M. poor quality image due to unbalanced lighting

M.
Ali Akber Dewan et al. (2014) proposed a frame work for segmenting nuclei’s. The
proposed method uses intensity, convexity and nuclei for automatic segmentation
of nuclei in phase contrast images. Separation of particular nuclei from the
background is the process of segmentation. Phase – contrast images are commonly
used in live cell microscopy, where there is high magnification is needed and
also when there is a colorless specimen is involved or when information’s are
so good that the color does not occur well. Using phase-contrast images has
limitations, where the end results gives poor quality image due to unbalanced
lighting conditions therefore to overcome this limitations the frame work for
segmenting nuclei has been proposed. There are three stages in the proposed
frame work first, in a phase-contrast image normally appears as a dark region
surrounded by a bright halo artifact. Second, in a two-dimensional microscopic
image, the nucleus is nearly convex. Third, the texture of a nucleus is different
from that associated with dirt, dust or other imaging artifacts in a cell image.
These three stages help to take over the intensity, convexity, and texture of
the nucleus for automatic segmentation of the nuclei in a phase-contrast image.
By using these three methods the following problem has been overtaken
low-contrast, non-uniform illumination, shading and imaging artifacts and noise
in the image. A top-hat ?lter has been used to remove the non-uniform illumination
and shading artifacts as well as to increase the contrast in the image, this
process happens in the first stage. In the second stage distance transformation
and the h-maxima transformation have been used to follow the information of
intensity and the convexity of the nucleus. There are chances of some false
segmentation due to imaging artifacts, prolonged cell cytoplasm or noise in the
second stage, to overcome the false segmentation problem, the Haralick-feature-based
nuclei texture analysis has been used in the third stage. The result shows the incorporation
of the texture information in conjunction with that of the intensity and
convexity of the nucleus further improves the accuracy of the segmentation.

Fuyong
Xing et al (2015) proposed a novel nucleus segmentation framework using deep
convolutional neural network and selection-based sparse shape model. For shape
initialization, deep CNN has been used. A novel segmentation
algorithm is exploited to separate individual nuclei combining a robust
selection-based sparse shape model and a local repulsive deformable model.
The
proposed method is general enough to perform well across multiple scenarios and
the proposed algorithm has been tested on three large scale pathology images
dataset.

Best services for writing your paper according to Trustpilot

Premium Partner
From $18.00 per page
4,8 / 5
4,80
Writers Experience
4,80
Delivery
4,90
Support
4,70
Price
Recommended Service
From $13.90 per page
4,6 / 5
4,70
Writers Experience
4,70
Delivery
4,60
Support
4,60
Price
From $20.00 per page
4,5 / 5
4,80
Writers Experience
4,50
Delivery
4,40
Support
4,10
Price
* All Partners were chosen among 50+ writing services by our Customer Satisfaction Team

Brette L. Luck et.al
(2005) proposed an automated nuclear segmentation algorithm to analyze confocal
re?ectance images of cervical epithelium. The model includes the system and tissue
properties of ?ber pattern, ?ber blur, pixel value range of the imaged tissue,
and nuclear size distribution within tissue. The results gives good progress
towards this goal of automatic segmentation—if the signal-to-background ratio
is above 0.74, 90% of nuclei compared to hand segmentation with a less amount
of false positive objects per frame when it comes for automatic segmentation
algorithms.