A New Multiple-Distribution GAN Model to Solve Complexity in End-to-End Chromosome Karyotyping
With significant development of Internet of medical things (IoMT) and cloud-fog-edge computing, medical industry is now involving medical big data to improve quality of service in patient care. Karyotyping refers classifying human chromosomes. However, performing karyotyping task generally requires...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2020/8923838 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832551012741677056 |
|---|---|
| author | Yirui Wu Xiao Tan Tong Lu |
| author_facet | Yirui Wu Xiao Tan Tong Lu |
| author_sort | Yirui Wu |
| collection | DOAJ |
| description | With significant development of Internet of medical things (IoMT) and cloud-fog-edge computing, medical industry is now involving medical big data to improve quality of service in patient care. Karyotyping refers classifying human chromosomes. However, performing karyotyping task generally requires domain expertise in cytogenetics, long-period experience for high accuracy, and considerable manual efforts. An end-to-end chromosome karyotype analysis system is proposed over medical big data to automatically and accurately perform chromosome related tasks of detection, segmentation, and classification. Facing image data generated and collected by means of edge computing, we firstly utilize visual feature to generate chromosome candidates with Extremal Regions (ER) technology. Due to severe occlusion and cross overlapping, we utilize ring radius transform to cluster pixels with same property to approximate chromosome shapes. To solve the problem of unbalanced and small dataset by covering diverse data patterns, we proposed multidistributed generated advertising network (MD-GAN) to perform data enhancement by generating additional training samples. Afterwards, we fine-tune CNN for chromosome classification task by involving generated and sufficient training images. Through experiments in self-collected datasets, the proposed method achieves high accuracy in tasks of chromosome detection, segmentation, and classification. Moreover, experimental results prove that MD-GAN-based data enhancement contributes to classification results of CNN to a certain extent. |
| format | Article |
| id | doaj-art-e18d507a9fbf4cf69448cb87ae9b2307 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-e18d507a9fbf4cf69448cb87ae9b23072025-02-03T06:05:16ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/89238388923838A New Multiple-Distribution GAN Model to Solve Complexity in End-to-End Chromosome KaryotypingYirui Wu0Xiao Tan1Tong Lu2College of Computer and Information, Hohai University, Nanjing, ChinaNanjing Tuofan Information Technology Company, Nanjing, ChinaNational Key Lab for Novel Software Technology, Nanjing University, Nanjing, ChinaWith significant development of Internet of medical things (IoMT) and cloud-fog-edge computing, medical industry is now involving medical big data to improve quality of service in patient care. Karyotyping refers classifying human chromosomes. However, performing karyotyping task generally requires domain expertise in cytogenetics, long-period experience for high accuracy, and considerable manual efforts. An end-to-end chromosome karyotype analysis system is proposed over medical big data to automatically and accurately perform chromosome related tasks of detection, segmentation, and classification. Facing image data generated and collected by means of edge computing, we firstly utilize visual feature to generate chromosome candidates with Extremal Regions (ER) technology. Due to severe occlusion and cross overlapping, we utilize ring radius transform to cluster pixels with same property to approximate chromosome shapes. To solve the problem of unbalanced and small dataset by covering diverse data patterns, we proposed multidistributed generated advertising network (MD-GAN) to perform data enhancement by generating additional training samples. Afterwards, we fine-tune CNN for chromosome classification task by involving generated and sufficient training images. Through experiments in self-collected datasets, the proposed method achieves high accuracy in tasks of chromosome detection, segmentation, and classification. Moreover, experimental results prove that MD-GAN-based data enhancement contributes to classification results of CNN to a certain extent.http://dx.doi.org/10.1155/2020/8923838 |
| spellingShingle | Yirui Wu Xiao Tan Tong Lu A New Multiple-Distribution GAN Model to Solve Complexity in End-to-End Chromosome Karyotyping Complexity |
| title | A New Multiple-Distribution GAN Model to Solve Complexity in End-to-End Chromosome Karyotyping |
| title_full | A New Multiple-Distribution GAN Model to Solve Complexity in End-to-End Chromosome Karyotyping |
| title_fullStr | A New Multiple-Distribution GAN Model to Solve Complexity in End-to-End Chromosome Karyotyping |
| title_full_unstemmed | A New Multiple-Distribution GAN Model to Solve Complexity in End-to-End Chromosome Karyotyping |
| title_short | A New Multiple-Distribution GAN Model to Solve Complexity in End-to-End Chromosome Karyotyping |
| title_sort | new multiple distribution gan model to solve complexity in end to end chromosome karyotyping |
| url | http://dx.doi.org/10.1155/2020/8923838 |
| work_keys_str_mv | AT yiruiwu anewmultipledistributionganmodeltosolvecomplexityinendtoendchromosomekaryotyping AT xiaotan anewmultipledistributionganmodeltosolvecomplexityinendtoendchromosomekaryotyping AT tonglu anewmultipledistributionganmodeltosolvecomplexityinendtoendchromosomekaryotyping AT yiruiwu newmultipledistributionganmodeltosolvecomplexityinendtoendchromosomekaryotyping AT xiaotan newmultipledistributionganmodeltosolvecomplexityinendtoendchromosomekaryotyping AT tonglu newmultipledistributionganmodeltosolvecomplexityinendtoendchromosomekaryotyping |