A review of metaphase chromosome image selection techniques for automatic karyotype generation

Current techniques for chromosome analysis need to be improved for rapid, economical identification of complex chromosomal defects by sensitive and selective visualisation. In this paper, we present a straightforward method for characterising unstained human metaphase chromosomes. Backscatter imaging in a dark-field setup combined with visible and short near-infrared spectroscopy is used to monitor morphological differences in the distribution of the chromosomal fine structure in human metaphase chromosomes. The reasons for the scattering centres in the fine structure are explained. Changes in the scattering centres during preparation of the metaphases are discussed. FDTD simulations are presented to substantiate the experimental findings. We show that local scattering features consisting of underlying spectral modulations of higher frequencies associated with a high variety of densely packed chromatin can be represented by their scatter profiles even on a sub-microscopic level. The result is independent of the chromosome preparation and structure size. This analytical method constitutes a rapid, cost-effective and label-free cytogenetic technique which can be used in a standard light microscope. Graphical abstract Hyperspectral backscatter imaging for label-free characterization.

show abstract

“…The results are still not good enough to be considered for the purpose of diagnosis of a medical condition [17].…”

Section: Introductionmentioning

confidence: 94%

Hyperspectral backscatter imaging: a label-free approach to cytogenetics

2016

View full text Add to dashboard Cite

show abstract

“…These approaches can generally be divided into two groups as rulebased and deep learning-based image processing methods [1]. When the studies in the literature are examined in rule-based methods, it can be observed that the rates of false positive are quite high [2]. In recent years, It has been observed that the deep learning methods give accurate results in many areas such as object recognition, target tracking, natural language processing, voice recognition [3].…”

Section: Introductionmentioning

confidence: 99%

Classification of Analyzable Metaphase Images by Extreme Learning Machines

Albayrak¹

2021

European Journal of Technic

View full text Add to dashboard Cite

“…In general, there are 23 pairs of chromosomes in a healthy human body, including 22 pairs autosomes and a pair of sex chromosomes (X and Y chromosome in male cells and double X in female cells) [1]. Karyotype analysis, illustrated by Figure 1, is a fundamental approach for clinical cytogeneticists to diagnose human chromosomes genetic diseases, which is generated by arranging these chromosomes after extracting them from the metaphase chromosome images [2]. For cytogeneticists, karyotyping is laborious work, many researchers have dedicated to autokaryotyping using computation techniques [3], [4], [5], [6], [7], [8] for years.…”

Section: Introductionmentioning

confidence: 99%

CIR-Net: Automatic Classification of Human Chromosome based on Inception-ResNet Architecture

Lin

Zhao

Yang

et al. 2020

IEEE/ACM Trans. Comput. Biol. and Bioinf.

View full text Add to dashboard Cite

Background:In medicine, karyotyping chromosomes is important for medical diagnostics, drug development, and biomedical research. Unfortunately, chromosome karyotyping is usually done by skilled cytologists manually, which requires experience, domain expertise, and considerable manual efforts. Therefore, automating the karyotyping process is a significant and meaningful task. Method:This paper focuses on chromosome classification because it is critical for chromosome karyotyping.In recent years, deep learning-based methods are the most promising methods for solving the tasks of chromosome classification. Although the deep learning-based Inception architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge, it has not been used in chromosome classification tasks so far. Therefore, we develop an automatic chromosome classification approach named CIR-Net based on Inception-ResNet which is an optimized version of Inception. However, the classification performance of origin Inception-ResNet on the insufficient chromosome dataset still has a lot of capacity for improvement. Further, we propose a simple but effective augmentation method called CDA for improving the performance of CIR-Net. Results:The experimental results show that our proposed method achieves 95.98% classification accuracy on the clinical G-band chromosome dataset whose training dataset is insufficient.Moreover, the proposed augmentation method CDA improves more than 8.5% (from 87.46% to 95.98%) classification accuracy comparing to other methods.In this paper, the experimental results demonstrate that our proposed method is recent the most effective solution for solving clinical chromosome classification problems in chromosome auto-karyotyping on the condition of the insufficient training dataset.

show abstract

A review of metaphase chromosome image selection techniques for automatic karyotype generation

Cited by 28 publications

References 35 publications

Hyperspectral backscatter imaging: a label-free approach to cytogenetics

Hyperspectral backscatter imaging: a label-free approach to cytogenetics

Classification of Analyzable Metaphase Images by Extreme Learning Machines

CIR-Net: Automatic Classification of Human Chromosome based on Inception-ResNet Architecture

Contact Info

Product

Resources

About