EXTENDED MAMMOGRAM CLASSIFICATION FROM TEXTURAL FEATURES
The efficient analysis of digital mammograms has an important role in the early detection of breast cancer and can lead to a higher percentage of recovery. This paper presents an extended computer-aided diagnosis system for the classification of mammograms into three classes (normal, benign and mal...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Babes-Bolyai University, Cluj-Napoca
2023-02-01
|
| Series: | Studia Universitatis Babes-Bolyai: Series Informatica |
| Subjects: | |
| Online Access: | http://193.231.18.162/index.php/subbinformatica/article/view/5799 |
| _version_ | 1797322201514377216 |
|---|---|
| author | Adél BAJCSI Camelia CHIRA Anca ANDREICA |
| author_facet | Adél BAJCSI Camelia CHIRA Anca ANDREICA |
| author_sort | Adél BAJCSI |
| collection | DOAJ |
| description |
The efficient analysis of digital mammograms has an important role in the early detection of breast cancer and can lead to a higher percentage of recovery. This paper presents an extended computer-aided diagnosis system for the classification of mammograms into three classes (normal, benign and malignant). The performance of the system is evaluated for two different mammogram databases (MIAS and DDSM) in order to assess its robustness. We discuss the changes required in the system, particularly at the level of the image preprocessing and feature extraction. Computational experiments are performed based on different methods for feature extraction, selection and classification. The results indicate an accuracy of 66.95% for the MIAS dataset and 54.1% for DDSM obtained using genetic algorithm based feature selection and Random Forest classification.
Received by the editors: 20 September 2022.
2010 Mathematics Subject Classification. 68T35.
1998 CR Categories and Descriptors. I.2.1 [Artifical Intelligence]: Applications and Expert Systems - Medicine and science; I.2.6 [Artifical Intelligence]: Learning - Knowledge acquisition; I.4.7 [Image Processing and Computer Vision]: Feature Measurement - Feature representation.
|
| first_indexed | 2024-03-08T05:10:47Z |
| format | Article |
| id | doaj.art-03a4ff0ea8f64fcca1911e336453b75e |
| institution | Directory Open Access Journal |
| issn | 2065-9601 |
| language | English |
| last_indexed | 2024-03-08T05:10:47Z |
| publishDate | 2023-02-01 |
| publisher | Babes-Bolyai University, Cluj-Napoca |
| record_format | Article |
| series | Studia Universitatis Babes-Bolyai: Series Informatica |
| spelling | doaj.art-03a4ff0ea8f64fcca1911e336453b75e2024-02-07T10:03:30ZengBabes-Bolyai University, Cluj-NapocaStudia Universitatis Babes-Bolyai: Series Informatica2065-96012023-02-0167210.24193/subbi.2022.2.01EXTENDED MAMMOGRAM CLASSIFICATION FROM TEXTURAL FEATURESAdél BAJCSI0Camelia CHIRA1Anca ANDREICA2Faculty of Mathematics and Computer Science, Babeș-Bolyai University, Cluj-Napoca, Romania. Email: adel.bajcsi@ubbcluj.ro.Faculty of Mathematics and Computer Science, Babeș-Bolyai University, Cluj-Napoca, Romania. Email: camelia.chira@ubbcluj.ro.Faculty of Mathematics and Computer Science, Babeș-Bolyai University, Cluj-Napoca, Romania. Email: anca.andreica@ubbcluj.ro. The efficient analysis of digital mammograms has an important role in the early detection of breast cancer and can lead to a higher percentage of recovery. This paper presents an extended computer-aided diagnosis system for the classification of mammograms into three classes (normal, benign and malignant). The performance of the system is evaluated for two different mammogram databases (MIAS and DDSM) in order to assess its robustness. We discuss the changes required in the system, particularly at the level of the image preprocessing and feature extraction. Computational experiments are performed based on different methods for feature extraction, selection and classification. The results indicate an accuracy of 66.95% for the MIAS dataset and 54.1% for DDSM obtained using genetic algorithm based feature selection and Random Forest classification. Received by the editors: 20 September 2022. 2010 Mathematics Subject Classification. 68T35. 1998 CR Categories and Descriptors. I.2.1 [Artifical Intelligence]: Applications and Expert Systems - Medicine and science; I.2.6 [Artifical Intelligence]: Learning - Knowledge acquisition; I.4.7 [Image Processing and Computer Vision]: Feature Measurement - Feature representation. http://193.231.18.162/index.php/subbinformatica/article/view/5799Breast cancer detection, Mammogram classification, GLRLM, Feature selection, Random Forests, MIAS, DDSM |
| spellingShingle | Adél BAJCSI Camelia CHIRA Anca ANDREICA EXTENDED MAMMOGRAM CLASSIFICATION FROM TEXTURAL FEATURES Studia Universitatis Babes-Bolyai: Series Informatica Breast cancer detection, Mammogram classification, GLRLM, Feature selection, Random Forests, MIAS, DDSM |
| title | EXTENDED MAMMOGRAM CLASSIFICATION FROM TEXTURAL FEATURES |
| title_full | EXTENDED MAMMOGRAM CLASSIFICATION FROM TEXTURAL FEATURES |
| title_fullStr | EXTENDED MAMMOGRAM CLASSIFICATION FROM TEXTURAL FEATURES |
| title_full_unstemmed | EXTENDED MAMMOGRAM CLASSIFICATION FROM TEXTURAL FEATURES |
| title_short | EXTENDED MAMMOGRAM CLASSIFICATION FROM TEXTURAL FEATURES |
| title_sort | extended mammogram classification from textural features |
| topic | Breast cancer detection, Mammogram classification, GLRLM, Feature selection, Random Forests, MIAS, DDSM |
| url | http://193.231.18.162/index.php/subbinformatica/article/view/5799 |
| work_keys_str_mv | AT adelbajcsi extendedmammogramclassificationfromtexturalfeatures AT cameliachira extendedmammogramclassificationfromtexturalfeatures AT ancaandreica extendedmammogramclassificationfromtexturalfeatures |