EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Transfer Learning with VGG16 on Merged Ultrasound Datasets for Automated Breast Cancer Classification with Grad-CAM Interpretability

Melwin D Souza, N. Kumaresh, Swapna Siddamsetti, Sookshma Adiga, Sudhakar K, Suren Kumar Sahu, A. Anandh

Journal of Robotics and Control (JRC) · 13.03.2026 · 7 (1) · 3383-3392

DOI: 10.18196/jrc.v7i1.26501 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Robotics and Control (JRC), online erschienen am 13.03.2026. Verfasst von Melwin D Souza und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Breast cancer detection using ultrasound is often hindered by speckle noise, image variability, and reliance on subjective expert interpretation, particularly in women with dense breast tissue. To address these challenges, this study proposes a deep learning-based classification system using a pre-trained VGG16 model with transfer learning, enhanced by median filtering for noise reduction and Grad-CAM for interpretability. The model architecture consists of a frozen convolutional base with a lightweight fully connected classifier designed to minimize overfitting. We introduce a novel integration strategy by merging the BUSI and Mendeley ultrasound datasets to evaluate model generalization across diverse imaging sources. The system was trained and tested on 897 breast ultrasound images, achieving a testing accuracy of 91.1%, sensitivity of 94%, specificity of 88.75%, F1-score of 0.89, and an AUC of 0.97. This study contributes a robust, interpretable, and computationally efficient deep learning pipeline for breast cancer diagnosis that leverages dataset integration, optimized preprocessing, and attention-based visualization. Grad-CAM overlays highlight class-discriminative regions in both benign and malignant cases, supporting clinical explainability. The system’s accuracy and transparency suggest its potential for real-world application, particularly in settings where access to expert radiologists is limited

Zitieren

APA

Souza, M. D., Kumaresh, N., Siddamsetti, S., Adiga, S., K, S., Sahu, S. K., & Anandh, A. (2026). Transfer Learning with VGG16 on Merged Ultrasound Datasets for Automated Breast Cancer Classification with Grad-CAM Interpretability. Journal of Robotics and Control (JRC), 7(1), 3383-3392. https://doi.org/10.18196/jrc.v7i1.26501

Vancouver

Souza MD, Kumaresh N, Siddamsetti S, Adiga S, K S, Sahu SK, et al. Transfer Learning with VGG16 on Merged Ultrasound Datasets for Automated Breast Cancer Classification with Grad-CAM Interpretability. Journal of Robotics and Control (JRC). 2026;7(1):3383-3392. doi:10.18196/jrc.v7i1.26501

BibTeX
@article{Souza2026,
  author = {Souza, Melwin D and Kumaresh, N. and Siddamsetti, Swapna and Adiga, Sookshma and K, Sudhakar and Sahu, Suren Kumar and Anandh, A.},
  title = {Transfer Learning with VGG16 on Merged Ultrasound Datasets for Automated Breast Cancer Classification with Grad-CAM Interpretability},
  journal = {Journal of Robotics and Control (JRC)},
  year = {2026},
  volume = {7},
  number = {1},
  pages = {3383--3392},
  doi = {10.18196/jrc.v7i1.26501}
}
Kostenlos starten →