scholarly journals DeepProjection: Rapid and structure-specific projections of tissue sheets embedded in 3D microscopy stacks using deep learning

2021 ◽  
Author(s):  
Daniel Haertter ◽  
Xiaolei Wang ◽  
Stephanie M Fogerson ◽  
Nitya Ramkumar ◽  
Janice M Crawford ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cell Sheet ◽  
Time Lapse ◽  
Biological Tissues ◽  
Projection Algorithm ◽  
Imaging Data ◽  
Curved Manifolds ◽  
Out Of Plane ◽  
Efficient Extraction ◽  
Binary Masking

The efficient extraction of local high-resolution content from massive amounts of imaging data remains a serious and unsolved problem in studies of complex biological tissues. Here we present DeepProjection, a trainable projection algorithm based on deep learning. This algorithm rapidly and robustly extracts image content contained in curved manifolds from time-lapse recorded 3D image stacks by binary masking of background content, stack by stack. The masks calculated for a given movie, when predicted, e.g., on fluorescent cell boundaries on one channel, can subsequently be applied to project other fluorescent channels from the same manifold. We apply DeepProjection to follow the dynamic movements of 2D-tissue sheets in embryonic development. We show that we can selectively project the amnioserosa cell sheet during dorsal closure in Drosophila melanogaster embryos and the periderm layer in the elongating zebrafish embryo while masking highly fluorescent out-of-plane artifacts.

scholarly journals DeepBacs: Bacterial image analysis using open-source deep learning approaches

2021 ◽  
Author(s):  
Christoph Spahn ◽  
Romain F. Laine ◽  
Pedro Matos Pereira ◽  
Estibaliz Gómez-de-Mariscal ◽  
Lucas von Chamier ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cell Biology ◽  
Bacterial Species ◽  
Super Resolution ◽  
Time Lapse ◽  
Growth Stages ◽  
Complex Data ◽  
Learning Approaches ◽  
Imaging Data ◽  
Microscopy Images

Deep Learning (DL) is rapidly changing the field of microscopy, allowing for efficient analysis of complex data while often outperforming classical algorithms. This revolution has led to a significant effort to create user-friendly tools allowing biomedical researchers with little background in computer sciences to use this technology effectively. Thus far, these approaches have mainly focused on analysing microscopy images from eukaryotic samples and are still underused in microbiology. In this work, we demonstrate how to use a range of state-of-the-art artificial neural-networks particularly suited for the analysis of bacterial microscopy images, using our recently developed ZeroCostDL4Mic platform. We showcase different DL approaches for segmenting bright field and fluorescence images of different bacterial species, use object detection to classify different growth stages in time-lapse imaging data, and carry out DL-assisted phenotypic profiling of antibiotic-treated cells. To also demonstrate the DL capacity to enhance low-phototoxicity live-cell microscopy, we showcase how image denoising can allow researchers to attain high-fidelity data in faster and longer imaging. Finally, artificial labelling of cell membranes and predictions of super-resolution images allow for accurate mapping of cell shape and intracellular targets. To aid in the training of novice users, we provide a purposefully-built database of training and testing data, enabling bacteriologists to quickly explore how to analyse their data through DL. We hope this lays a fertile ground for the efficient application of DL in microbiology and fosters the creation of novel tools for bacterial cell biology and antibiotic research.

Cleavage of Human Embryos: Options and Diversity

Acta Naturae ◽  
2016 ◽  
Vol 8 (3) ◽  
pp. 88-96
Author(s):  
Yu. K. Doronin ◽  
I. V. Senechkin ◽  
L. V. Hilkevich ◽  
M. A. Kurcer
Keyword(s):  
Time Lapse ◽  
Reproductive Technologies ◽  
Human Embryos ◽  
Imaging Data ◽  
Noninvasive Methods ◽  
Topographic Features ◽  
Time Parameters ◽  
Embryo Cleavage ◽  
Time Lapse Imaging ◽  
Developmental Dynamics

In order to estimate the diversity of embryo cleavage relatives to embryo progress (blastocyst formation), time-lapse imaging data of preimplantation human embryo development were used. This retrospective study is focused on the topographic features and time parameters of the cleavages, with particular emphasis on the lengths of cleavage cycles and the genealogy of blastomeres in 2- to 8-cell human embryos. We have found that all 4-cell human embryos have four developmental variants that are based on the sequence of appearance and orientation of cleavage planes during embryo cleavage from 2 to 4 blastomeres. Each variant of cleavage shows a strong correlation with further developmental dynamics of the embryos (different cleavage cycle characteristics as well as lengths of blastomere cycles). An analysis of the sequence of human blastomere divisions allowed us to postulate that the effects of zygotic determinants are eliminated as a result of cleavage, and that, thereafter, blastomeres acquire the ability of own syntheses, regulation, polarization, formation of functional contacts, and, finally, of specific differentiation. This data on the early development of human embryos obtained using noninvasive methods complements and extend our understanding of the embryogenesis of eutherian mammals and may be applied in the practice of reproductive technologies.

