Fully‐automatic raw G‐band chromosome image segmentation
Open Access
- 3 June 2020
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 14 (9) , 1920-1928
Abstract
Analysis of the chromosome images plays an important role in discovering one's genetic information and possible genetic disorders. Segmentation has a very substantial place in the chromosome analysis and without an automatic solution, it is a time‐consuming and error‐prone procedure. Many researchers tried to automate the segmentation process. However, background noise, objects other than chromosomes in the image, touching and overlapped chromosomes are still current issues. To address these issues, the authors proposed fully‐automatic raw G‐band chromosome image segmentation, which aims to segment every single chromosome with a minimal error. The proposed algorithm contains the following steps: clearing the background noise, eliminating the objects other than chromosomes, distinguishing single chromosomes and chromosome clusters, separating touching and overlapping chromosomes. The proposed algorithm is tested on 508 raw images and achieved an accuracy of 94.7% for touching chromosome separation, 96.3% for overlapped chromosome separation, and 98.94% for segmentation of all chromosomes. The whole segmentation process takes 2–7 s for one image, depending on the number of touching and overlapping chromosomes. The segmentation results showed that compared to the previously proposed methods, their algorithm achieved better accuracy.Keywords
This publication has 29 references indexed in Scilit:
- A review of thresholding strategies applied to human chromosome segmentationComputer Methods and Programs in Biomedicine, 2012
- Automatic segmentation of metaphase cells based on global context and variant analysisPattern Recognition, 2008
- Trainable grey-level models for disentangling overlapping chromosomesPattern Recognition, 1999
- Data-driven homologue matching for chromosome identificationIEEE Transactions on Medical Imaging, 1998
- Toward a completely automatic neural-network-based human chromosome analysisIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1998
- A classification-driven partially occluded object segmentation (CPOOS) method with application to chromosome analysisIEEE Transactions on Signal Processing, 1998
- Geometric separation of partially overlapping nonrigid objects applied to automatic chromosome classificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Fully automatic chromosome segmentationCytometry, 1994
- Morphological grayscale reconstruction in image analysis: applications and efficient algorithmsIEEE Transactions on Image Processing, 1993
- Intelligent splitting in the chromosome domainPattern Recognition, 1989