EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSDTCN-Net: A Multi-Scale Dual-Encoder Network for Skin Lesion Segmentation

Da Li, Xinyang Wu, Qin Wei

Diagnostics · 19.11.2025 · 15 (22) · 2924

DOI: 10.3390/diagnostics15222924 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 19.11.2025. Verfasst von Da Li und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Accurate segmentation of skin lesions is essential for early skin cancer detection. However, traditional CNNs are limited in modeling long-range dependencies, leading to poor performance on lesions with complex shapes.

Methods

We propose MSDTCN-Net, a dual-encoder network that integrates ConvNeXt and Deformable Transformer to extract both local details and global semantic information. A Squeeze-and-Excitation (SE) mechanism is introduced to adaptively emphasize important channels. To address scale variation in lesions, we design a Multi-Scale Receptive Field (MSRF) module combining multi-branch and dilated convolutions. Furthermore, a Hierarchical Feature Transfer (HFT) mechanism is employed to guide high-level semantics progressively to shallow layers, enhancing boundary reconstruction in the decoder.

Results

Extensive experiments on the ISIC 2016, ISIC 2017, ISIC 2018, and PH2 datasets show that MSDTCN-Net achieves competitive performance across metrics including IoU, Dice, and ACC, validating its effectiveness and generalization in skin lesion segmentation.

Conclusions

MSDTCN-Net effectively combines local and global feature extraction, multi-scale adaptability, and semantic guidance to achieve high-accuracy skin lesion segmentation, demonstrating its potential in clinical diagnostic applications.

Schlagwörter

Stichwörter der Autor:innen

convolutional neural networkshierarchical feature transfermulti-scale receptive fieldskin lesion segmentationtransformer

Autor:innen und Institutionen

  • School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China.

Zitieren

APA

Li, D., Wu, X., & Wei, Q. (2025). MSDTCN-Net: A Multi-Scale Dual-Encoder Network for Skin Lesion Segmentation. Diagnostics, 15(22), 2924. https://doi.org/10.3390/diagnostics15222924

Vancouver

Li D, Wu X, Wei Q. MSDTCN-Net: A Multi-Scale Dual-Encoder Network for Skin Lesion Segmentation. Diagnostics. 2025;15(22):2924. doi:10.3390/diagnostics15222924

BibTeX
@article{Li2025,
  author = {Li, Da and Wu, Xinyang and Wei, Qin},
  title = {MSDTCN-Net: A Multi-Scale Dual-Encoder Network for Skin Lesion Segmentation},
  journal = {Diagnostics},
  year = {2025},
  volume = {15},
  number = {22},
  pages = {2924},
  doi = {10.3390/diagnostics15222924}
}
Kostenlos starten →