A Comprehensive Study on Convolutional Neural Networks for Chromosome Classification

Remya, R.; Hariharan, S; Vinod, Vishnu; Fernandez, David John W; Ajmal, NM Muhammed; Gopakumar, C.

doi:10.1109/accthpa49271.2020.9213238

Cited by 8 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to reduce the burden on doctors and save the consumption of resources such as manpower and materials, some experts and scientists have proposed an automatic or semi-automatic procedure for karyotype analysis. In the early years, machine learning methods were used to extract the feature vectors of different chromosome types and then calculate the distance between the unknown chromosome and each chromosome type to determine which chromosome type the chromosome belongs to [5][6][7][8]. With the rapid development of deep learning in recent years, the use of deep learning for chromosome classification has achieved good results, but there are still some challenges.…”

Section: Introductionmentioning

confidence: 99%

SRAS‐net: Low‐resolution chromosome image classification based on deep learning

Liu

Lin

et al. 2022

IET Systems Biology

View full text Add to dashboard Cite

Prenatal karyotype diagnosis is important to determine if the foetus has genetic diseases and some congenital diseases. Chromosome classification is an important part of karyotype analysis, and the task is tedious and lengthy. Chromosome classification methods based on deep learning have achieved good results, but if the quality of the chromosome image is not high, these methods cannot learn image features well, resulting in unsatisfactory classification results. Moreover, the existing methods generally have a poor effect on sex chromosome classification. Therefore, in this work, the authors propose to use a super‐resolution network, Self‐Attention Negative Feedback Network, and combine it with traditional neural networks to obtain an efficient chromosome classification method called SRAS‐net. The method first inputs the low‐resolution chromosome images into the super‐resolution network to generate high‐resolution chromosome images and then uses the traditional deep learning model to classify the chromosomes. To solve the problem of inaccurate sex chromosome classification, the authors also propose to use the SMOTE algorithm to generate a small number of sex chromosome samples to ensure a balanced number of samples while allowing the model to learn more sex chromosome features. Experimental results show that our method achieves 97.55% accuracy and is better than state‐of‐the‐art methods.

show abstract

Section: Introductionmentioning

confidence: 99%

SRAS‐net: Low‐resolution chromosome image classification based on deep learning

Liu

Lin

et al. 2022

IET Systems Biology

View full text Add to dashboard Cite

show abstract

“…Evaluation results from 1,909 karyograms showed that their proposed Varifocal-Net achieved the highest accuracy per patient case of 98.9% accuracy for both type and polarity tasks. [30] provided two varieties of CNNs named ChromNet1 and ChromNet2 for the chromosome classification task. According to their evaluation results on the private dataset with 21,423 samples, ChromNet2 achieved 91.3% classification accuracy.…”

Section: Methods For Chromosome Classificationmentioning

confidence: 99%

“…First of all, none of these methods were developed and evaluated on the same dataset. Most of these methods [13,17,33,41,28,8,30,21] are evaluated on private datasets that are not available to the public. [34] developed and evaluated their method on the BioImLab dataset that is a Q-band chromosome dataset.…”

Section: Methods For Chromosome Classificationmentioning

confidence: 99%

ChromosomeNet: A massive dataset enabling benchmarking and building basedlines of clinical chromosome classification

Lin

Chen

Huang

et al. 2022

Computational Biology and Chemistry

View full text Add to dashboard Cite

“…Lin et al 23 presented CIR‐net model based on Inception‐ResNet for clinical G‐band chromosome classification with 95.98% accuracy after augmentation. Remya et al 24 modelled ChromNet1 and ChromNet2, a CNN‐based classification networks for chromosome classification on proprietary dataset of 21 423 chromosomes. Somasundaram 25 has used CNN approach on 1000 chromosomes for binary classification as normal or abnormal chromosomes.…”

Section: Literature Reviewmentioning

confidence: 99%

Karyotyping of human chromosomes in metaphase images using faster R‐CNN and inception models

Chavan,

Nair,

Nimbalkar

et al. 2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Karyotyping is the process of pairing and ordering human chromosomes from metaphase chromosomal images depending on their size, centromere position, and banding patterns. It is used to analyze human chromosomes for various genetic disorders especially during prenatal screenings. Since manual karyotyping is a labor‐intensive and a time‐consuming task, developing an automatic or semi‐automatic computer‐assisted karyotyping system is the need of the hour. The proposed karyotyping system aims to detect human chromosomes (22 pairs of autosomes and one pair of sex chromosome) from the microscopic metaphase images which is followed by separation of overlapped chromosomes. Extracted chromosomes are first classified into seven Denver groups (A to G) followed by classifying individual chromosomes within their Denver group. Then the classified chromosome pairs are used to create a karyotype with the assistance of cytologists or by using estimated chromosome length as cytogenetic parameter. A total of 234 chromosomal images from two different public datasets are used for experimentation. Human chromosomes in the microscopic metaphase images are detected using faster regions with convolutional neural networks (Faster R‐CNN) combined with Inception v2. Then convexity defect algorithm is preferred for separation of overlapped chromosomes. The detected chromosomes are classified using the proposed two‐step approach in which Inception v3 model is used. Then the classified chromosome pairs are used to create a karyotype with the assistance of cytologists or by using estimated chromosome length as cytogenetic parameter. Faster R‐CNN model gives a detection accuracy of 98.53%. Denver group classification with the two‐step approach provides a better accuracy of 84.59% when network is trained for 64 902 epochs. Faster R‐CNN outperforms in detection and works faster as it searches chromosomes within the regional proposals. The two‐step classification approach gives better classification accuracy. The proposed approach also works very well for overlapping chromosomes due to use of convexity defects algorithm. The classified chromosome pairs are useful tools for the cytologists to create a karyotype with minimal efforts.

show abstract

A Comprehensive Study on Convolutional Neural Networks for Chromosome Classification

Cited by 8 publications

References 16 publications

SRAS‐net: Low‐resolution chromosome image classification based on deep learning

SRAS‐net: Low‐resolution chromosome image classification based on deep learning

ChromosomeNet: A massive dataset enabling benchmarking and building basedlines of clinical chromosome classification

Karyotyping of human chromosomes in metaphase images using faster R‐CNN and inception models

Contact Info

Product

Resources

About