EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Ingeniously Designed Skin Lesion Classification Model Across Clinical and Dermatoscopic Datasets

Ying Huang, Zhishuo Zhang iD, Xin Ran iD, Kaiwen Zhuang iD, Yuping Ran iD

Diagnostics · 11.08.2025 · 15 (16) · 2011

DOI: 10.3390/diagnostics15162011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 11.08.2025. Verfasst von Ying Huang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Dermatovenereology, West China Hospital, Sichuan University, Chengdu 610041, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 135 project for disciplines of excellence-Clinical Research Incubation Project, National Key Research and Development Program of China, 135 projects for disciplines of excellence—Clinical Research Incubation Project, West China Hospital, Sichuan University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Skin cancer diagnosis faces critical challenges due to the visual similarity of lesions and dataset limitations.

Methods

This study introduces HybridSkinFormer, a robust deep learning model designed to classify skin lesions from both clinical and dermatoscopic images. The model employs a two-stage architecture: a multi-layer ConvNet for local feature extraction and a residual-learnable multi-head attention module for global context fusion. A novel activation function (StarPRelu) and Enhanced Focal Loss (EFLoss) address neuron death and class imbalance, respectively.

Results

Evaluated on a hybrid dataset (37,483 images across nine classes), HybridSkinFormer achieved state-of-the-art performance with an overall accuracy of 94.2%, a macro precision of 91.1%, and a macro recall of 91.0%, outperforming nine CNN and ViT baselines.

Conclusions

Its ability to handle multi-modality data and mitigate imbalance highlights its clinical utility for early cancer detection in resource-constrained settings.

Schlagwörter

Stichwörter der Autor:innen

adaptively learnable activation functionhybird feature extractionskin lesion classification

Autor:innen und Institutionen

  • Department of Dermatovenereology, West China Hospital, Sichuan University, Chengdu 610041, China.
  • School of Information and Software Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu 610054, China.

ORCID-Profile: Zhishuo Zhang, Xin Ran, Kaiwen Zhuang, Yuping Ran

Förderung

  • 135 project for disciplines of excellence-Clinical Research Incubation Project
  • National Key Research and Development Program of China
  • 135 projects for disciplines of excellence—Clinical Research Incubation Project, West China Hospital, Sichuan University

Zitieren

APA

Huang, Y., Zhang, Z., Ran, X., Zhuang, K., & Ran, Y. (2025). An Ingeniously Designed Skin Lesion Classification Model Across Clinical and Dermatoscopic Datasets. Diagnostics, 15(16), 2011. https://doi.org/10.3390/diagnostics15162011

Vancouver

Huang Y, Zhang Z, Ran X, Zhuang K, Ran Y. An Ingeniously Designed Skin Lesion Classification Model Across Clinical and Dermatoscopic Datasets. Diagnostics. 2025;15(16):2011. doi:10.3390/diagnostics15162011

BibTeX
@article{Huang2025,
  author = {Huang, Ying and Zhang, Zhishuo and Ran, Xin and Zhuang, Kaiwen and Ran, Yuping},
  title = {An Ingeniously Designed Skin Lesion Classification Model Across Clinical and Dermatoscopic Datasets},
  journal = {Diagnostics},
  year = {2025},
  volume = {15},
  number = {16},
  pages = {2011},
  doi = {10.3390/diagnostics15162011}
}
Kostenlos starten →