EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Few-shot skin lesion classification with Adaptive Multi-Scale Convolutional Attention Network

HuiYing Jin, E Liu, Qin Xu, YuChen Li iD, XiaoLiang Chen iD, WeiHua Chen

PLOS One · 25.06.2026 · 21 (6) · e0351318

DOI: 10.1371/journal.pone.0351318 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 25.06.2026. Verfasst von HuiYing Jin und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Laboratory Medicine, Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu, China. Hauptthemen laut MEDLINE: Skin, Diagnosis, Computer-Assisted, Skin Diseases, Image Interpretation, Computer-Assisted. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Supported by Joint Innovation Fund of Health Commission of Chengdu and Chengdu University of Traditional Chinese Medicine.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computer-aided diagnosis of skin lesions faces core challenges, including scale diversity, blurred boundaries, intra-class morphological variations, and sparse data. Existing methods often rely on fixed receptive fields or generic attention mechanisms, struggling to fully adapt to the unique characteristics of skin lesions. To address this, we propose an Adaptive Multi-scale Convolutional Attention Network (AMCANet), which aims to achieve accurate and robust classification of skin lesions with limited data. AMCANet comprises three core modules: the adaptive multi-scale convolution module dynamically adjusts the receptive field to accommodate lesions of varying sizes; the hierarchical channel attention module integrates multi-level semantic information across different resolutions; and the skin spatial attention module leverages image gradient information to enhance lesion boundaries and local texture features. Extensive few-shot experiments on the HAM10000 and PAD-UFES-20 public datasets demonstrate that AMCANet significantly outperforms existing baseline models across multiple metrics, exhibiting promising generalization capabilities on the evaluated datasets. Qualitative and visual analyses further validate the model’s ability to extract discriminative features and effectively focus on lesion regions. This study proposes a deep learning model, which demonstrates certain effectiveness in classifying skin lesions even with a small number of samples, providing a potential direction for future research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SkinDiagnosis, Computer-AssistedSkin DiseasesImage Interpretation, Computer-AssistedHumansConvolutional Neural NetworksAlgorithmsDeep Learning

Autor:innen und Institutionen

  • Department of Laboratory Medicine, Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu, China.
  • Chengdu University of Traditional Chinese Medicine, Chengdu, China.
  • Anesthesiology Department/Operating Room, Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu, China.
  • College of Electronic and Information Engineering, Tongji University, Shanghai, China.

ORCID-Profile: YuChen Li, XiaoLiang Chen

Förderung

  • Supported by Joint Innovation Fund of Health Commission of Chengdu and Chengdu University of Traditional Chinese Medicine

Zitieren

APA

Jin, H., Liu, E., Xu, Q., Li, Y., Chen, X., & Chen, W. (2026). Few-shot skin lesion classification with Adaptive Multi-Scale Convolutional Attention Network. PLOS One, 21(6), e0351318. https://doi.org/10.1371/journal.pone.0351318

Vancouver

Jin H, Liu E, Xu Q, Li Y, Chen X, Chen W. Few-shot skin lesion classification with Adaptive Multi-Scale Convolutional Attention Network. PLOS One. 2026;21(6):e0351318. doi:10.1371/journal.pone.0351318

BibTeX
@article{Jin2026,
  author = {Jin, HuiYing and Liu, E and Xu, Qin and Li, YuChen and Chen, XiaoLiang and Chen, WeiHua},
  title = {Few-shot skin lesion classification with Adaptive Multi-Scale Convolutional Attention Network},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0351318},
  doi = {10.1371/journal.pone.0351318}
}
Kostenlos starten →