DeepACE: Automated Chromosome Enumeration in Metaphase Cell Images Using Deep Convolutional Neural Networks

@inproceedings{Xiao2019DeepACEAC,
  title={DeepACE: Automated Chromosome Enumeration in Metaphase Cell Images Using Deep Convolutional Neural Networks},
  author={Li Xiao and Chunlong Luo and Yufan Luo and Tianqi Yu and Chan Tian and Jie Qiao and Yi Zhao},
  booktitle={MICCAI},
  year={2019}
}
Chromosome enumeration is an important but tedious procedure in karyotyping analysis. In this paper, to automate the enumeration process, we developed a chromosome enumeration framework, DeepACE, based on the region based object detection scheme. Firstly, the ability of region proposal network is enhanced by a newly proposed Hard Negative Anchors Sampling to extract unapparent but important information about highly confusing partial chromosomes. Next, to alleviate serious occlusion problems, we… Expand

Figures, Tables, and Topics from this paper

DeepACEv2: Automated Chromosome Enumeration in Metaphase Cell Images Using Deep Convolutional Neural Networks
TLDR
A chromosome enumeration framework, DeepACEv2, based on the region based object detection scheme, which outperforms all the previous methods, and design a Truncated Normalized Repulsion Loss and add it to the loss function to avoid inaccurate localization caused by occlusion. Expand
DEEPACC:Automate Chromosome Classification Based On Metaphase Images Using Deep Learning Framework Fused With Priori Knowledge
TLDR
This work proposes a detection based method, DeepACC, to locate and fine classify chromosomes simultaneously based on the whole metaphase image to alleviate batch effects and introduces the Additive Angular Margin Loss to enhance the discriminative power of the model. Expand

References

SHOWING 1-10 OF 12 REFERENCES
Varifocal-Net: A Chromosome Classification Approach Using Deep Convolutional Networks
TLDR
The evaluation results from 1909 karyotyping cases showed that the proposed Varifocal-Net achieved the highest accuracy per patient case (%) of 99.2 for both type and polarity tasks, and outperformed state-of-the-art methods. Expand
A novel approach for segmentation of human metaphase chromosome images using region based active contours
  • T. Arora
  • Computer Science
  • Int. Arab J. Inf. Technol.
  • 2019
TLDR
A segmentation technique has been proposed to segment the objects present in the human metaphase chromosome images using region based active contour techniques, which has been quite efficient from prospective of number of objects segmented. Expand
A geometric approach to fully automatic chromosome segmentation
TLDR
A geometric-based method is used for automatic detection of touching and overlapping chromosomes and separating them and it can easily be applied to any type of images such as binary images and does not require multispectral images as well. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
Chromosome counting via digital image analysis
TLDR
An automated counting algorithm based on digital image analysis that accelerates the karyotyping process, thereby facilitating quicker and less expensive cytogenetic analysis. Expand
DEVELOPMENT OF COMPUTERIZED SYSTEMS FOR AUTOMATED CHROMOSOME ANALYSIS: CURRENT STATUS AND FUTURE PROSPECTS
Computer Aided Diagnosis (CAD) is an important pattern recognition application in the field of medical sciences. Such systems assist (not replaces) doctors in the interpretation of medical image.Expand
Fast R-CNN
  • Ross B. Girshick
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deepExpand
Soft-NMS — Improving Object Detection with One Line of Code
TLDR
Soft-NMS is proposed, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M and improves state-of-the-art in object detection from 39.8% to 40.9% with a single model. Expand
Automated Cytogenetics in the Study of Mutagenesis and Cancer
TLDR
Cytogenetics automation now provides practical and cost effective assistance in some subject areas, notably in clinical cytogenetics for the determination of the human constitutional karyotype, for example for ante-natal screening of genetic disorders. Expand
Molecular genetic analysis of Down syndrome
TLDR
Progress in understanding the genetic mechanisms by which trisomy of HSA21 leads to DS is the subject of this review. Expand
...
1
2
...