Using Deep Learning to Identify Cell and Particle in Live-Cell Time-lapse Images

2018 ◽  
Author(s):  
Hui-Jun Cheng ◽  
Chun-Yuan Lin ◽  
Cheng-Xian Wu ◽  
Che-Lun Hung ◽  
Wei-Hsiang Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Time Lapse ◽  
Live Cell

scholarly journals Time lapse synchrotron IR chemical imaging for observing the acclimation of a single algal cell to CO2 treatment

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ghazal Azarfar ◽  
Ebrahim Aboualizadeh ◽  
Simona Ratti ◽  
Camilla Olivieri ◽  
Alessandra Norici ◽  
...  
Keyword(s):  
Algal Cell ◽  
Principal Component ◽  
External Perturbation ◽  
Time Lapse ◽  
Chemical Imaging ◽  
Hyperspectral Data ◽  
Aqueous Environment ◽  
Ir Absorption ◽  
Imaging Data ◽  
Mid Infrared

AbstractAlgae are the main primary producers in aquatic environments and therefore of fundamental importance for the global ecosystem. Mid-infrared (IR) microspectroscopy is a non-invasive tool that allows in principle studying chemical composition on a single-cell level. For a long time, however, mid-infrared (IR) imaging of living algal cells in an aqueous environment has been a challenge due to the strong IR absorption of water. In this study, we employed multi-beam synchrotron radiation to measure time-resolved IR hyperspectral images of individual Thalassiosira weissflogii cells in water in the course of acclimation to an abrupt change of CO2 availability (from 390 to 5000 ppm and vice versa) over 75 min. We used a previously developed algorithm to correct sinusoidal interference fringes from IR hyperspectral imaging data. After preprocessing and fringe correction of the hyperspectral data, principal component analysis (PCA) was performed to assess the spatial distribution of organic pools within the algal cells. Through the analysis of 200,000 spectra, we were able to identify compositional modifications associated with CO2 treatment. PCA revealed changes in the carbohydrate pool (1200–950 cm$$^{-1}$$ - 1 ), lipids (1740, 2852, 2922 cm$$^{-1}$$ - 1 ), and nucleic acid (1160 and 1201 cm$$^{-1}$$ - 1 ) as the major response of exposure to elevated CO2 concentrations. Our results show a local metabolism response to this external perturbation.

scholarly journals Unsupervised content-preserving transformation for optical microscopy

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Xinyang Li ◽  
Guoxun Zhang ◽  
Hui Qiao ◽  
Feng Bao ◽  
Yue Deng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Optical Microscopy ◽  
Training Data ◽  
Fluorescence Labeling ◽  
Imaging Data ◽  
Image Transformation ◽  
General Applicability ◽  
Data Annotation ◽  
Biomedical Image ◽  
Wide Range

AbstractThe development of deep learning and open access to a substantial collection of imaging data together provide a potential solution for computational image transformation, which is gradually changing the landscape of optical imaging and biomedical research. However, current implementations of deep learning usually operate in a supervised manner, and their reliance on laborious and error-prone data annotation procedures remains a barrier to more general applicability. Here, we propose an unsupervised image transformation to facilitate the utilization of deep learning for optical microscopy, even in some cases in which supervised models cannot be applied. Through the introduction of a saliency constraint, the unsupervised model, named Unsupervised content-preserving Transformation for Optical Microscopy (UTOM), can learn the mapping between two image domains without requiring paired training data while avoiding distortions of the image content. UTOM shows promising performance in a wide range of biomedical image transformation tasks, including in silico histological staining, fluorescence image restoration, and virtual fluorescence labeling. Quantitative evaluations reveal that UTOM achieves stable and high-fidelity image transformations across different imaging conditions and modalities. We anticipate that our framework will encourage a paradigm shift in training neural networks and enable more applications of artificial intelligence in biomedical imaging.

Sign in / Sign up

Export Citation Format

Share Document