scholarly journals Verification of an algorithm for actin tail detection of subviral particles by comparison with expert validated data

2021 ◽  
Vol 7 (2) ◽  
pp. 117-120
Author(s):  
Jan Chowanietz ◽  
Andreas Rausch ◽  
Thomas Schanze
Keyword(s):  
Image Sequences ◽  
Marburg Virus ◽  
Particle Movement ◽  
Fluorescence Image ◽  
Particle Speed ◽  
Subviral Particle ◽  
Subviral Particles

Abstract The locomotion of subviral particles of Marburg virus has been shown to be primarily actin based. For this work, a virologist selected 14 subviral particles that show actin tails in fluorescence image sequences. Using the tracked coordinates, examination areas around these subviral particles are defined. The brightness of within the examination area behind the subviral particle is analysed. In addition, the speed of the particle in each frame is calculated to investigate potential correlations between actin activity and particle speed. The results show that actin tracks can be automatically detected and analysed. First hints of a correlation between subviral particle movement and actin activity could be gathered with the presented actin tail quantifier.

scholarly journals Fractal Dimensions of Subviral Particle Movement

2018 ◽  
Vol 4 (1) ◽  
pp. 79-82 ◽  
Author(s):  
Andreas Rausch ◽  
Thomas Schanze
Keyword(s):  
Virus Disease ◽  
Fractal Dimensions ◽  
Real Data ◽  
Marburg Virus ◽  
Virus Infections ◽  
Fluorescence Image ◽  
Good Potential ◽  
Infected Cells ◽  
Subviral Particle ◽  
Subviral Particles

AbstractThe development of new medicines against virus infections like the Marburg virus disease requires an accurate knowledge of the respective pathogens. Conventionally, this process is very time expensive. In cooperation with the Virology of the Philipps-University in Marburg an automatic tracking algorithm for subviral particles in fluorescence image sequences was developed and programmed. To expand the benefit for the pharmaceutical researchers, also the trackevaluations need to be widely automated. In this work, a new parameterizing-method facing the fractal dimensions of spline interpolated subviral particle tracks is presented and tested with simulated and real data. The results reveal a good potential to classify tracks and, thus, types of subviral particles in infected cells.

scholarly journals Deep learning-based recognition of cell structures in fluorescence microscopy sequences with respect to their morphology on cells infected with Marburg virus

2020 ◽  
Vol 6 (3) ◽  
pp. 501-504
Author(s):  
Dennis Schmidt ◽  
Andreas Rausch ◽  
Thomas Schanze
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Infected Cell ◽  
Network Architecture ◽  
Image Sequences ◽  
Marburg Virus ◽  
Microscopic Image ◽  
Cell Structures ◽  
Fast Recognition ◽  
Subviral Particles

AbstractThe Institute of Virology at the Philipps-Universität Marburg is currently researching possible drugs to combat the Marburg virus. This involves classifying cell structures based on fluoroscopic microscopic image sequences. Conventionally, membranes of cells must be marked for better analysis, which is time consuming. In this work, an approach is presented to identify cell structures in images that are marked for subviral particles. It could be shown that there is a correlation between the distribution of subviral particles in an infected cell and the position of the cell’s structures. The segmentation is performed with a "Mask-R-CNN" algorithm, presented in this work. The model (a region-based convolutional neural network) is applied to enable a robust and fast recognition of cell structures. Furthermore, the network architecture is described. The proposed method is tested on data evaluated by experts. The results show a high potential and demonstrate that the method is suitable.

scholarly journals Visualization and Parametrization of the Motion Behaviour of Subviral Particles

2018 ◽  
Vol 4 (1) ◽  
pp. 359-362
Author(s):  
Michelle Kaak ◽  
Andreas Rausch ◽  
Dennis Müller ◽  
Thomas Schanze
Keyword(s):  
Real Data ◽  
Hemorrhagic Fever ◽  
Marburg Virus ◽  
Particle Analysis ◽  
Motion Patterns ◽  
Microscopy Technique ◽  
Accurate Knowledge ◽  
Good Potential ◽  
Subviral Particle ◽  
Subviral Particles

AbstractThe development of a drug against pathogens of hemorrhagic fever, like the Marburg virus, is a great challenge. Therefore, accurate knowledge of the properties of subviral particles in the host cell must be obtained. The base for subviral particle analysis is a special fluorescence microscopy technique. In order to automate and visualize the subviral particles’ motion patterns, previously a tracking algorithm was developed. In this article a new algorithm to parameterize and visualize the achieved particle tracks is introduced. A good potential for a fast data recognition is shown, with constantly respecting a high usability for pharmaceutical researchers. This algorithm was tested on both simulated and real data and provides reproducible results.

