Automatic classification of chromosomes in Q-band images

Poletti, Enea; Grisan, Enrico; Ruggeri, Alfredo

doi:10.1109/iembs.2008.4649560

Cited by 35 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The distribution of chromosomes over classes is shown in Table 4. Biomedical Imaging Laboratory (BioImLab): which is publicly available online [59]. The dataset contains 5474 grayscale separated chromosome images and the distribution of these chromosomes over classes is tabulated in Table 5.…”

Section: B Datasetmentioning

confidence: 99%

Automated System for Chromosome Karyotyping to Recognize the Most Common Numerical Abnormalities Using Deep Learning

2020

View full text Add to dashboard Cite

Chromosome analysis is an essential task in a cytogenetics lab, where cytogeneticists can diagnose whether there are abnormalities or not. Karyotyping is a standard technique in chromosome analysis that classifies metaphase image to 24 chromosome classes. The main two categories of chromosome abnormalities are structural abnormalities that are changing in the structure of chromosomes and numerical abnormalities which include either monosomy (missing one chromosome) or trisomy (extra copy of the chromosome). Manual karyotyping is complex and requires high domain expertise, as it takes an amount of time. With these motivations, in this research, we used deep learning 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. The metaphase images went through three stages. The first one is individual chromosomes detection using YOLOv2 Convolutional Neural Network followed by some chromosome post-processing. This step achieved 0.84 mean IoU, 0.9923 AP, and 100% individual chromosomes detection accuracy. The second stage is feature extraction and classification where we fine-tune VGG19 network using two different approaches, one by adding extra fully connected layer(s) and another by replacing fully connected layers with the global average pooling layer. The best accuracy obtained is 95.04%. The final step is detecting abnormality and this step obtained 96.67% abnormality detection accuracy. To further validate the proposed classification method, we examined the Biomedical Imaging Laboratory dataset which is publicly available online and achieved 94.11% accuracy.

show abstract

Section: B Datasetmentioning

confidence: 99%

Automated System for Chromosome Karyotyping to Recognize the Most Common Numerical Abnormalities Using Deep Learning

2020

View full text Add to dashboard Cite

show abstract

“…We utilized the publicly available Bioimage Chromosome Classification dataset (Poletti et al, 2008). This dataset contains a total of 5,256 images of chromosomes of healthy patients, which were manually segmented and labeled by expert cytogeneticists.…”

Section: Datasetmentioning

confidence: 99%

Deep Metric Learning Network using Proxies for Chromosome Classification and Retrieval in Karyotyping Test

Jung¹,

Park²,

Lee³

et al. 2020

Preprint

View full text Add to dashboard Cite

In karyotyping, the classification of chromosomes is a tedious, complicated, and timeconsuming process. It requires extremely careful analysis of chromosomes by well-trained cytogeneticists. To assist cytogeneticists in karyotyping, we introduce Proxy-ResNeXt-CBAM which is a metric learning based network using proxies with a convolutional block attention module (CBAM) designed for chromosome classification. RexNeXt-50 is used as a backbone network. To apply metric learning, the fully connected linear layer of the backbone network (ResNeXt-50) is removed and is replaced with CBAM. The similarity between embeddings, which are the outputs of the metric learning network, and proxies are measured for network training.Proxy-ResNeXt-CBAM is validated on a public chromosome image dataset, and it achieves an accuracy of 95.86%, a precision of 95.87%, a recall of 95.9%, and an F-1 score of 95.79%. Proxy-ResNeXt-CBAM which is the metric learning network using proxies outperforms the baseline networks. In addition, the results of our embedding analysis demonstrate the effectiveness of using proxies in metric learning for optimizing deep convolutional neural networks. As the embedding analysis results show, Proxy-ResNeXt-CBAM obtains a 94.78% Recall@1 in image retrieval, and the embeddings of each chromosome are well clustered according to their similarity.

show abstract

“…Para o desenvolvimento deste trabalho, foi utilizada a base de imagens disponibilizada pelo Laboratório de Imagem Biomédica [21]. A escolha dessa base de imagens é por ela apresentar arquivos de imagens de cromossomos já segmentados e com suas devidas classificações.…”

Section: Figura 6: Disposição Dos Arquivos Da Base De Copenhagenunclassified

Organização e estruturação em XML das características morfológicas de cromossomos a partir de uma base de imagens para o processo de identificação de cromossomos

Kurtz

Oliveira

Zamberlan

et al. 2016

RBCA

View full text Add to dashboard Cite

Resumo: o objetivo deste trabalho é apresentar uma simplificação, estruturação e organização das informações a respeito das características morfológicas de cromossomos a partir de uma base de imagens, aplicados ao processo de identificação automática de cromossomos humanos. Neste trabalho, foram realizadas pesquisas com o intuito de investigar como funciona o processo de identificação de cromossomos humanos, quais são as principais informações morfológicas utilizadas bem como as opções já existentes e utilizadas por outros autores, analisando suas características e fragilidades. Por fim, são apresentadas duas propostas de estruturação e organização dessas informações utilizando XML Schema e XML. Palavras-chave:Cromossomos. XML. Características morfológicas. Estruturação. Identificação de cromossomos. Abstract: The objective of this paper is to present a simplification, structuring and organization of informations about the morphological characteristics of chromosomes from an image dataset IntroduçãoNas últimas duas décadas, a área da genética, em especial a genética médica, cresceu muito no Brasil e tem atraído um grande número de profissionais. A citogenética humana foi uma de suas primeiras subáreas a ser implantada no país, inicialmente em laboratórios de pesquisa e, mais recentemente, também em laboratórios de análises clínicas. Atualmente, suas aplicações incluem a caracterização de polimorfismos nas populações e a pesquisa da ação de agentes mutagênicos (que causam mutações ou mudanças na forma do DNA) ou carcinogênicos (que causam mutações e levam a ativação de genes tumorais) em ensaios in vitro, além da análise de cariótipo em muitas doenças. Suas técnicas compreendem importantes ferramentas de diagnóstico pré e pós-natal de anomalias congênitas (alterações nas quais os indivíduos já nascem com ela) e de diagnóstico e monitoramento de terapia em casos de neoplasias, principalmente hematológicas [1].

show abstract

Automatic classification of chromosomes in Q-band images

Cited by 35 publications

References 13 publications

Automated System for Chromosome Karyotyping to Recognize the Most Common Numerical Abnormalities Using Deep Learning

Automated System for Chromosome Karyotyping to Recognize the Most Common Numerical Abnormalities Using Deep Learning

Deep Metric Learning Network using Proxies for Chromosome Classification and Retrieval in Karyotyping Test

Organização e estruturação em XML das características morfológicas de cromossomos a partir de uma base de imagens para o processo de identificação de cromossomos

Contact Info

Product

Resources

About