Recurrent neural networks (RNNs) have been widely adopted in research areas concerned with sequential data, such as text, audio, and video. However, RNNs consisting of sigma cells or tanh cells are unable to learn the relevant information of input data when the input gap is large. By introducing gate functions into the cell structure, the long short-term memory (LSTM) could handle the problem of long-term dependencies well. Since its introduction, almost all the exciting results based on RNNs have been achieved by the LSTM. The LSTM has become the focus of deep learning. We review the LSTM cell and its variants to explore the learning capacity of the LSTM cell. Furthermore, the LSTM networks are divided into two broad categories: LSTM-dominated networks and integrated LSTM networks. In addition, their various applications are discussed. Finally, future research directions are presented for LSTM networks.

No abstract

Conventional flow cytometry (FC) methods report optical signals integrated from individual cells at throughput rates as high as thousands of cells per second. This is further combined with the powerful utility to subsequently sort and/or recover the cells of interest. However, these methods cannot extract spatial information. This limitation has prompted efforts by some commercial manufacturers to produce state-of-the-art commercial flow cytometry systems allowing fluorescence images to be recorded by an imaging detector. Nonetheless, there remains an immediate and growing need for technologies facilitating spatial analysis of fluorescent signals from cells maintained in flow suspension. Here, we report a novel methodological approach to this problem that combines micro-fluidic flow, and microelectrode dielectric-field control to manipulate, immobilize and image individual cells in suspension. The method also offers unique possibilities for imaging studies on cells in suspension. In particular, we report the system's immediate utility for confocal "axial tomography" using micro-rotation imaging and show that it greatly enhances 3-D optical resolution compared with conventional light reconstruction (deconvolution) image data treatment. That the method we present here is relatively rapid and lends itself to full automation suggests its eventual utility for 3-D imaging cytometry.

Summary Recently, micro‐rotation confocal microscopy has enabled the acquisition of a sequence of micro‐rotated images of nonadherent living cells obtained during a partially controlled rotation movement of the cell through the focal plane. Although we are now able to estimate the three‐dimensional position of every optical section with respect to the cell frame, the reconstruction of the cell from the positioned micro‐rotated images remains a last task that this paper addresses. This is not strictly an interpolation problem since a micro‐rotated image is a convoluted two‐dimensional map of a three‐dimensional reality. It is rather a ‘reconstruction from projection’ problem where the term projection is associated to the PSF of the deconvolution process. Micro‐rotation microscopy has a specific difficulty. It does not yield a complete coverage of the volume. In this paper, experiments illustrate the ability of the classical EM algorithm to deconvolve efficiently cell volume despite of the incomplete coverage. This cell reconstruction method is compared to a kernel‐based method of interpolation, which does not take account explicitly the point‐spread‐function (PSF). It is also compared to the standard volume obtained from a conventional z‐stack. Our results suggest that deconvolution of micro‐rotation image series opens some exciting new avenues for further analysis, ultimately laying the way towards establishing an enhanced resolution 3D light microscopy.

No abstract

SummaryThe conventional approach for microscopic 3D cellular imaging is based on axial through-stack image series which has some significant limitations such as anisotropic resolution and axial aberration. To overcome these drawbacks, we have recently introduced an alternative approach based on micro-rotation image series. Unfortunately, this new technique suffers from a huge burden of computation that makes its use quite difficult for current applications.To address these problems we propose a new imaging strategy called bi-protocol, which consists of coupling microrotation acquisition and conventional z-stack acquisition. We experimentally prove bi-protocol 3D reconstruction produces similar quality to that of pure micro-rotation, but offers the advantage of reduced computation burden because it uses the z-stack volume to accelerate the registration of the microrotation images.

Abstract. Recently, micro-rotation confocal microscopy has enabled the acquisition of a sequence of slices for a non-adherent living cells where the slices' positions are roughly controlled by a dielectric-field biological cage. The high resolution volume reconstruction requires then the integration of precise alignment of slice positions. We propose in the Bayesian context, a new method combining both slice positioning and 3D volume reconstruction simultaneously, which leads naturally to an energy minimization procedure of a variational problem. An automatic calibration paradigm via Maximum Likelihood estimation (MLE) principle is used for the relative hyper-parameter determination. We provide finally experimental comparison results on both conventional z-stack confocal images and 3D volume reconstruction from micro-rotation slices of the same non-adherent living cell to show its potential biomedical application.

No abstract