scholarly journals Dual Dictionary Learning for Cell Segmentation in Bright-field Microscopy Images

2016 ◽  
Vol 22 (3) ◽  
pp. 21-29
Author(s):  
Gyuhyun Lee ◽  
Jeong Wonki ◽  
Tran Minh Quan
Keyword(s):  
Dictionary Learning ◽  
Cell Segmentation ◽  
Bright Field ◽  
Bright Field Microscopy ◽  
Microscopy Images

scholarly journals YeastNet: Deep-Learning-Enabled Accurate Segmentation of Budding Yeast Cells in Bright-Field Microscopy

2021 ◽  
Vol 11 (6) ◽  
pp. 2692
Author(s):  
Danny Salem ◽  
Yifeng Li ◽  
Pengcheng Xi ◽  
Hilary Phenix ◽  
Miroslava Cuperlovic-Culf ◽  
...  
Keyword(s):  
Deep Learning ◽  
Live Cell ◽  
Cell Labeling ◽  
Yeast Cells ◽  
Knowledge Generation ◽  
Cell Segmentation ◽  
Bright Field ◽  
Convolutional Network ◽  
Bright Field Microscopy ◽  
Microscopy Images

Accurate and efficient segmentation of live-cell images is critical in maximizing data extraction and knowledge generation from high-throughput biology experiments. Despite recent development of deep-learning tools for biomedical imaging applications, great demand for automated segmentation tools for high-resolution live-cell microscopy images remains in order to accelerate the analysis. YeastNet dramatically improves the performance of the non-trainable classic algorithm, and performs considerably better than the current state-of-the-art yeast-cell segmentation tools. We have designed and trained a U-Net convolutional network (named YeastNet) to conduct semantic segmentation on bright-field microscopy images and generate segmentation masks for cell labeling and tracking. YeastNet enables accurate automatic segmentation and tracking of yeast cells in biomedical applications. YeastNet is freely provided with model weights as a Python package on GitHub.

scholarly journals YeastNet: Deep Learning Enabled Accurate Segmentation of Budding Yeast Cells in Bright-field Microscopy

2020 ◽  
Author(s):  
Danny Salem ◽  
Yifeng Li ◽  
Pengcheng Xi ◽  
Hilary Phenix ◽  
Miroslava Cuperlovic-Culf ◽  
...  
Keyword(s):  
Deep Learning ◽  
Live Cell ◽  
Yeast Cells ◽  
Knowledge Generation ◽  
Cell Segmentation ◽  
Cell Labelling ◽  
Bright Field ◽  
Convolutional Network ◽  
Bright Field Microscopy ◽  
Microscopy Images

Accurate and efficient segmentation of live-cell images is critical in maximising data extraction and knowledge generation from high-throughput biology experiments. Despite recent development of deep learning tools for biomedical imaging applications, great demand for automated segmentation tools for high-resolution live-cell microscopy images remains in order to accelerate the analysis. YeastNet dramatically improves the performance of non-trainable classic algorithm, and performs considerably better than the current state-of-the-art yeast cell segmentation tools. We have designed and trained a U-Net convolutional network (named YeastNet) to conduct semantic segmentation on bright-field microscopy images and generate segmentation masks for cell labelling and tracking. YeastNet enables accurate automatic segmentation and tracking of yeast cells in biomedical applications. YeastNet is freely provided with model weights as a Python package on GitHub. https://github.com/kaernlab/YeastNet

scholarly journals Quasi-spectral characterization of intracellular regions in bright-field light microscopy images

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Kirill Lonhus ◽  
Renata Rychtáriková ◽  
Ganna Platonova ◽  
Dalibor Štys
Keyword(s):  
Cell Structure ◽  
A Priori ◽  
Semantic Segmentation ◽  
Bright Field ◽  
Model Free ◽  
Bright Field Microscopy ◽  
Priori Information ◽  
The Right ◽  
Microscopy Images

Abstract Investigation of cell structure is hardly imaginable without bright-field microscopy. Numerous modifications such as depth-wise scanning or videoenhancement make this method being state-of-the-art. This raises a question what maximal information can be extracted from ordinary (but well acquired) bright-field images in a model-free way. Here we introduce a method of a physically correct extraction of features for each pixel when these features resemble a transparency spectrum. The method is compatible with existent ordinary bright-field microscopes and requires mathematically sophisticated data processing. Unsupervised clustering of the spectra yields reasonable semantic segmentation of unstained living cells without any a priori information about their structures. Despite the lack of reference data (to prove strictly that the proposed feature vectors coincide with transparency), we believe that this method is the right approach to an intracellular (semi)quantitative and qualitative chemical analysis.

scholarly journals Identification of individual cells from z-stacks of bright-field microscopy images

2018 ◽  
Vol 8 (1) ◽  
Author(s):  
Jean-Baptiste Lugagne ◽  
Srajan Jain ◽  
Pierre Ivanovitch ◽  
Zacchary Ben Meriem ◽  
Clément Vulin ◽  
...  
Keyword(s):  
Bright Field ◽  
Bright Field Microscopy ◽  
Microscopy Images

scholarly journals Simulation of bright‐field microscopy images depicting pap‐smear specimen

2015 ◽  
Vol 87 (3) ◽  
pp. 212-226 ◽  
Author(s):  
Patrik Malm ◽  
Anders Brun ◽  
Ewert Bengtsson
Keyword(s):  
Pap Smear ◽  
Bright Field ◽  
Bright Field Microscopy ◽  
Microscopy Images

scholarly journals Development of an open source program to identify the size of objects using bright-field microscopy - an automated calibration tool

2021 ◽  
Author(s):  
Gerard Glowacki ◽  
Alexis Gkantiragas ◽  
Brooke Brett-Holt ◽  
Peter He ◽  
Daniel Mihalik
Keyword(s):  
Light Microscopy ◽  
Open Source ◽  
Object Identification ◽  
Bright Field ◽  
Open Source Program ◽  
Source Program ◽  
Bright Field Microscopy ◽  
Microscopy Techniques ◽  
Calibration Tool ◽  
Microscopy Images

In light microscopy, eyepiece graticules are commonly used to gauge the size of objects at the micron scale. While this is a relatively simple tool to use, not all microscopes possess this feature. Furthermore, calibrating an eyepiece graticule with a stage micrometer can be time-consuming, particularly for inexperienced microscopists. Similarly, calculating the size of individual objects may also take some time. We present an open-source program to determine the size of objects under a microscope using Python and OpenCV. Taking photos of a stage micrometer under a microscope, we identify gradations on the micrometer and calculate the distance between lines on the micrometer in pixels. From this, we can infer the size of objects from bright-field microscopy images. We believe this will improve access to quantitative microscopy techniques and increase the speed at which samples may be analyzed by light microscopy. Future studies may aim to integrate this with machine learning for object identification

Sign in / Sign up

Export Citation Format

Share Document