Search

LED array microscopes have the advantages of miniaturisation and low cost. It has been demonstrated that LED array microscopes outperform Köhler illumination microscopes in some applications. A LED array allows for a large numerical aperture of illumination. The larger numerical aperture of illumination brings the higher spatial resolution, but the lower image contrast as well. Therefore, there is a tradeoff between resolution and contrast for LED array microscopes. The Fourier ptychographic algorithm can overcome this tradeoff by increasing image contrast without sacrificing spatial resolution. However, the Fourier ptychographic algorithm requires acquisition of multiple images, which is time‐consuming and results in live sample imaging challenging. To solve this problem, we develop contrast‐enhanced, single‐shot LED array microscopy based on the Fourier ptychographic algorithm and deep learning. The sample to be imaged is under illumination by all LEDs of the array simultaneously. The image captured is fed to several trained convolutional neural networks to generate the same number of images that are required by the Fourier ptychographic algorithm. We experimentally present that the image contrast of the final reconstruction is remarkably improved in comparison with the image captured. The proposed method can also produce chromatic‐aberration‐free results, even when an objective without aberration correction is used. We believe the method might provide live sample imaging with a low‐cost approach. [ABSTRACT FROM AUTHOR]

The realization of accurate fault diagnosis is crucial to ensure the normal operation of machines. At present, an intelligent fault diagnosis method based on deep learning has been widely applied in mechanical areas due to its strong ability of feature extraction and accurate identification. However, it often depends on enough training samples. Generally, the model performance depends on sufficient training samples. However, the fault data are always insufficient in practical engineering as the mechanical equipment often works under normal conditions, resulting in imbalanced data. Deep learning-based models trained directly with the imbalanced data will greatly reduce the diagnosis accuracy. In this paper, a diagnosis method is proposed to address the imbalanced data problem and enhance the diagnosis accuracy. Firstly, signals from multiple sensors are processed by the wavelet transform to enhance data features, which are then squeezed and fused through pooling and splicing operations. Subsequently, improved adversarial networks are constructed to generate new samples for data augmentation. Finally, an improved residual network is constructed by introducing the convolutional block attention module for enhancing the diagnosis performance. The experiments containing two different types of bearing datasets are adopted to validate the effectiveness and superiority of the proposed method in single-class and multi-class data imbalance cases. The results show that the proposed method can generate high-quality synthetic samples and improve the diagnosis accuracy presenting great potential in imbalanced fault diagnosis. [ABSTRACT FROM AUTHOR]

Motivation Cryo-Electron Tomography (cryo-ET) is a 3D imaging technology that enables the visualization of subcellular structures in situ at near-atomic resolution. Cellular cryo-ET images help in resolving the structures of macromolecules and determining their spatial relationship in a single cell, which has broad significance in cell and structural biology. Subtomogram classification and recognition constitute a primary step in the systematic recovery of these macromolecular structures. Supervised deep learning methods have been proven to be highly accurate and efficient for subtomogram classification, but suffer from limited applicability due to scarcity of annotated data. While generating simulated data for training supervised models is a potential solution, a sizeable difference in the image intensity distribution in generated data as compared with real experimental data will cause the trained models to perform poorly in predicting classes on real subtomograms. Results In this work, we present Cryo-Shift , a fully unsupervised domain adaptation and randomization framework for deep learning-based cross-domain subtomogram classification. We use unsupervised multi-adversarial domain adaption to reduce the domain shift between features of simulated and experimental data. We develop a network-driven domain randomization procedure with 'warp' modules to alter the simulated data and help the classifier generalize better on experimental data. We do not use any labeled experimental data to train our model, whereas some of the existing alternative approaches require labeled experimental samples for cross-domain classification. Nevertheless, Cryo-Shift outperforms the existing alternative approaches in cross-domain subtomogram classification in extensive evaluation studies demonstrated herein using both simulated and experimental data. Availabilityand implementation https://github.com/xulabs/aitom. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]