Gene expression extraction in cervical cancer by segmentation of microarray images using a novel fuzzy method
It is necessary to obtain gene expression values to identify gene biomarkers involved in all types of cancers, and microarray data is one of the best data for this purpose. In order to extract gene expression values from microarray images that have different challenges. This article presents a compl...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/21681163.2023.2261555 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839636018256412672 |
|---|---|
| author | Nayyer Mostaghim Bakhshayesh Mousa Shamsi Faegheh Golabi |
| author_facet | Nayyer Mostaghim Bakhshayesh Mousa Shamsi Faegheh Golabi |
| author_sort | Nayyer Mostaghim Bakhshayesh |
| collection | DOAJ |
| description | It is necessary to obtain gene expression values to identify gene biomarkers involved in all types of cancers, and microarray data is one of the best data for this purpose. In order to extract gene expression values from microarray images that have different challenges. This article presents a completely automatic and comprehensive method that can deal with the various challenges in these images and obtain gene expression values with high accuracy. A pre-processing approach is proposed for contrast enhancement using a genetic algorithm and for removing noise and artefacts in microarray cells using wavelet transform based on a complex Gaussian scaling model. For each point, the coordinate centre is determined using Self Organising Maps. Then, using a new hybrid model based on the Fuzzy Local Information Gaussian Mixture Model (FLIGMM), the position of each spot is accurately determined. In this model, various features are obtained using local information about pixels, considering the pixel neighbourhood correlation coefficient. Finally, the gene expression values are obtained. The performance of the proposed algorithm was evaluated using real microarray images of cervical cancer from the GMRCL microarray dataset as well as simulated images. The results show that the proposed algorithm achieves 90.91% and 98% accuracy in segmenting microarray spots for noiseless and noisy spots, respectively. |
| format | Article |
| id | doaj-art-c6f60fe99b5b4cce9e4de97c321de3c1 |
| institution | Matheson Library |
| issn | 2168-1163 2168-1171 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization |
| spelling | doaj-art-c6f60fe99b5b4cce9e4de97c321de3c12025-07-08T10:28:46ZengTaylor & Francis GroupComputer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization2168-11632168-11712024-12-0112110.1080/21681163.2023.2261555Gene expression extraction in cervical cancer by segmentation of microarray images using a novel fuzzy methodNayyer Mostaghim Bakhshayesh0Mousa Shamsi1Faegheh Golabi2Faculty of Biomedical Engineering, Sahand University of Technology, Tabriz, IranFaculty of Biomedical Engineering, Sahand University of Technology, Tabriz, IranFaculty of Advanced Medical Sciences, Tabriz University of Medical Sciences, Tabriz, IranIt is necessary to obtain gene expression values to identify gene biomarkers involved in all types of cancers, and microarray data is one of the best data for this purpose. In order to extract gene expression values from microarray images that have different challenges. This article presents a completely automatic and comprehensive method that can deal with the various challenges in these images and obtain gene expression values with high accuracy. A pre-processing approach is proposed for contrast enhancement using a genetic algorithm and for removing noise and artefacts in microarray cells using wavelet transform based on a complex Gaussian scaling model. For each point, the coordinate centre is determined using Self Organising Maps. Then, using a new hybrid model based on the Fuzzy Local Information Gaussian Mixture Model (FLIGMM), the position of each spot is accurately determined. In this model, various features are obtained using local information about pixels, considering the pixel neighbourhood correlation coefficient. Finally, the gene expression values are obtained. The performance of the proposed algorithm was evaluated using real microarray images of cervical cancer from the GMRCL microarray dataset as well as simulated images. The results show that the proposed algorithm achieves 90.91% and 98% accuracy in segmenting microarray spots for noiseless and noisy spots, respectively.https://www.tandfonline.com/doi/10.1080/21681163.2023.2261555Gene expressionsegmentationmicroarray imagescervical cancerfuzzy local information gaussian mixture model |
| spellingShingle | Nayyer Mostaghim Bakhshayesh Mousa Shamsi Faegheh Golabi Gene expression extraction in cervical cancer by segmentation of microarray images using a novel fuzzy method Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization Gene expression segmentation microarray images cervical cancer fuzzy local information gaussian mixture model |
| title | Gene expression extraction in cervical cancer by segmentation of microarray images using a novel fuzzy method |
| title_full | Gene expression extraction in cervical cancer by segmentation of microarray images using a novel fuzzy method |
| title_fullStr | Gene expression extraction in cervical cancer by segmentation of microarray images using a novel fuzzy method |
| title_full_unstemmed | Gene expression extraction in cervical cancer by segmentation of microarray images using a novel fuzzy method |
| title_short | Gene expression extraction in cervical cancer by segmentation of microarray images using a novel fuzzy method |
| title_sort | gene expression extraction in cervical cancer by segmentation of microarray images using a novel fuzzy method |
| topic | Gene expression segmentation microarray images cervical cancer fuzzy local information gaussian mixture model |
| url | https://www.tandfonline.com/doi/10.1080/21681163.2023.2261555 |
| work_keys_str_mv | AT nayyermostaghimbakhshayesh geneexpressionextractionincervicalcancerbysegmentationofmicroarrayimagesusinganovelfuzzymethod AT mousashamsi geneexpressionextractionincervicalcancerbysegmentationofmicroarrayimagesusinganovelfuzzymethod AT faeghehgolabi geneexpressionextractionincervicalcancerbysegmentationofmicroarrayimagesusinganovelfuzzymethod |