Hybrid Attention U-Net with Evolutionary Optimization for Skin Lesion Segmentation on ISIC 2018 Dataset
Keywords:
Skin Lesion Segmentation, U-Net, Attention Mechanism, Evolutionary OptimizationAbstract
Skin lesion segmentation is a fundamental step in automated melanoma detection systems. Although deep learning architectures such as U-Net have significantly advanced the field, challenges persist due to variations in lesion size, shape, color, and the presence of imaging artifacts. In this paper, we propose a Hybrid Attention U-Net (HA-UNet) that integrates channel-wise and spatial attention mechanisms to improve feature representation. To further enhance segmentation accuracy and reduce manual hyperparameter tuning, we employ Differential Evolution (DE) as an evolutionary optimization strategy. The proposed method is evaluated on the ISIC 2018 dataset, consisting of 2,594 dermoscopic images with corresponding ground truth masks. Experimental results show that HA-UNet with DE optimization achieves a Dice similarity coefficient of 0.908 and a mean Intersection over Union (IoU) of 0.862, outperforming standard U-Net and Attention U-Net. The results demonstrate that hybrid attention combined with evolutionary optimization provides a robust, automated solution for skin lesion segmentation.
References
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation.
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
