EUVIMEDEUVIMED entdecken
Crossref

An Intelligent Skin Cancer Diagnosis System Using Hybrid EfficientNet–ResNet Ensemble Deep Learning

Rutuja Chavare, Shankar Pujari

Dandao Xuebao/Journal of Ballistics · 22.06.2026 · 38 (2) · 950-960

DOI: 10.52783/dxjb.v38.440 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dandao Xuebao/Journal of Ballistics, online erschienen am 22.06.2026. Verfasst von Rutuja Chavare und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Environmental and lifestyle-related factors like extreme exposure to UV rays, loss of ozone, pollution and hereditary factors are contributing to the rise in skin cancer across the world, which has become one of the most common cancers worldwide. Typical diagnosis methods include a dermatologist's visual examination and biopsy. While these techniques are effective, they can be time-consuming, intrusive and heavily reliant on clinical expertise, making intelligent computer-assisted diagnostic tools suitable for assisting clinicians in making faster, more precise decisions. In this research an ensemble based deep learning framework is proposed to detect and classify skin cancer from dermoscopic images. The proposed system is a combination of the EfficientNet and ResNet architectures, each known for its robust feature extraction capabilities, which aim to enhance the performance of the classification task and ensure system robustness. EfficientNet and ResNet combination of these two architectures in a unified ensemble model allows for the benefits of both networks to be combined, leading to improved prediction accuracy and reduced misclassification. The ensemble approach is very well suited for the cases where seemingly different appearances of lesions are encountered, such as differences in color, texture, shape and size, which are common in skin cancer analysis. In general, the proposed ensemble deep learning model showcases the strong potential of artificial intelligence in improving the field of medical imaging and to support real-time clinical decision making to aid in better patient care and survival rates.

Zitieren

APA

Chavare, R., & Pujari, S. (2026). An Intelligent Skin Cancer Diagnosis System Using Hybrid EfficientNet–ResNet Ensemble Deep Learning. Dandao Xuebao/Journal of Ballistics, 38(2), 950-960. https://doi.org/10.52783/dxjb.v38.440

Vancouver

Chavare R, Pujari S. An Intelligent Skin Cancer Diagnosis System Using Hybrid EfficientNet–ResNet Ensemble Deep Learning. Dandao Xuebao/Journal of Ballistics. 2026;38(2):950-960. doi:10.52783/dxjb.v38.440

BibTeX
@article{Chavare2026,
  author = {Chavare, Rutuja and Pujari, Shankar},
  title = {An Intelligent Skin Cancer Diagnosis System Using Hybrid EfficientNet–ResNet Ensemble Deep Learning},
  journal = {Dandao Xuebao/Journal of Ballistics},
  year = {2026},
  volume = {38},
  number = {2},
  pages = {950--960},
  doi = {10.52783/dxjb.v38.440}
}
Kostenlos starten →