Corpus ID: 37342780

Image Segmentation to Distinguish Between Overlapping Human Chromosomes

@article{Hu2017ImageST,
  title={Image Segmentation to Distinguish Between Overlapping Human Chromosomes},
  author={R. Lily Hu and Jeremy Karnowski and Ross Fadely and Jean-Patrick Pommier},
  journal={ArXiv},
  year={2017},
  volume={abs/1712.07639}
}
In medicine, visualizing chromosomes is important for medical diagnostics, drug development, and biomedical research. Unfortunately, chromosomes often overlap and it is necessary to identify and distinguish between the overlapping chromosomes. A segmentation solution that is fast and automated will enable scaling of cost effective medicine and biomedical research. We apply neural network-based image segmentation to the problem of distinguishing between partially overlapping DNA chromosomes. A… Expand
Segmentation of overlapping chromosome images using U-Net with improved dilated convolutions
TLDR
It is demonstrated that the improved dilated convolutions can be used for the automatic segmentation of overlapping chromosome images and are suitable as general neural network operations to replace standard convolutions in any network. Expand
ChromSeg: Two-Stage Framework for Overlapping Chromosome Segmentation and Reconstruction
TLDR
This project implemented a fully automatic method, called ChromSeg, which efficiently separates crossing-overlap chromosomes from metaphase cell images and is the first tool to provide an image of the reconstructed chromosomes. Expand
An Improved Segmentation for Raw G-Band Chromosome Images
TLDR
This paper has tried to present an algorithm to overcome all the difficulties such as accurate thresholding, separation of touching and overlapping chromosomes, and is also focusing on issues that may increase the segmentation quality beyond the separation of overlapping chromosomes. Expand
Automated System for Chromosome Karyotyping to Recognize the Most Common Numerical Abnormalities Using Deep Learning
TLDR
Deep learning is used to automate karyotyping to recognize the common numerical abnormalities on a dataset containing 147 non-overlapped metaphase images collected from the Center of Excellence in Genomic Medicine Research at King Abdulaziz University. Expand
Nuclei Detection in Cytological Images Using Convolutional Neural Network and Ellipse Fitting Algorithm
TLDR
An approach, which combines convolutional neural network and ellipse fitting algorithm to segment nuclei in cytological images of breast cancer is proposed, which can accurately segment elliptic-shaped objects. Expand
A Web-based Tool for Semi-interactively Karyotyping the Chromosome Images for Analyzing Chromosome Abnormalities
Chromosome abnormalities relate to several genetic diseases. These abnormalities can be diagnosed based on the analysis of karyogram of the human chromosomes. However, the manual chromosomeExpand
A new convolutional neural network model for peripapillary atrophy area segmentation from retinal fundus images
TLDR
A novel multi-task fully convolutional network (MFCN) model is proposed to extract PPA related features based on the segmented PPA area on differentiating glaucomatous and physiologic large cup cases, and experiment conducted on real datasets confirms the effectiveness of using these features forglaucoma diagnosis. Expand
A variable region scalable fitting energy approach for human Metaspread chromosome image segmentation
TLDR
The proposed method is capable of efficiently segmenting the human metaspread chromosome images that suffer from intensity inhomogeneity and the chromosomes that have very low contrast with the background or the group of chromosomes that appear to be nearly touching each other are segmented correctly from the metasp read images. Expand
Método integral de segmentación automática de cromosomas basado en redes neuronales profundas
Resumen En este trabajo se aborda el problema de la segmentación automática de cromosomas con tinción en banda G mediante la aplicación de redes convolucionales profundas. Se propone una metodoloǵıaExpand
Adversarial Multiscale Feature Learning for Overlapping Chromosome Segmentation
TLDR
An adversarial multiscale feature learning framework to improve the accuracy and adaptability of overlapping chromosome segmentation and is proven superior by using public datasets in eight evaluation criteria. Expand
...
1
2
...

References

SHOWING 1-10 OF 21 REFERENCES
Automatic karyotyping of metaphase cells with overlapping chromosomes.
TLDR
Image analysis research aimed at analyzing images of banded, human chromosomes is described and an experimental automated karyotyping system (AKS) has been assembled, designed to automatically process cells containing overlapping chromosomes. Expand
A geometric approach to fully automatic chromosome segmentation
TLDR
A geometric-based method is used for automatic detection of touching and overlapping chromosomes and separating them and it can easily be applied to any type of images such as binary images and does not require multispectral images as well. Expand
A novel approach for efficient extrication of overlapping chromosomes in automated karyotyping
TLDR
A novel algorithm to extricate overlapping chromosomes in a metaphase image using Delaunay triangulation to automatically identify the number of overlaps in a cluster followed by the detection of the appropriate cut-points is introduced. Expand
Automatic Segmentation and Disentangling of Chromosomes in Q-Band Prometaphase Images
TLDR
An automatic procedure is proposed to obtain the separated chromosomes, which are then ready for a subsequent classification step, carried out by means of a space-variant thresholding scheme, which proved to be successful even in presence of hyper- or hypofluorescent regions in the image. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
A review of metaphase chromosome image selection techniques for automatic karyotype generation
  • T. Arora, R. Dhir
  • Biology, Medicine
  • Medical & Biological Engineering & Computing
  • 2015
TLDR
The various reported methods for metaphase chromosome image selection for automatic karyotype generation are compared and it has been concluded that each metaphase chromosomes image selection method has its advantages and disadvantages. Expand
Fully automatic chromosome segmentation.
  • L. Ji
  • Biology, Medicine
  • Cytometry
  • 1994
TLDR
A rule-based approach is described which treats the cell as a whole rather than as a series of individual chromosomes or clusters, and has been implemented in an automatic aberration scoring system for routine use. Expand
Human genetics and disease: Human cytogenetics: 46 chromosomes, 46 years and counting
  • B. Trask
  • Biology, Medicine
  • Nature Reviews Genetics
  • 2002
TLDR
Human cytogenetics was born in 1956 with the fundamental, but empowering, discovery that normal human cells contain 46 chromosomes and now informs human genomics, disease and cancer genetics, chromosome evolution and the relationship of nuclear structure to function. Expand
Telomere length measurements using digital fluorescence microscopy.
TLDR
It is demonstrated that accurate and repeatable fluorescence intensity measurements can be made from Q-FISH images that provide information on the length of telomere repeats at individual chromosomes from limited number of cells. Expand
Heterogeneity in telomere length of human chromosomes.
TLDR
Telomere fluorescence intensity values from metaphase chromosomes of cultured human hematopoietic cells decreased with the replication history of the cells, varied up to six-fold within a metaphase, and were similar between sister chromatid telomeres. Expand
...
1
2
3
...