Hybrid discrete wavelet transform and texture analysis methods for feature extraction and classification of breast dynamic thermogram sequences
Breast cancer is a common cancer that hits women causing thousands of casualties every year. A cancerous tumor causes an increase of temperature near the region of the tumor. The heat generated by the temperature transferred to the skin surface. The temperature in the tumor area is warmer than in th...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Faculty of Computer Science and Information Technology, University of Malaya
2021
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/97571/ |
| _version_ | 1848862635877990400 |
|---|---|
| author | Mustaffa, Mas Rina Khalid, Fatimah C. Doraisamy, Shyamala Al-Rababah, Khaleel de Pina Júnior, Luís Filipe |
| author_facet | Mustaffa, Mas Rina Khalid, Fatimah C. Doraisamy, Shyamala Al-Rababah, Khaleel de Pina Júnior, Luís Filipe |
| author_sort | Mustaffa, Mas Rina |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Breast cancer is a common cancer that hits women causing thousands of casualties every year. A cancerous tumor causes an increase of temperature near the region of the tumor. The heat generated by the temperature transferred to the skin surface. The temperature in the tumor area is warmer than in the healthy area. Detecting breast cancer in early stages can save women’s lives and lower the burden on the cost. Thermography is an imaging technique used for breast cancer detection. A dynamic thermography technique which is used to generate infrared images over a fixed time measured in minutes to detect the difference between the normal and cancerous areas in images. In this research, we propose a methodology to deal with the changes of temperature in patient's breasts by defining a set of efficient features resulted from extraction and reduction of coefficients obtained from breast thermogram images followed by classification. Texture feature methods (Histogram of Oriented Gradients (HOG) and Discrete Curvelet transform) are applied separately using the HH (high-high) and HL (high-low) sub band images of Discrete Wavelet transform (DWT). HOG-based features and Curvelet features are extracted by reducing coefficients’ vectors returned by the two methods. Finally, Support Vector Machine (SVM) binary classifier is used to classify the images to either normal or abnormal. The proposed work has successfully achieved an Accuracy of 98.2%, Sensitivity of 97.7%, and Specificity of 98.2% through empirical studies using dynamic breast thermogram dataset. |
| first_indexed | 2025-11-15T13:20:10Z |
| format | Article |
| id | upm-97571 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T13:20:10Z |
| publishDate | 2021 |
| publisher | Faculty of Computer Science and Information Technology, University of Malaya |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-975712024-05-20T03:39:27Z http://psasir.upm.edu.my/id/eprint/97571/ Hybrid discrete wavelet transform and texture analysis methods for feature extraction and classification of breast dynamic thermogram sequences Mustaffa, Mas Rina Khalid, Fatimah C. Doraisamy, Shyamala Al-Rababah, Khaleel de Pina Júnior, Luís Filipe Breast cancer is a common cancer that hits women causing thousands of casualties every year. A cancerous tumor causes an increase of temperature near the region of the tumor. The heat generated by the temperature transferred to the skin surface. The temperature in the tumor area is warmer than in the healthy area. Detecting breast cancer in early stages can save women’s lives and lower the burden on the cost. Thermography is an imaging technique used for breast cancer detection. A dynamic thermography technique which is used to generate infrared images over a fixed time measured in minutes to detect the difference between the normal and cancerous areas in images. In this research, we propose a methodology to deal with the changes of temperature in patient's breasts by defining a set of efficient features resulted from extraction and reduction of coefficients obtained from breast thermogram images followed by classification. Texture feature methods (Histogram of Oriented Gradients (HOG) and Discrete Curvelet transform) are applied separately using the HH (high-high) and HL (high-low) sub band images of Discrete Wavelet transform (DWT). HOG-based features and Curvelet features are extracted by reducing coefficients’ vectors returned by the two methods. Finally, Support Vector Machine (SVM) binary classifier is used to classify the images to either normal or abnormal. The proposed work has successfully achieved an Accuracy of 98.2%, Sensitivity of 97.7%, and Specificity of 98.2% through empirical studies using dynamic breast thermogram dataset. Faculty of Computer Science and Information Technology, University of Malaya 2021-12-31 Article PeerReviewed Mustaffa, Mas Rina and Khalid, Fatimah and C. Doraisamy, Shyamala and Al-Rababah, Khaleel and de Pina Júnior, Luís Filipe (2021) Hybrid discrete wavelet transform and texture analysis methods for feature extraction and classification of breast dynamic thermogram sequences. Malaysian Journal of Computer Science, 29 (spec.2). 116 - 131. ISSN 0127-9084 https://ejournal.um.edu.my/index.php/MJCS/article/view/34403 10.22452/mjcs.sp2021no2.8 |
| spellingShingle | Mustaffa, Mas Rina Khalid, Fatimah C. Doraisamy, Shyamala Al-Rababah, Khaleel de Pina Júnior, Luís Filipe Hybrid discrete wavelet transform and texture analysis methods for feature extraction and classification of breast dynamic thermogram sequences |
| title | Hybrid discrete wavelet transform and texture analysis methods for feature extraction and classification of breast dynamic thermogram sequences |
| title_full | Hybrid discrete wavelet transform and texture analysis methods for feature extraction and classification of breast dynamic thermogram sequences |
| title_fullStr | Hybrid discrete wavelet transform and texture analysis methods for feature extraction and classification of breast dynamic thermogram sequences |
| title_full_unstemmed | Hybrid discrete wavelet transform and texture analysis methods for feature extraction and classification of breast dynamic thermogram sequences |
| title_short | Hybrid discrete wavelet transform and texture analysis methods for feature extraction and classification of breast dynamic thermogram sequences |
| title_sort | hybrid discrete wavelet transform and texture analysis methods for feature extraction and classification of breast dynamic thermogram sequences |
| url | http://psasir.upm.edu.my/id/eprint/97571/ http://psasir.upm.edu.my/id/eprint/97571/ http://psasir.upm.edu.my/id/eprint/97571/ |