreover, SACNN is capable of reconstructing features 75 times beyond the memory effect range for a 120 grits diffuser. Our work paves the way to boost the field of view and depth of field for various sparse patterns with complex scatters, especially in deep tissue imaging.

Fraunhofer diffraction and the state of polarization of partially coherent electromagnetic beams.

We generalize the concept of Fraunhofer diffraction to partially coherent electromagnetic beams and show how the state of polarization is affected by a circular aperture. It is illustrated that the far-zone properties of a random beam can be tuned by varying the aperture radius. We find that even an incident beam that is completely unpolarized can sometimes produce a field that is highly polarized.

Hilbert's Hotel in polarization singularities.

We demonstrate theoretically how the creation of polarization singularities by the evolution of a fractional nonuniform polarization optical element involves the peculiar mathematics of countably infinite sets in the form of "Hilbert's Hotel." Two distinct topological processes can be observed, depending on the structure of the fractional optical element.

Electromagnetic diffraction theory of refractive axicon lenses.

We study the field that is produced by a paraxial refractive axicon lens. The results from geometrical optics, scalar wave optics, and electromagnetic diffraction theory are compared. In particular, the axial intensity, the on-axis effective wavelength, the transverse intensity, and the far-zone field are examined. A rigorous electromagnetic diffraction analysis shows that the state of polarization of the incident beam strongly affects the transverse intensity distribution, but not the intensity distribution in the far zone.

Strong suppression of forward or backward Mie scattering by using spatial coherence.

We derive analytic expressions relating Mie scattering with partially coherent fields to scattering with fully coherent fields. These equations are then used to demonstrate how the intensity of the forward- or backward-scattered field can be suppressed several orders of magnitude by tuning the spatial coherence properties of the incident field. This method allows the creation of cone-like scattered fields, with the angle of maximum intensity given by a simple formula.

Tunable, anomalous Mie scattering using spatial coherence.

We demonstrate that a J0-Bessel-correlated beam that is incident on a homogeneous sphere produces a highly unusual distribution of the scattered field, with the maximum no longer occurring in the forward direction. Such a beam can be easily generated using a spatially incoherent, annular source. Moreover, the direction of maximal scattering can be shifted by changing the spatial coherence length. In this process, the total power that is scattered remains constant. This new tool to control scattering directionality may be used to steer the scattered field away from the forward direction and selectively address detectors situated at different angles.