EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Boosting Skin Cancer Classification: A Multi-Scale Attention and Ensemble Approach with Vision Transformers

Guang Yang iD, Suhuai Luo, Peter Greer iD

Sensors · 15.04.2025 · 25 (8) · 2479

DOI: 10.3390/s25082479 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.04.2025. Verfasst von Guang Yang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Physical Sciences, The University of Newcastle, Callaghan, NSW 2308, Australia. Hauptthemen laut MEDLINE: Skin Neoplasms, Melanoma. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skin cancer is a significant global health concern, with melanoma being the most dangerous form, responsible for the majority of skin cancer-related deaths. Early detection of skin cancer is critical, as it can drastically improve survival rates. While deep learning models have achieved impressive results in skin cancer classification, there remain challenges in accurately distinguishing between benign and malignant lesions. In this study, we introduce a novel multi-scale attention-based performance booster inspired by the Vision Transformer (ViT) architecture, which enhances the accuracy of both ViT and convolutional neural network (CNN) models. By leveraging attention maps to identify discriminative regions within skin lesion images, our method improves the models’ focus on diagnostically relevant areas. Additionally, we employ ensemble learning techniques to combine the outputs of several deep learning models using majority voting. Our skin cancer classifier, consisting of ViT and EfficientNet models, achieved a classification accuracy of 95.05% on the ISIC2018 dataset, outperforming individual models. The results demonstrate the effectiveness of integrating attention-based multi-scale learning and ensemble methods in skin cancer classification.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Skin NeoplasmsMelanomaHumansNeural Networks, ComputerDeep LearningAlgorithmsAttention

Stichwörter der Autor:innen

deep learningimage processingneural networksskin cancer classificationtransformer

Autor:innen und Institutionen

  • School of Information and Physical Sciences, The University of Newcastle, Callaghan, NSW 2308, Australia.
  • School of Information and Physical Sciences, College of Engineering, Science and Environment, The University of Newcastle, Callaghan NSW 2308, Australia.

ORCID-Profile: Guang Yang, Peter Greer

Zitieren

APA

Yang, G., Luo, S., & Greer, P. (2025). Boosting Skin Cancer Classification: A Multi-Scale Attention and Ensemble Approach with Vision Transformers. Sensors, 25(8), 2479. https://doi.org/10.3390/s25082479

Vancouver

Yang G, Luo S, Greer P. Boosting Skin Cancer Classification: A Multi-Scale Attention and Ensemble Approach with Vision Transformers. Sensors. 2025;25(8):2479. doi:10.3390/s25082479

BibTeX
@article{Yang2025,
  author = {Yang, Guang and Luo, Suhuai and Greer, Peter},
  title = {Boosting Skin Cancer Classification: A Multi-Scale Attention and Ensemble Approach with Vision Transformers},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {8},
  pages = {2479},
  doi = {10.3390/s25082479}
}
Kostenlos starten →