Abstract

Accurate delineation of lesion boundaries in dermoscopic images is important for melanoma diagnosis. This study proposes a U-Net architecture whose encoder-decoder structure is extended with residual connections and channel-spatial attention blocks. The model was trained on ISIC 2018 and externally validated on PH2. The proposed architecture achieved a Dice coefficient of 0.912 and a Jaccard index of 0.847, a significant improvement over the baseline U-Net. Thanks to its lightweight design, the model runs in real time on mobile devices.

Keywords:image segmentationU-Netskin lesionattention mechanismmedical imaging

Full Text

PDF Download · 8.7 KB

Declarations

Ethics Approval
This study does not require ethics committee approval.
Conflict of Interest
The authors declare no conflict of interest.

References 6

  1. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 (pp. 234–241). Springer. https://doi.org/10.1007/978-3-319-24574-4_28
  2. Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115–118. https://doi.org/10.1038/nature21056
  3. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778). https://doi.org/10.1109/CVPR.2016.90
  4. Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., et al. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88. https://doi.org/10.1016/j.media.2017.07.005
  5. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), 1929–1958.
  6. Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In International Conference on Learning Representations.

How to Cite

Tekin, B., Mammadova, L., & Karaca, E. (2025). An Improved U-Net Architecture with Residual Attention Blocks for Skin Lesion Segmentation. International Journal of Science and Technology Research, 7(1), 18–32. https://doi.org/10.99999/ubtad.2025.8
BibTeX RIS (EndNote, Zotero, Mendeley)

License

CC BY 4.0

© 2025 Burak Tekin, Leyla Mammadova, Elif Karaca. This article is distributed under the terms of the CC BY 4.0 license, which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. License text