EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SkinSwinViT: A Lightweight Transformer-Based Method for Multiclass Skin Lesion Classification with Enhanced Generalization Capabilities

Kun Tang, Jing Su, Ruihan Chen, Rui Huang, Ming Dai, Yongjiang Li

Applied Sciences · 08.05.2024 · 14 (10) · 4005

DOI: 10.3390/app14104005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 08.05.2024. Verfasst von Kun Tang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Ocean University, Guangdong Basic and Applied Basic Research Foundation, National College Students Innovation and Entrepreneurship Training Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent decades, skin cancer has emerged as a significant global health concern, demanding timely detection and effective therapeutic interventions. Automated image classification via computational algorithms holds substantial promise in significantly improving the efficacy of clinical diagnoses. This study is committed to mitigating the challenge of diagnostic accuracy in the classification of multiclass skin lesions. This endeavor is inherently formidable owing to the resemblances among various lesions and the constraints associated with extracting precise global and local image features within diverse dimensional spaces using conventional convolutional neural network methodologies. Consequently, this study introduces the SkinSwinViT methodology for skin lesion classification, a pioneering model grounded in the Swin Transformer framework featuring a global attention mechanism. Leveraging the inherent cross-window attention mechanism within the Swin Transformer architecture, the model adeptly captures local features and interdependencies within skin lesion images while additionally incorporating a global self-attention mechanism to discern overarching features and contextual information effectively. The evaluation of the model’s performance involved the ISIC2018 challenge dataset. Furthermore, data augmentation techniques augmented training dataset size and enhanced model performance. Experimental results highlight the superiority of the SkinSwinViT method, achieving notable metrics of accuracy, recall, precision, specificity, and F1 score at 97.88%, 97.55%, 97.83%, 99.36%, and 97.79%, respectively.

Förderung

  • Guangdong Ocean University
  • Guangdong Basic and Applied Basic Research Foundation
  • National College Students Innovation and Entrepreneurship Training Program
  • Guangdong Provincial Science and Technology Innovation Strategy
  • Guangdong Ocean University Undergraduate Innovation Team Project

Zitieren

APA

Tang, K., Su, J., Chen, R., Huang, R., Dai, M., & Li, Y. (2024). SkinSwinViT: A Lightweight Transformer-Based Method for Multiclass Skin Lesion Classification with Enhanced Generalization Capabilities. Applied Sciences, 14(10), 4005. https://doi.org/10.3390/app14104005

Vancouver

Tang K, Su J, Chen R, Huang R, Dai M, Li Y. SkinSwinViT: A Lightweight Transformer-Based Method for Multiclass Skin Lesion Classification with Enhanced Generalization Capabilities. Applied Sciences. 2024;14(10):4005. doi:10.3390/app14104005

BibTeX
@article{Tang2024,
  author = {Tang, Kun and Su, Jing and Chen, Ruihan and Huang, Rui and Dai, Ming and Li, Yongjiang},
  title = {SkinSwinViT: A Lightweight Transformer-Based Method for Multiclass Skin Lesion Classification with Enhanced Generalization Capabilities},
  journal = {Applied Sciences},
  year = {2024},
  volume = {14},
  number = {10},
  pages = {4005},
  doi = {10.3390/app14104005}
}
Kostenlos starten →