Evaluation of color based breast cancer cell images analysis
This paper describes a simple yet effective algorithm for automatically counting stained breast cancer cell imagesbased on color contents. The procedure for the approach consists of four steps. First, the cancer cell image in red-greenblue(RGB) color space is transformed with Haar wavelet. Second, t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Prince of Songkla University
2010-07-01
|
| Series: | Songklanakarin Journal of Science and Technology (SJST) |
| Subjects: | |
| Online Access: | http://www.rdoapp.psu.ac.th/html/sjst/journal/32-3/0125-3395-32-3-231-239.pdf |
| _version_ | 1811329806032175104 |
|---|---|
| author | Chalit Primkhajeepong Pornchai Phukpattaranont Somchai Limsiroratana Pleumjit Boonyaphiphat Kanita Kayasut3 |
| author_facet | Chalit Primkhajeepong Pornchai Phukpattaranont Somchai Limsiroratana Pleumjit Boonyaphiphat Kanita Kayasut3 |
| author_sort | Chalit Primkhajeepong |
| collection | DOAJ |
| description | This paper describes a simple yet effective algorithm for automatically counting stained breast cancer cell imagesbased on color contents. The procedure for the approach consists of four steps. First, the cancer cell image in red-greenblue(RGB) color space is transformed with Haar wavelet. Second, the wavelet transformed image is changed to gray-scaleimage. Next, the gray-scale image is segmented with global thresholding using Otsu’s method and morphological operationsusing opening, region filling, border clearing, and watershed segmentation. Third, the wavelet transformed image is changedto CIEL*a*b* color space. The feature, i.e. average value of b* of each isolated cell, is extracted. Finally, the classification isapplied by using the extracted feature. If the average value of b* is positive that indicates yellow, the cancer cell is a positivecell. In addition, if the average value of b* is negative that indicates blue, the cancer cell is a negative cell. Results show thatthe classified cancer cells by the proposed algorithm are in good agreement with the expert perception. In addition, thealgorithm is practical to be used by a pathologist due to its simplicity and effectiveness. |
| first_indexed | 2024-04-13T15:50:24Z |
| format | Article |
| id | doaj.art-f741c1837a284528beea3ccd7db9c3d1 |
| institution | Directory Open Access Journal |
| issn | 0125-3395 |
| language | English |
| last_indexed | 2024-04-13T15:50:24Z |
| publishDate | 2010-07-01 |
| publisher | Prince of Songkla University |
| record_format | Article |
| series | Songklanakarin Journal of Science and Technology (SJST) |
| spelling | doaj.art-f741c1837a284528beea3ccd7db9c3d12022-12-22T02:40:52ZengPrince of Songkla UniversitySongklanakarin Journal of Science and Technology (SJST)0125-33952010-07-01323231239Evaluation of color based breast cancer cell images analysisChalit PrimkhajeepongPornchai PhukpattaranontSomchai LimsiroratanaPleumjit BoonyaphiphatKanita Kayasut3This paper describes a simple yet effective algorithm for automatically counting stained breast cancer cell imagesbased on color contents. The procedure for the approach consists of four steps. First, the cancer cell image in red-greenblue(RGB) color space is transformed with Haar wavelet. Second, the wavelet transformed image is changed to gray-scaleimage. Next, the gray-scale image is segmented with global thresholding using Otsu’s method and morphological operationsusing opening, region filling, border clearing, and watershed segmentation. Third, the wavelet transformed image is changedto CIEL*a*b* color space. The feature, i.e. average value of b* of each isolated cell, is extracted. Finally, the classification isapplied by using the extracted feature. If the average value of b* is positive that indicates yellow, the cancer cell is a positivecell. In addition, if the average value of b* is negative that indicates blue, the cancer cell is a negative cell. Results show thatthe classified cancer cells by the proposed algorithm are in good agreement with the expert perception. In addition, thealgorithm is practical to be used by a pathologist due to its simplicity and effectiveness.http://www.rdoapp.psu.ac.th/html/sjst/journal/32-3/0125-3395-32-3-231-239.pdfquantitative immunohistophathologybiomedical image processingimage segmentationwavelet transformationmorphological operation |
| spellingShingle | Chalit Primkhajeepong Pornchai Phukpattaranont Somchai Limsiroratana Pleumjit Boonyaphiphat Kanita Kayasut3 Evaluation of color based breast cancer cell images analysis Songklanakarin Journal of Science and Technology (SJST) quantitative immunohistophathology biomedical image processing image segmentation wavelet transformation morphological operation |
| title | Evaluation of color based breast cancer cell images analysis |
| title_full | Evaluation of color based breast cancer cell images analysis |
| title_fullStr | Evaluation of color based breast cancer cell images analysis |
| title_full_unstemmed | Evaluation of color based breast cancer cell images analysis |
| title_short | Evaluation of color based breast cancer cell images analysis |
| title_sort | evaluation of color based breast cancer cell images analysis |
| topic | quantitative immunohistophathology biomedical image processing image segmentation wavelet transformation morphological operation |
| url | http://www.rdoapp.psu.ac.th/html/sjst/journal/32-3/0125-3395-32-3-231-239.pdf |
| work_keys_str_mv | AT chalitprimkhajeepong evaluationofcolorbasedbreastcancercellimagesanalysis AT pornchaiphukpattaranont evaluationofcolorbasedbreastcancercellimagesanalysis AT somchailimsiroratana evaluationofcolorbasedbreastcancercellimagesanalysis AT pleumjitboonyaphiphat evaluationofcolorbasedbreastcancercellimagesanalysis AT kanitakayasut3 evaluationofcolorbasedbreastcancercellimagesanalysis |