scholarly journals Automatic cell segmentation from brightfield microscopy images of pseudohyphal cell-aggregates

2019 ◽  
Author(s):  
Valdinei Luís Belini ◽  
Orides Morandin Junior ◽  
Sandra Regina Ceccato-Antonini ◽  
Philipp Wiedemann ◽  
Hajo Suhr
Keyword(s):  
Imaging System ◽  
Statistical Significance ◽  
Automatic Segmentation ◽  
Cell Counting ◽  
Cell Segmentation ◽  
Simultaneous Occurrence ◽  
Watershed Algorithm ◽  
Cell Aggregates ◽  
Brightfield Microscopy ◽  
Microscopy Images

Abstract Background: The automatic segmentation of pseudohyphal cell-aggregates from brightfield microscopy images for counting forming cells is a challenging task due to the heterogeneous optical appearances of the cells as they may lie on different focal planes. The current cell counting method is based on a time-consuming manual counting of stained cells on a hemocytometer and in most cases, it represents estimates of low statistical significance due to the effort needed to prepare and analyze many samples. In this work, we evaluated the effectiveness of a marker-controlled watershed algorithm for automatic segmentation of pseudohyphae from brightfield microscopic images. The cell heterogeneity problem was addressed by processing intracellular contents of focused and defocused cells to extract initial foreground markers for the watershed method. By properly segmenting cells of different classes within a pseudohypha allows increasing the number of cells analyzed contributing thus to more reliable estimates. To facilitate the evaluation of the proposal by acquiring images containing a diversity of cells´ appearances, we utilized in situ microscopy, an imaging system used to capture images directly from suspensions.Results: The performance of the method was evaluated on 120 portraits of a yeast exhibiting a diversity of pseudohyphal morphologies. Automatic results were compared with manual references obtained by visual inspection of the images. Despite the simultaneous occurrence of a representative mixture of focused, over-, and under-focused cells, the method produced robust results with an average segmentation sensitivity, specificity, and accuracy of 76%, 89%, and 76%, respectively. On average, each microscopic image was processed within 3 s.Conclusions: Our approach was capable to segment pseudohyphae formed by cells exhibiting a large diversity of appearances. The application of a marker-controlled watershed algorithm as a simple, yet effective technique for segmenting pseudohyphae demonstrated satisfactory overall performance to support automated analysis of pseudohyphal cell-aggregates from brightfield images.

Automatic segmentation of adherent biological cell boundaries and nuclei from brightfield microscopy images

2011 ◽  
Vol 23 (4) ◽  
pp. 607-621 ◽  
Author(s):  
Rehan Ali ◽  
Mark Gooding ◽  
Tünde Szilágyi ◽  
Borivoj Vojnovic ◽  
Martin Christlieb ◽  
...  
Keyword(s):  
Automatic Segmentation ◽  
Biological Cell ◽  
Brightfield Microscopy ◽  
Microscopy Images

scholarly journals A deep convolutional neural network approach for astrocyte detection

2017 ◽  
Author(s):  
Ilida Suleymanova ◽  
Tamas Balassa ◽  
Sushil Tripathi ◽  
Csaba Molnar ◽  
Mart Saarma ◽  
...  
Keyword(s):  
Image Analysis ◽  
Automatic Segmentation ◽  
Brain Regions ◽  
Cell Counting ◽  
Detection Accuracy ◽  
Cell Detection ◽  
Strong Positive Correlation ◽  
Deep Convolutional Neural Networks ◽  
Neural Network Approach ◽  
Microscopy Images

AbstractAstrocytes are involved in brain pathologies such as trauma or stroke, neurodegenerative disorders like Alzheimer’s and Parkinson’s disease, chronic pain, and many others. Determining cell density and timing of morphological and biochemical changes is important for a proper understanding of the role of astrocytes in physiological and pathological conditions. One of the most important of such analyses is astrocytes count within a complex tissue environment in microscopy images. The most widely used approaches for the quantification of microscopy images data are either manual stereological cell counting or semi-automatic segmentation techniques. Detecting astrocytes automatically is a highly challenging computational task, for which we currently lack efficient image analysis tools. In this study, we developed a fast and fully automated software that assesses the number of astrocytes using Deep Convolutional Neural Networks (DCNN). The method highly outperforms state-of-the-art image analysis and machine learning methods and provides detection accuracy and precision comparable to that of human experts. Additionally, the runtime of cell detection is significantly less than other three analyzed computational methods, and it is faster than human observers by orders of magnitude. We applied DCNN-based method to examine the number of astrocytes in different brain regions of rats with opioid-induced hyperalgesia/tolerance (OIH/OIT) as morphine tolerance is believed to activate glial cells in the brain. We observed strong positive correlation between manual cell detection and DCNN-based analysis method for counting astrocytes in the brains of experimental animals.

