Application of Data Mining Algorithms for Mammogram Classification
Abstract
One of the leading causes of cancer death among women is breast cancer. In our work we aim at proposing a prototype of a medical expert system (based on data mining techniques) that could significantly aid medical experts to detect breast cancer. This paper presents the CAD (computer aided diagnosis) system for the detection of normal and abnormal pattern in the breast. The proposed system consists of four major steps: the image preprocessing, the feature extraction, the feature selection and the classification process that classifies mammogram into normal (without tumor) and abnormal (with tumor) pattern. After removing noise from mammogram using the Discrete Wavelet Transformation (DWT), first is selected the region of interest (ROI). By identifying the boundary of the breast, it is possible to remove any artifact present outside the breast area, such as patient markings. Then, a total of 20 GLCM features are extracted from the ROI, which were used as inputs for classification algori...thms. In order to compare the classification results, we used seven different classifiers. Normal breast images and breast image with masses (total 322 images) used as input images in this study are taken from the mini-MIAS database.
Source:
2013 IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE), 2013Publisher:
- IEEE, New York
Funding / projects:
- Semantic Infostructure interlinking an open source Finite Element tool and libraries with a model repository for the multi-scale Modelling and 3d visualization of the inner-ear (EU-600933)
- Multiscale Methods and Their Applicatios in Nanomedicine (RS-174028)
- Application of biomedical engineering for preclinical and clinical practice (RS-41007)
Collections
Institution/Community
Geografski fakultetTY - CONF AU - Radović, Miloš AU - Đoković, Marina AU - Peulić, Aleksandar AU - Filipović, Nenad PY - 2013 UR - https://gery.gef.bg.ac.rs/handle/123456789/603 AB - One of the leading causes of cancer death among women is breast cancer. In our work we aim at proposing a prototype of a medical expert system (based on data mining techniques) that could significantly aid medical experts to detect breast cancer. This paper presents the CAD (computer aided diagnosis) system for the detection of normal and abnormal pattern in the breast. The proposed system consists of four major steps: the image preprocessing, the feature extraction, the feature selection and the classification process that classifies mammogram into normal (without tumor) and abnormal (with tumor) pattern. After removing noise from mammogram using the Discrete Wavelet Transformation (DWT), first is selected the region of interest (ROI). By identifying the boundary of the breast, it is possible to remove any artifact present outside the breast area, such as patient markings. Then, a total of 20 GLCM features are extracted from the ROI, which were used as inputs for classification algorithms. In order to compare the classification results, we used seven different classifiers. Normal breast images and breast image with masses (total 322 images) used as input images in this study are taken from the mini-MIAS database. PB - IEEE, New York C3 - 2013 IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE) T1 - Application of Data Mining Algorithms for Mammogram Classification UR - https://hdl.handle.net/21.15107/rcub_gery_603 ER -
@conference{ author = "Radović, Miloš and Đoković, Marina and Peulić, Aleksandar and Filipović, Nenad", year = "2013", abstract = "One of the leading causes of cancer death among women is breast cancer. In our work we aim at proposing a prototype of a medical expert system (based on data mining techniques) that could significantly aid medical experts to detect breast cancer. This paper presents the CAD (computer aided diagnosis) system for the detection of normal and abnormal pattern in the breast. The proposed system consists of four major steps: the image preprocessing, the feature extraction, the feature selection and the classification process that classifies mammogram into normal (without tumor) and abnormal (with tumor) pattern. After removing noise from mammogram using the Discrete Wavelet Transformation (DWT), first is selected the region of interest (ROI). By identifying the boundary of the breast, it is possible to remove any artifact present outside the breast area, such as patient markings. Then, a total of 20 GLCM features are extracted from the ROI, which were used as inputs for classification algorithms. In order to compare the classification results, we used seven different classifiers. Normal breast images and breast image with masses (total 322 images) used as input images in this study are taken from the mini-MIAS database.", publisher = "IEEE, New York", journal = "2013 IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE)", title = "Application of Data Mining Algorithms for Mammogram Classification", url = "https://hdl.handle.net/21.15107/rcub_gery_603" }
Radović, M., Đoković, M., Peulić, A.,& Filipović, N.. (2013). Application of Data Mining Algorithms for Mammogram Classification. in 2013 IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE) IEEE, New York.. https://hdl.handle.net/21.15107/rcub_gery_603
Radović M, Đoković M, Peulić A, Filipović N. Application of Data Mining Algorithms for Mammogram Classification. in 2013 IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE). 2013;. https://hdl.handle.net/21.15107/rcub_gery_603 .
Radović, Miloš, Đoković, Marina, Peulić, Aleksandar, Filipović, Nenad, "Application of Data Mining Algorithms for Mammogram Classification" in 2013 IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE) (2013), https://hdl.handle.net/21.15107/rcub_gery_603 .