EUVIMEDEUVIMED entdecken
Crossref

Empowering Early Diagnosis: Convolutional Neural Networks In Breast Cancer Detection

Megha R. Dave, Dr. Manish M. Patel

International Journal of Drug Delivery Technology · 11.05.2026 · 16 (26s)

DOI: 10.25258/ijddt.16.26s.30 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 11.05.2026. Verfasst von Megha R. Dave und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Breast cancer remains one of the leading causes of death among women world-wide, with early detection being crucial for improving patient outcomes. Mammography has been the primary method for breast cancer screening, but it has limitations, particularly in women with denser breast tissue. To address this, several modalities such as ultrasonography, thermography, and wearable biosensors like smart bras have emerged as non-invasive and cost-effective alternatives. These technologies, when coupled with ai algorithms (e.g., catboost) and deep learning-based systems (e.g., yolo-v4), show promising potential in improving the accuracy of tumor detection and classification. Additionally, advanced machine learning techniques like svm, knn, and cnns have been employed to diagnose breast cancer using clinical and imaging features, achieving impressive accuracy rates. However, classical algorithms face challenges in terms of computational complexity, motivating the use of quantum machine learning to accelerate computational processes. The integration of these technologies offers an exciting prospect for revolutionizing breast cancer diagnosis by reducing diagnostic errors, enhancing screening rates, and ultimately improving patient survival. This study presents various approaches, including cnn-based models, transfer learning, and a combination of deep learning methods, to improve breast cancer classification and detection performance. Evaluation metrics such as accuracy, precision, recall, and roc curves were used to assess model effectiveness. The achieved results include a model accuracy of 0.9995, with a validation loss of 0.6800 and a validation accuracy of 0.7651.

Zitieren

APA

Dave, M. R., & Patel, D. M. M. (2026). Empowering Early Diagnosis: Convolutional Neural Networks In Breast Cancer Detection. International Journal of Drug Delivery Technology, 16(26s). https://doi.org/10.25258/ijddt.16.26s.30

Vancouver

Dave MR, Patel DMM. Empowering Early Diagnosis: Convolutional Neural Networks In Breast Cancer Detection. International Journal of Drug Delivery Technology. 2026;16(26s). doi:10.25258/ijddt.16.26s.30

BibTeX
@article{Dave2026,
  author = {Dave, Megha R. and Patel, Dr. Manish M.},
  title = {Empowering Early Diagnosis: Convolutional Neural Networks In Breast Cancer Detection},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {26s},
  doi = {10.25258/ijddt.16.26s.30}
}
Kostenlos starten →