EUVIMEDEUVIMED entdecken
Crossref

Detection and Classification of Breast Cancer from Mammogram Images using Adaptive Deep Learning Technique

B.V.S.N. Lakshmi, P. Lakshmi Prasanna, D. Noorjaha, B. Mokshagna

International Journal of Engineering & Extended Technologies Research · 28.03.2026 · 08 (02)

DOI: 10.15662/ijeetr.2026.0802167 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 28.03.2026. Verfasst von B.V.S.N. Lakshmi und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Breast cancer has been one of the top causes of death among women in the world and hence early and accurate diagnosis is essential in the process of effective diagnosis and treatment planning. Even though mammogram image is the key in the diagnosis of the aberrant tissue pattern, it is time consuming and subject to human error. To eliminate these challenges, an automated system of detecting and classifying breast cancer based on mammography images is developed using a flexible DL. In order to increase model generalization, data preparation steps such as scaling, data normalization, and data augmentation are undertaken upon the prepared dataset containing labeled images to be classified during preparation and detection bounding box annotations to be identified during preparation. Among the many learning strategies that the framework uses in classification, there are Adaptive CNN, CRNN + LSTM), SVM with (SVM+MLP), Hierarchical Clustering with GLCM, and several parameter transfer learning models such as Xception, EfficientNetB0, and DenseNet121. In order to detect abnormalities, suspicious regions in mammography images are detected with the help of object detection models of the YOLO family, including YOLOv3, YOLOv5, YOLOv8, and YOLOv11. Experimental analysis indicates that YOLOv3 works best with a precision of 71.2 and mAP of 52.4 and also DenseNet121 has 99.8 as its highest accuracy in classification. In addition, explainable AI with Grad-CAM is built to detect discriminative areas that affect model predictions. To report on diagnostic automatically and infer in real time, the trained models are integrated into a web interface based on Flask

Zitieren

APA

Lakshmi, B., Prasanna, P. L., Noorjaha, D., & Mokshagna, B. (2026). Detection and Classification of Breast Cancer from Mammogram Images using Adaptive Deep Learning Technique. International Journal of Engineering & Extended Technologies Research, 08(02). https://doi.org/10.15662/ijeetr.2026.0802167

Vancouver

Lakshmi B, Prasanna PL, Noorjaha D, Mokshagna B. Detection and Classification of Breast Cancer from Mammogram Images using Adaptive Deep Learning Technique. International Journal of Engineering & Extended Technologies Research. 2026;08(02). doi:10.15662/ijeetr.2026.0802167

BibTeX
@article{Lakshmi2026,
  author = {Lakshmi, B.V.S.N. and Prasanna, P. Lakshmi and Noorjaha, D. and Mokshagna, B.},
  title = {Detection and Classification of Breast Cancer from Mammogram Images using Adaptive Deep Learning Technique},
  journal = {International Journal of Engineering & Extended Technologies Research},
  year = {2026},
  volume = {08},
  number = {02},
  doi = {10.15662/ijeetr.2026.0802167}
}
Kostenlos starten →