Multiscale morphology and SVM-based mammogram classification
International Journal of Engineering Approaches · 17.06.2026 · 3 (1) · 28-36
DOI: 10.66160/ijea.1882787 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Engineering Approaches, online erschienen am 17.06.2026. Verfasst von Canan Oral und 1 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben.
Abstract (Originalsprache)
Breast cancer is one of the most common diseases in women, and early diagnosis can significantly improve survival time and quality of life. This study proposes an effective computer-aided diagnosis (CAD) system for classifying mammogram images as normal or abnormal. The designed system consists of preprocessing based on multiscale morphological top-hat transformation, textural and spatial feature extraction, dimensionality reduction with principal component analysis (PCA), and support vector machine (SVM)-based classification stages. In the preprocessing step, a multiscale morphological enhancement technique was used to improve the image and remove noise. In the feature extraction stage, spatial and textural features were extracted from the enhanced mammogram images. In the classification stage, a SVM was used. Experimental studies were performed on the MIAS mammography database. Model performance was analyzed using a 5-fold cross-validation method to provide a more reliable assessment. The results showed that while an accuracy of 91.86% was obtained without PCA, the accuracy increased to 93.02% after PCA. Furthermore, ROC analysis revealed an improvement in classification performance and discrimination power after dimensionality reduction (AUC = 0.8939). The results demonstrate that the proposed method offers competitive, low-cost, and reliable performance, especially under limited data conditions, and can be used as a clinical decision support system for the early diagnosis of breast cancer.
Zitieren
APA
Oral, C., & Sezgin, H. (2026). Multiscale morphology and SVM-based mammogram classification. International Journal of Engineering Approaches, 3(1), 28-36. https://doi.org/10.66160/ijea.1882787
Vancouver
Oral C, Sezgin H. Multiscale morphology and SVM-based mammogram classification. International Journal of Engineering Approaches. 2026;3(1):28-36. doi:10.66160/ijea.1882787
BibTeX
@article{Oral2026,
author = {Oral, Canan and Sezgin, Hatice},
title = {Multiscale morphology and SVM-based mammogram classification},
journal = {International Journal of Engineering Approaches},
year = {2026},
volume = {3},
number = {1},
pages = {28--36},
doi = {10.66160/ijea.1882787}
}
EUVIMED