DMFF-Net: a multi-scale feature fusion network based on DeepLabV3 for skin lesion segmentation
The DMFF-Net model, with its multi-scale feature fusion and attention mechanisms, substantially improves skin lesion segmentation by preserving crucial spatial details and improving feature representation. Its superior performance on multiple datasets highlights its potential as a powerful tool for skin lesion diagnosis and provides an important reference for future advancements in medical image segmentation.
Authors
- Yujie Zhang (ORCID: https://orcid.org/0000-0003-0581-759X)
- Xü Lin (ORCID: https://orcid.org/0000-0002-6382-7414)
- Linshuai Zhang (ORCID: https://orcid.org/0000-0002-2173-3698)
- Jing Guo (ORCID: https://orcid.org/0000-0002-6399-3877)
- Pengfei Zhang (ORCID: https://orcid.org/0000-0002-9853-0426)
- Yin Ji
- Shange Wang
- Tao Jiang (ORCID: https://orcid.org/0009-0003-1122-8940)
Institutions
- Chengdu University of Traditional Chinese Medicine (CN)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-11-26
- DOI
- https://doi.org/10.3389/fmed.2025.1633209
- Primary Topic
- Cutaneous Melanoma Detection and Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Chengdu University of Traditional Chinese Medicine
- Chengdu University
- Health Commission of Sichuan Province