Comparative analysis of breast cancer detection in mammograms and thermograms
Само за регистроване кориснике
2015
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
In this paper, we present a system based on feature extraction techniques for detecting abnormal patterns in digital mammograms and thermograms. A comparative study of texture-analysis methods is performed for three image groups: mammograms from the Mammographic Image Analysis Society mammographic database; digital mammograms from the local database; and thermography images of the breast. Also, we present a procedure for the automatic separation of the breast region from the mammograms. Computed features based on gray-level co-occurrence matrices are used to evaluate the effectiveness of textural information possessed by mass regions. A total of 20 texture features are extracted from the region of interest. The ability of feature set in differentiating abnormal from normal tissue is investigated using a support vector machine classifier, Naive Bayes classifier and K-Nearest Neighbor classifier. To evaluate the classification performance, five-fold cross-validation method and receiver o...perating characteristic analysis was performed.
Кључне речи:
breast cancer / mammography / region of interest / texture analysis / thermographyИзвор:
Biomedical Engineering-Biomedizinische Technik, 2015, 60, 1, 49-56Издавач:
- Walter De Gruyter Gmbh, Berlin
DOI: 10.1515/bmt-2014-0047
ISSN: 0013-5585
PubMed: 25720034
WoS: 000350406100006
Scopus: 2-s2.0-84925344935
Колекције
Институција/група
Geografski fakultetTY - JOUR AU - Milošević, Marina AU - Janković, Dragan AU - Peulić, Aleksandar PY - 2015 UR - https://gery.gef.bg.ac.rs/handle/123456789/718 AB - In this paper, we present a system based on feature extraction techniques for detecting abnormal patterns in digital mammograms and thermograms. A comparative study of texture-analysis methods is performed for three image groups: mammograms from the Mammographic Image Analysis Society mammographic database; digital mammograms from the local database; and thermography images of the breast. Also, we present a procedure for the automatic separation of the breast region from the mammograms. Computed features based on gray-level co-occurrence matrices are used to evaluate the effectiveness of textural information possessed by mass regions. A total of 20 texture features are extracted from the region of interest. The ability of feature set in differentiating abnormal from normal tissue is investigated using a support vector machine classifier, Naive Bayes classifier and K-Nearest Neighbor classifier. To evaluate the classification performance, five-fold cross-validation method and receiver operating characteristic analysis was performed. PB - Walter De Gruyter Gmbh, Berlin T2 - Biomedical Engineering-Biomedizinische Technik T1 - Comparative analysis of breast cancer detection in mammograms and thermograms VL - 60 IS - 1 SP - 49 EP - 56 DO - 10.1515/bmt-2014-0047 UR - https://hdl.handle.net/21.15107/rcub_gery_718 ER -
@article{ author = "Milošević, Marina and Janković, Dragan and Peulić, Aleksandar", year = "2015", abstract = "In this paper, we present a system based on feature extraction techniques for detecting abnormal patterns in digital mammograms and thermograms. A comparative study of texture-analysis methods is performed for three image groups: mammograms from the Mammographic Image Analysis Society mammographic database; digital mammograms from the local database; and thermography images of the breast. Also, we present a procedure for the automatic separation of the breast region from the mammograms. Computed features based on gray-level co-occurrence matrices are used to evaluate the effectiveness of textural information possessed by mass regions. A total of 20 texture features are extracted from the region of interest. The ability of feature set in differentiating abnormal from normal tissue is investigated using a support vector machine classifier, Naive Bayes classifier and K-Nearest Neighbor classifier. To evaluate the classification performance, five-fold cross-validation method and receiver operating characteristic analysis was performed.", publisher = "Walter De Gruyter Gmbh, Berlin", journal = "Biomedical Engineering-Biomedizinische Technik", title = "Comparative analysis of breast cancer detection in mammograms and thermograms", volume = "60", number = "1", pages = "49-56", doi = "10.1515/bmt-2014-0047", url = "https://hdl.handle.net/21.15107/rcub_gery_718" }
Milošević, M., Janković, D.,& Peulić, A.. (2015). Comparative analysis of breast cancer detection in mammograms and thermograms. in Biomedical Engineering-Biomedizinische Technik Walter De Gruyter Gmbh, Berlin., 60(1), 49-56. https://doi.org/10.1515/bmt-2014-0047 https://hdl.handle.net/21.15107/rcub_gery_718
Milošević M, Janković D, Peulić A. Comparative analysis of breast cancer detection in mammograms and thermograms. in Biomedical Engineering-Biomedizinische Technik. 2015;60(1):49-56. doi:10.1515/bmt-2014-0047 https://hdl.handle.net/21.15107/rcub_gery_718 .
Milošević, Marina, Janković, Dragan, Peulić, Aleksandar, "Comparative analysis of breast cancer detection in mammograms and thermograms" in Biomedical Engineering-Biomedizinische Technik, 60, no. 1 (2015):49-56, https://doi.org/10.1515/bmt-2014-0047 ., https://hdl.handle.net/21.15107/rcub_gery_718 .