EUVIMEDEUVIMED entdecken
Crossref

Automated Diagnosis System for Early Breast Cancer Detection

Jamal Othman Ali, Alan Anwer Abdulla

Academic Journal of International University of Erbil · 25.05.2026

DOI: 10.63841/iue326995 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Journal of International University of Erbil, online erschienen am 25.04.2026. Verfasst von Jamal Othman Ali und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Given that manual disease diagnosis and treatment determination are time-consuming, expensive, and demand skilled professionals, developments in computer technology and medical imaging processing within healthcare environments have improved diagnostic accuracy and early disease detection. Since they overcome the limitations associated with manual diagnostic approaches, automated or computer-assisted diagnostic systems can serve as viable alternatives. These systems are known as computer-aided diagnostic (CAD) systems and are commonly utilised for cancer diagnosis and other medical conditions. Digital image processing plays a vital role in handling and examining medical images for cancer identification and detection. This research introduces a CAD system designed for early breast cancer detection. Following the segmentation of the region of interest (ROI) from mammographic images through thresholding segmentation methods, texture and shape characteristics are extracted. For textural feature extraction, Tamura and Bag of Visual Words (BoVW) techniques are utilised. Additionally, shape-based statistical features, including compactness, sphericity, area, and elongation, are extracted. The images are subsequently categorized as normal or abnormal through k-nearest neighbour (kNN) and support vector machine (SVM) classification algorithms based on the extracted features. Comprehensive experiments conducted on the well-known Mammographic Image Analysis Society (MIAS) mammography image dataset were used to assess the proposed system's performance. The experimental results demonstrate that the proposed system achieves superior performance compared to other existing systems, with an accuracy rate of 99.6%.

Zitieren

APA

Ali, J. O., & Abdulla, A. A. (2026). Automated Diagnosis System for Early Breast Cancer Detection. Academic Journal of International University of Erbil. https://doi.org/10.63841/iue326995

Vancouver

Ali JO, Abdulla AA. Automated Diagnosis System for Early Breast Cancer Detection. Academic Journal of International University of Erbil. 2026. doi:10.63841/iue326995

BibTeX
@article{Ali2026,
  author = {Ali, Jamal Othman and Abdulla, Alan Anwer},
  title = {Automated Diagnosis System for Early Breast Cancer Detection},
  journal = {Academic Journal of International University of Erbil},
  year = {2026},
  doi = {10.63841/iue326995}
}
Kostenlos starten →