ORIGINAL RESEARCH article
Front. Med.
Sec. Dermatology
This article is part of the Research TopicApplications and Advances of Artificial Intelligence in Medical Image Analysis: PET, SPECT/ CT, MRI, and Pathology ImagingView all 9 articles
DMFF-Net: A Multi-Scale Feature Fusion Network Based on DeepLabV3 for Skin Lesion Segmentation
Provisionally accepted
- Chengdu University of Traditional Chinese Medicine, Chengdu, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
ABSTRACT Objective: In computer-aided medical diagnosis, precise skin lesion segmentation is crucial for the early detection and treatment of skin cancer. However, challenges such as unclear lesion boundaries, low contrast, and varying lesion shapes make accurate segmentation a difficult task. To address these challenges, we propose DMFF-Net, a multi-scale, multi-attention feature fusion network based on DeepLabV3, designed to improve the accuracy of skin lesion segmentation. Methods: DMFF-Net integrates several advanced modules to enhance segmentation performance. The network incorporates a Global Grid Coordinate Attention Module (GGCAM), which effectively fuses spatial and channel features to capture the complex relationships between local and global information. Additionally, a Multi-Scale Depthwise Separable Dilated Convolution (MDSDC) module is employed to strengthen multi-scale feature extraction, thereby preventing resolution degradation during convolution. A Mid-High Level Feature Fusion (MHLFF) module is also introduced to refine critical feature representations and suppress irrelevant information, thereby improving segmentation accuracy. Results: The proposed network was evaluated on four publicly available datasets: ISIC 2016, ISIC 2017, ISIC 2018, and PH2. The results show that DMFF-Net significantly outperforms existing advanced methods. Specifically, it achieves MIoU values of 89.31%, 91.47%, and 86.93% on the ISIC 2016, ISIC 2017, and ISIC 2018 datasets, respectively. Furthermore, the network achieves accuracy values of 95.62%, 97.33%, and 94.78%, and F1 scores of 96.93%, 94.91%, and 93.61%, respectively, demonstrating its robustness and effectiveness in skin lesion segmentation. Conclusion: 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.
Keywords: skin lesion segmentation, DeepLabV3, Multi-scale feature fusion, attention mechanism, medicine image segmentation
Received: 22 May 2025; Accepted: 27 Oct 2025.
Copyright: © 2025 Jiang, Wang, Xu, Yin, Zhang, Zhang, Guo and Zhang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Jing Guo, 80620404@qq.com
Pengfei Zhang, zhangpengfei@cdutcm.edu.cn
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.