Multi-Resolution Wavelet-Transformed Image Analysis of Histological Sections of Breast Carcinomas
Multi-resolution images of histological sections of breast cancer tissue were analyzed using texture features of Haar- and Daubechies transform wavelets. Tissue samples analyzed were from ductal regions of the breast and included benign ductal hyperplasia, ductal carcinoma in situ (DCIS), and invasi...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2005-01-01
|
| Series: | Cellular Oncology |
| Online Access: | http://dx.doi.org/10.1155/2005/526083 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832549087548801024 |
|---|---|
| author | Hae-Gil Hwang Hyun-Ju Choi Byeong-Il Lee Hye-Kyoung Yoon Sang-Hee Nam Heung-Kook Choi |
| author_facet | Hae-Gil Hwang Hyun-Ju Choi Byeong-Il Lee Hye-Kyoung Yoon Sang-Hee Nam Heung-Kook Choi |
| author_sort | Hae-Gil Hwang |
| collection | DOAJ |
| description | Multi-resolution images of histological sections of breast cancer tissue were analyzed using texture features of Haar- and Daubechies transform wavelets. Tissue samples analyzed were from ductal regions of the breast and included benign ductal hyperplasia, ductal carcinoma in situ (DCIS), and invasive ductal carcinoma (CA). To assess the correlation between computerized image analysis and visual analysis by a pathologist, we created a two-step classification system based on feature extraction and classification. In the feature extraction step, we extracted texture features from wavelet-transformed images at 10× magnification. In the classification step, we applied two types of classifiers to the extracted features, namely a statistics-based multivariate (discriminant) analysis and a neural network. Using features from second-level Haar transform wavelet images in combination with discriminant analysis, we obtained classification accuracies of 96.67 and 87.78% for the training and testing set (90 images each), respectively. We conclude that the best classifier of carcinomas in histological sections of breast tissue are the texture features from the second-level Haar transform wavelet images used in a discriminant function. |
| format | Article |
| id | doaj-art-36e785b7abf04fa3a42af605f519b350 |
| institution | Kabale University |
| issn | 1570-5870 1875-8606 |
| language | English |
| publishDate | 2005-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Cellular Oncology |
| spelling | doaj-art-36e785b7abf04fa3a42af605f519b3502025-02-03T06:12:08ZengWileyCellular Oncology1570-58701875-86062005-01-0127423724410.1155/2005/526083Multi-Resolution Wavelet-Transformed Image Analysis of Histological Sections of Breast CarcinomasHae-Gil Hwang0Hyun-Ju Choi1Byeong-Il Lee2Hye-Kyoung Yoon3Sang-Hee Nam4Heung-Kook Choi5School of Computer Engineering, Inje University, Republic of KoreaSchool of Computer Engineering, Inje University, Republic of KoreaDepartment of Nuclear Medicine, Chonnam National University, Republic of KoreaDepartment of Pathology, Inje University, Republic of KoreaMedical Imaging Research Center, Inje University, Republic of KoreaSchool of Computer Engineering, Inje University, Republic of KoreaMulti-resolution images of histological sections of breast cancer tissue were analyzed using texture features of Haar- and Daubechies transform wavelets. Tissue samples analyzed were from ductal regions of the breast and included benign ductal hyperplasia, ductal carcinoma in situ (DCIS), and invasive ductal carcinoma (CA). To assess the correlation between computerized image analysis and visual analysis by a pathologist, we created a two-step classification system based on feature extraction and classification. In the feature extraction step, we extracted texture features from wavelet-transformed images at 10× magnification. In the classification step, we applied two types of classifiers to the extracted features, namely a statistics-based multivariate (discriminant) analysis and a neural network. Using features from second-level Haar transform wavelet images in combination with discriminant analysis, we obtained classification accuracies of 96.67 and 87.78% for the training and testing set (90 images each), respectively. We conclude that the best classifier of carcinomas in histological sections of breast tissue are the texture features from the second-level Haar transform wavelet images used in a discriminant function.http://dx.doi.org/10.1155/2005/526083 |
| spellingShingle | Hae-Gil Hwang Hyun-Ju Choi Byeong-Il Lee Hye-Kyoung Yoon Sang-Hee Nam Heung-Kook Choi Multi-Resolution Wavelet-Transformed Image Analysis of Histological Sections of Breast Carcinomas Cellular Oncology |
| title | Multi-Resolution Wavelet-Transformed Image Analysis of Histological Sections of Breast Carcinomas |
| title_full | Multi-Resolution Wavelet-Transformed Image Analysis of Histological Sections of Breast Carcinomas |
| title_fullStr | Multi-Resolution Wavelet-Transformed Image Analysis of Histological Sections of Breast Carcinomas |
| title_full_unstemmed | Multi-Resolution Wavelet-Transformed Image Analysis of Histological Sections of Breast Carcinomas |
| title_short | Multi-Resolution Wavelet-Transformed Image Analysis of Histological Sections of Breast Carcinomas |
| title_sort | multi resolution wavelet transformed image analysis of histological sections of breast carcinomas |
| url | http://dx.doi.org/10.1155/2005/526083 |
| work_keys_str_mv | AT haegilhwang multiresolutionwavelettransformedimageanalysisofhistologicalsectionsofbreastcarcinomas AT hyunjuchoi multiresolutionwavelettransformedimageanalysisofhistologicalsectionsofbreastcarcinomas AT byeongillee multiresolutionwavelettransformedimageanalysisofhistologicalsectionsofbreastcarcinomas AT hyekyoungyoon multiresolutionwavelettransformedimageanalysisofhistologicalsectionsofbreastcarcinomas AT sangheenam multiresolutionwavelettransformedimageanalysisofhistologicalsectionsofbreastcarcinomas AT heungkookchoi multiresolutionwavelettransformedimageanalysisofhistologicalsectionsofbreastcarcinomas |