Improved automatic detection of herpesvirus secondary envelopment stages in electron microscopy by augmenting training data with synthetic labelled images generated by a generative adversarial network

Devan, Kavitha Shaga; Walther, Paul; Einem, Jens von; Ropinski, Timo; Kestler, Hans A.; Read, Clarissa

doi:10.1111/cmi.13280

Cited by 10 publications

(11 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although current data (Read et al, 2019;Schauflinger et al, 2013;Shaga Devan et al, 2021;Taisne et al, 2019) have mainly described that HCMV capsids individually bud into small vesicles in the AC (Figure 1a,b), several studies have described large vesicles filled with virus particles (Bughio et al, 2013;Fraile-Ramos et al, 2010;Momtaz et al, 2021;Schauflinger et al, 2011;Severi et al, 1988).…”

Section: H CMV Us E S Mv Ibs For Intermit Tent Bulk Rele a S E Of Vir...mentioning

confidence: 95%

The unconventional way out—Egress of HCMV through multiviral bodies

Wedemann

Flomm

Bosse

2022

Molecular Microbiology

View full text Add to dashboard Cite

Human cytomegalovirus (HCMV) is a ubiquitous herpesvirus and the leading cause of congenital disabilities as well as a significant cause of disease in immunocompromised patients. The envelopment and egress of HCMV particles is an essential step of the viral life cycle as it determines viral spread and potentially tropism. Here we review the current literature on HCMV envelopment and egress with a particular focus on the role of virus‐containing multivesicular body‐like vesicles for virus egress and spread. We discuss the difficulties of determining the cellular provenance of these structures in light of viral redistribution of cellular marker proteins and provide potential paths to illuminate their genesis. Finally, we discuss how divergent egress pathways could result in virions of different tropisms.

show abstract

Section: H CMV Us E S Mv Ibs For Intermit Tent Bulk Rele a S E Of Vir...mentioning

confidence: 95%

The unconventional way out—Egress of HCMV through multiviral bodies

Wedemann

Flomm

Bosse

2022

Molecular Microbiology

View full text Add to dashboard Cite

show abstract

“…al. [ 43 ] provides another example of a GAN implementation for limited biological dataset augmentation. The authors of this work use GAN to increase the size of a transmission electron microscope image dataset.…”

Section: Related Workmentioning

confidence: 99%

Generative Adversarial Networks for Morphological–Temporal Classification of Stem Cell Images

Witmer

Bhanu

2021

Sensors

View full text Add to dashboard Cite

Frequently, neural network training involving biological images suffers from a lack of data, resulting in inefficient network learning. This issue stems from limitations in terms of time, resources, and difficulty in cellular experimentation and data collection. For example, when performing experimental analysis, it may be necessary for the researcher to use most of their data for testing, as opposed to model training. Therefore, the goal of this paper is to perform dataset augmentation using generative adversarial networks (GAN) to increase the classification accuracy of deep convolutional neural networks (CNN) trained on induced pluripotent stem cell microscopy images. The main challenges are: 1. modeling complex data using GAN and 2. training neural networks on augmented datasets that contain generated data. To address these challenges, a temporally constrained, hierarchical classification scheme that exploits domain knowledge is employed for model learning. First, image patches of cell colonies from gray-scale microscopy images are generated using GAN, and then these images are added to the real dataset and used to address class imbalances at multiple stages of training. Overall, a 2% increase in both true positive rate and F1-score is observed using this method as compared to a straightforward, imbalanced classification network, with some greater improvements on a classwise basis. This work demonstrates that synergistic model design involving domain knowledge is key for biological image analysis and improves model learning in high-throughput scenarios.

show abstract

“…LSCT particles present different particle sizes under the action of mechanical force, which directly affects its properties when it is undertaken as concrete building materials [28,29]. Among the analytical methods for studying LSCT particles, SEM can observe the microscopic morphology and particle size of tailing particles, and X-ray spectroscopy can obtain In this study, the particle morphology and PSD of LSCT are studied, and CNN and SEM images of LSCT are combined to identify and analyse different morphological features and particle sizes, aimed at providing reference for analysis of particle size and performance of LSCT under the action of mechanical force [30,31].…”

Section: Particle Detection Of Lsct Based On Image Processingmentioning

confidence: 99%

Image Analysis Technology in the Detection of Particle Size Distribution and the Activity Effect of Low‐Silicon Copper Tailings

Zhao

Liu

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

To speed up the comprehensive utilization and treatment of copper tailings, the digital image processing technology is proposed in this study to detect the low-silicon copper tailings (LSCT) using a scanning electron microscope (SEM), and the particle size distribution (PSD) and the activity of LSCT are analysed under the action of mechanical force. Firstly, the current status and application of copper tailings are introduced, and the influence of the particle size of LSCT on its practical application performance is explained. Secondly, the LSCT SEM image target recognition model is designed based on the convolutional neural network (CNN), and the model parameters and the reference CNN are selected. Finally, the experimental process is designed, a SEM image data set of LSCT is prepared, the model is trained through the training set, and the image recognition test is performed on the produced data set. The experimental results show that when the number of iterations of the CNN is 10, the accuracy of model recognition can be guaranteed. After the action of mechanical force, the PSD of LSCT is mainly concentrated at 1 μm~100 μm; that around 1.4 μm~10 μm is the largest, and the PSD of LSCT around 1.4 μm increases with the increase of action time of mechanical force, but the PSD of the LSCT begins to increase when the grinding time exceeds 150 minutes, and the activity of LSCT reaches the maximum (75.545%) at 150 minutes. The average accuracy of SEM image detection of the model is 86.97%, and the model based on DenseNet shows better recognition accuracy than other models. This study provides a reference for analysing the PSD of LSCT.

show abstract

Improved automatic detection of herpesvirus secondary envelopment stages in electron microscopy by augmenting training data with synthetic labelled images generated by a generative adversarial network

Cited by 10 publications

References 52 publications

The unconventional way out—Egress of HCMV through multiviral bodies

The unconventional way out—Egress of HCMV through multiviral bodies

Generative Adversarial Networks for Morphological–Temporal Classification of Stem Cell Images

Image Analysis Technology in the Detection of Particle Size Distribution and the Activity Effect of Low‐Silicon Copper Tailings

Contact Info

Product

Resources

About