scholarly journals Improving subviral particle tracks in fluoroscopic image sequences by global motion compensation

2017 ◽  
Vol 3 (2) ◽  
pp. 211-215
Author(s):  
Andreas Rausch ◽  
Thomas Schanze
Keyword(s):  
Modern Medicine ◽  
Image Sequences ◽  
Global Motion ◽  
Great Ability ◽  
Medicine Research ◽  
Detection And Tracking ◽  
Linear Assignment Problem ◽  
Cross Correlations ◽  
Subviral Particle ◽  
Linear Assignment

AbstractAutomatic detection and tracking of subviral particles in image sequences is an indispensable supportive method for modern medicine research programs. This paper describes the development of a highly adaptable camera-to-world system motion invariant tracking algorithm. A translation compensation is obtained by cross correlations. Particles are detected by an implemented existing algorithm. The detected particles are linked by solving a Linear Assignment Problem. For highly stable results the tracks are improved by Kalman filtering. The algorithm is tested on simulated sequences. The results show a great ability for stable tracking.

scholarly journals Improvement of a subviral particle tracker by the use of a LAP-Kalman-algorithm

2016 ◽  
Vol 2 (1) ◽  
pp. 415-418 ◽  
Author(s):  
Andreas Rausch ◽  
Dennis Müller ◽  
Thomas Schanze
Keyword(s):  
Image Sequences ◽  
Automated Detection ◽  
Problem Solver ◽  
Simulated Image ◽  
Original Algorithm ◽  
Detection And Tracking ◽  
Linear Assignment Problem ◽  
Particle Tracking Algorithm ◽  
Subviral Particle ◽  
Linear Assignment

AbstractAutomated detection and tracking of subviral particles is a promising method to obtain insights in complicated virus-cell interactions. This paper describes the implementation of a linear assignment problem solver and a Kalman-filter in an existing particle tracking algorithm. Two different simulated image sequences are used for the evaluation of the algorithms. Tracking and detection results of the new implemented solver are compared to the results of the original algorithm. The improved algorithm is able to improve the results by closing gaps in the particle tracks.

scholarly journals Estimation of accuracy loss by training a deep-learning-based cell organelle recognition software using full dataset and a reduced dataset containing only subviral particle distribution information

2021 ◽  
Vol 7 (2) ◽  
pp. 183-186
Author(s):  
Nils Busch ◽  
Andreas Rausch ◽  
Thomas Schanze
Keyword(s):  
Deep Learning ◽  
Particle Distribution ◽  
Cell Organelle ◽  
Cell Organelles ◽  
Full Dataset ◽  
Infected Cells ◽  
Recognition Software ◽  
Subviral Particle ◽  
Microscopy Images ◽  
Subviral Particles

Abstract In collaboration with the Institute of Virology, Philipps University, Marburg, a deep-learning-based method that recognizes and classifies cell organelles based on the distribution of subviral particles in fluorescence microscopy images of virus-infected cells has been further developed. In this work a method to recognize cell organelles by means of partial image information is extended. The focus is on investigating loss of accuracy by only providing information about subviral particles and not all cell organelles to an adopted Mask-R convolutional neural network. Our results show that the subviral particle distribution holds information about the cell morphology, thus making it possible to use it for cell organelle-labelling.

scholarly journals Automatic Classification of the Movements of Directed and Undirected Subviral Particles

2020 ◽  
Vol 6 (3) ◽  
pp. 147-150
Author(s):  
Michelle Kaak ◽  
Andreas Rausch ◽  
Thomas Schanze
Keyword(s):  
Ebola Virus ◽  
Hemorrhagic Fever ◽  
Research Process ◽  
Image Sequences ◽  
Microscopic Image ◽  
Passive Transport ◽  
Mean Squared Displacement ◽  
Motion Characteristics ◽  
Subviral Particles

AbstractThe development of drugs against pathogens that cause hemorrhagic fever, such as Marburg and Ebola virus, requires researchers to gather much information about the virus. The accelerating of the research process is of great interest; therefore a new algorithm was developed to analyze intracellular processes. The algorithm will classify the motion characteristics of subviral particles in fluorescence microscopic image sequences of Ebola or Marburg virusinfected cells. The classification is based on the calculation of mean squared displacement. The results look promising to distinguish different particle tracks in active and passive transport. The paper ends with a discussion.

Sign in / Sign up

Export Citation Format

Share Document