ASSESSMENT OF STATISTICAL SIGNIFICANCE OF HISTORIC DANUBE FLOODS

2020 ◽  
Author(s):  
Stevan Prohaska ◽  
◽  
Aleksandra Ilić ◽  
Pavla Pekarova ◽  
◽  
...  
Keyword(s):  
Middle Ages ◽  
Linear Trend ◽  
Statistical Significance ◽  
Danube River ◽  
Exceedance Probability ◽  
Simultaneous Occurrence ◽  
Flood Wave ◽  
Probability Of Occurrence ◽  
Comprehensive Method ◽  
Flood Hydrograph

Data on historic floods along the Danube River exist since the year 1012. In the Middle Ages, floods were estimated based on historical documents, including original handwritten notes, newspaper articles, chronicles, formal letters, books, maps and photographs. From 1500 until the beginning of organized water regime observations, floods were hydraulically reconstructed based on water marks on old buildings in cities along the Danube (Passau, Melk, Emmersdorf an der Donau, Spilz, Schonbuhen and Bratislava). The paper presents a procedure for assessing the statistical significance of registered historic floods using a comprehensive method for defining theoretical flood hydrographs at hydrological stations. The approach is based on correlation analysis of two basic flood hydrograph parameters – maximum hydrograph ordinate (peak) and flood wave volume. The PROIL model is used to define the probability of simultaneous occurrence of these parameters. It defines the exceedance probability of two random variables, in the specific case two hydrograph parameters of the form: P{Qmax more equal to qmax,p)∩(Wmax more equal to wmax,p)} = P (1) where: Qmax – maximum hydrograph ordinate (peak); qmax,p – maximum discharge of the probability of occurrence p; Wmax – maximum hydrograph volume; wmax,p – maximum flood wave volume of the probability of occurrence p; P – exceedance probability. Spatial positions of the lines of exceedance of two flood hydrograph parameters and the empirical points of the corresponding parameters of the considered historic flood in the correlation field Qmax - Wmax, allow direct assessment of the exceedance probability of a historic flood, or its statistical significance. The proposed procedure was applied in practice to assess the statistical significance of the biggest floods registered along the Danube in the sector from its mouth to the Djerdap 1 Dam. The linear trend in the time-series of maximum annual flows at a representative hydrological station and the frequency of historic floods in the considered sector of the Danube are discussed at the end of the paper.

scholarly journals Deeply-supervised density regression for automatic cell counting in microscopy images

2021 ◽  
Vol 68 ◽  
pp. 101892
Author(s):  
Shenghua He ◽  
Kyaw Thu Minn ◽  
Lilianna Solnica-Krezel ◽  
Mark A. Anastasio ◽  
Hua Li
Keyword(s):  
Cell Counting ◽  
Density Regression ◽  
Microscopy Images

SAU-Net: A Unified Network for Cell Counting in 2D and 3D Microscopy Images

2021 ◽  
pp. 1-1
Author(s):  
Yue Guo ◽  
Oleh Krupa ◽  
Jason Stein ◽  
Guorong Wu ◽  
Ashok Krishnamurthy
Keyword(s):  
Cell Counting ◽  
3D Microscopy ◽  
2D And 3D ◽  
Microscopy Images

A hybrid 3D watershed algorithm incorporating gradient cues and object models for automatic segmentation of nuclei in confocal image stacks

Cytometry ◽  
2003 ◽  
Vol 56A (1) ◽  
pp. 23-36 ◽  
Author(s):  
Gang Lin ◽  
Umesh Adiga ◽  
Kathy Olson ◽  
John F. Guzowski ◽  
Carol A. Barnes ◽  
...  
Keyword(s):  
Automatic Segmentation ◽  
Watershed Algorithm ◽  
Confocal Image ◽  
Object Models

scholarly journals Automatic segmentation of fluorescence lifetime microscopy images of cells using multiresolution community detection-a first study

2013 ◽  
Vol 253 (1) ◽  
pp. 54-64 ◽  
Author(s):  
D. HU ◽  
P. SARDER ◽  
P. RONHOVDE ◽  
S. ORTHAUS ◽  
S. ACHILEFU ◽  
...  
Keyword(s):  
Community Detection ◽  
Fluorescence Lifetime ◽  
Automatic Segmentation ◽  
Microscopy Images

A Robust Generic Method for Grid Detection in White Light Microscopy Malassez Blade Images in the Context of Cell Counting

2014 ◽  
Vol 21 (1) ◽  
pp. 239-248 ◽  
Author(s):  
Ambroise Marin ◽  
Emmanuel Denimal ◽  
Stéphane Guyot ◽  
Ludovic Journaux ◽  
Paul Molin
Keyword(s):  
Image Processing ◽  
Fourier Transform ◽  
Light Microscopy ◽  
White Light ◽  
Hough Transform ◽  
High Variability ◽  
Cell Counting ◽  
Cell Segmentation ◽  
Primary Measurement

AbstractIn biology, cell counting is a primary measurement and it is usually performed manually using hemocytometers such as Malassez blades. This work is tedious and can be automated using image processing. An algorithm based on Fourier transform filtering and the Hough transform was developed for Malassez blade grid extraction. This facilitates cell segmentation and counting within the grid. For the present work, a set of 137 images with high variability was processed. Grids were accurately detected in 98% of these images.

Sign in / Sign up

Export Citation Format

Share Document