Geometric separation of partially overlapping nonrigid objects applied to automatic chromosome classification

Agam, Gady; Dinstein, I.

doi:10.1109/34.632981

Cited by 114 publications

(79 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Agam [9] has worked on grayscale chromosome images and has used miniset based approach to disassociate touching and overlapping chromosomes. The work is based upon hypothesis of shape testing to find cut points that can potentially divide the chromosomes in a cluster.…”

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

“…The procedures for automatic segregation of overlapping chromosomes aim at applying thresholding based methods to divide the different overlapping chromosomes into different chromosomes by using the geometric shapes [6][7][8], curvature of the boundary of the chromosome [9,10], layout of the chromosome [11] and pattern of the bands [12,13] in this paper an attempt has been made to propose a efficient segmentation method for overlapping chromosomes using computational geometry based approaches that have been successfully used for various image analysis tasks [14][15][16] …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Segmentation Method for Overlapping Chromosome Images

Tanvi¹,

Dhir²

2014

IJCA

View full text Add to dashboard Cite

Systems are being developed to automate the task of classification of chromosomes. The chromosomes are nonrigid material and they are several times touching each other or they overlap each other in the metaphase images. So different techniques are required to segregate the overlapping chromosomes. This paper presents a novel method for segmenting chromosomes based upon computational geometry. In the proposed approach first the contour line is traced for the overlapping chromosomes and then all the cut points are traced for the overlapping chromosomes. Then based on computational geometry method a specific number of cut points are selected and they are used for separating the two chromosomes. We have found that 87.4% of the images were correctly segmented using the proposed method.

show abstract

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Efficient Segmentation Method for Overlapping Chromosome Images

Tanvi¹,

Dhir²

2014

IJCA

View full text Add to dashboard Cite

show abstract

“…For the third step, some researches concentrate only on disentangling of touching clusters using dark paths [6] or using geometric shape [4] and some researches concentrate only on separation of overlapping chromosomes by using different methods, such as Watershed segmentation method [7,8] or using shape of clusters [9], curvature of the cluster boundaries [10], chromosome skeleton [11] banded images [12,13]. In this research, the dark paths and geometric shape of clusters are used to separate touching and overlapping clusters…”

Section: Introductionmentioning

confidence: 99%

Mass Detection in Lung CT Images Using Region Growing Segmentation and Decision Making Based on Fuzzy Inference System and Artificial Neural Network

Hashemi¹,

Pilevar²,

Rafeh³

2013

IJIGSP

View full text Add to dashboard Cite

Abstract-Nowadays, Karyotype analysis is frequently used in cytogenetics. It is a time-consuming and repetitive work therefore an automatic analysis can greatly be valued. In this research, an automatic method is presented. Firstly, a proposed locally adaptive thresholding method is used to segment chromosome clusters. Then, the clusters is divided into two main categories including, single chromosomes and multichromosome clusters based on geometric shape of clusters. In the next step, each extracted cluster is investigated to find the dark paths in order to detect touching chromosomes. Then, overlapping chromosomes are separated in clusters based on their geometric shapes. Finally, a criterion function is used to measure the similarity between the outputs of the proposed algorithm and the single chromosomes in order to recognize separated parts. The proposed algorithm is applied on 47 G-band images. The results shows that single chromosomes and clusters are recognized by the precision of 98.5% and 86.4%, respectively and separation of touching and overlapping clusters are done by precision of 70% and 67%, respectively.

show abstract

“…Cut points are then found by examining the shape of boundary of the cluster [2,3,12]. Occasionally, grayscale information from inside the chromosome clusters is also used.…”

Section: Multi-spectral Entropy Estimation For Segmentationmentioning

confidence: 99%

“…However, since many images often have to be inspected and since visual inspection is time consuming and expensive, many attempts have been made to automate chromosome image analysis. For example, automated segmentation algorithms for grayscale chromosome images have been able to correctly decompose about 80-90% of touching and overlapping chromosomes [1,2,3]. These automated procedures rely on chromosome shape and texture.…”

Section: Introductionmentioning

confidence: 99%