SavedAdd your journal

Journals / Zeki Sistemler Teori ve Uygulamaları Dergisi / 2026 / Cilt: 9 Sayı: 2026

Automated Skin Lesion Segmentation in Medical Images Using U-Net Architectures

U-Net Mimarileri Kullanılarak Tıbbi Görüntülerde Otomatik Cilt Lezyon Segmentasyonu

Muhammad Owais Raza(SAKARYA UNIVERSITY OF APPLIED SCIENCES)0009-0009-8707-4793
Zeynep Garip(SAKARYA UYGULAMALI BİLİMLER ÜNİVERSİTESİ)0000-0002-0420-8541
Ekin Ekinci(SAKARYA UNIVERSITY OF APPLIED SCIENCES)0000-0003-0658-592X
Pages
1–12
Publication Date
2026-03-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results show that attention mechanisms and residual structures provide significant contributions to the accurate segmentation of skin lesions and that these architectures have the potential to be used in clinical decision support systems.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The biggest challenge, modern methods for laser and surgical treatments face in context of skin diseases is to find the exact boundaries of skin lesions.
📊
Key Findings & Data:The aim of this study is to comparatively investigate the performances of U-Net and its three improved variations, Residual U-Net, Attention U-Net and Residual Attention U-Net, in skin lesion segmentation.
💡
Conclusion & Impact:The results show that attention mechanisms and residual structures provide significant contributions to the accurate segmentation of skin lesions and that these architectures have the potential to be used in clinical decision support systems.
🔬Design:Modeling & Simulation
📍Scope:2016 Verileri
⚙️Variables:Cilt kanseri · lezyon segmentasyonu · derin öğrenme

Abstract

The biggest challenge, modern methods for laser and surgical treatments face in context of skin diseases is to find the exact boundaries of skin lesions. However, with the integration of deep learning applications with these treatments have shown a great improvement in finding the lesions boundaries. The aim of this study is to comparatively investigate the performances of U-Net and its three improved variations, Residual U-Net, Attention U-Net and Residual Attention U-Net, in skin lesion segmentation. The models were tested on two widely available public datasets, namely ISIC-2016 and ISIC-2017, and the comparison was performed using the same training parameters, image dimensions and evaluation metrics namely accuracy, Dice score and IoU. Attention U-Net model achieved the highest success on ISIC-2016 dataset with 94.4% accuracy, 81.9% Dice score and 81.5% IoU. On the ISIC-2017 dataset, the Residual Attention U-Net model showed superior performance with 92.2% accuracy, 76.9% Dice score and 69.5% IoU. The results show that attention mechanisms and residual structures provide significant contributions to the accurate segmentation of skin lesions and that these architectures have the potential to be used in clinical decision support systems.

Özet

Lazer ve cerrahi tedavilerde karşılaşılan en büyük zorluklardan biri, cilt hastalıkları bağlamında cilt lezyonlarının sınırlarını doğru bir şekilde belirlemektir. Ancak, derin öğrenme uygulamalarının bu tedavilerle entegre edilmesi, lezyon sınırlarının tespitinde önemli ilerlemeler sağlamıştır. Bu çalışmanın amacı, U-Net ve onun geliştirilmiş üç varyasyonu olan Residual U-Net, Attention U-Net ve Residual Attention U-Net modellerinin cilt lezyonu segmentasyonundaki performanslarını karşılaştırmalı olarak incelemektir. Modeller, ISIC-2016 ve ISIC-2017 adlı iki yaygın kamuya açık veri kümesi üzerinde test edilmiş ve karşılaştırma; aynı eğitim parametreleri, görüntü boyutları ve doğruluk, Dice skoru ve IoU değerlendirme metrikleri kullanılarak gerçekleştirilmiştir. ISIC-2016 veri kümesinde en yüksek başarıyı %94.4 doğruluk, %81.9 Dice skoru ve %81.5 IoU ile Attention U-Net modeli elde etmiştir. ISIC-2017 veri kümesinde ise Residual Attention U-Net modeli %92.2 doğruluk, %76.9 Dice skoru ve %69.5 IoU ile üstün performans göstermiştir. Sonuçlar, dikkat mekanizmalarının ve artık yapıların cilt lezyonlarının doğru segmentasyonu açısından önemli katkılar sağladığını ve bu mimarilerin klinik karar destek sistemlerinde kullanılabilir potansiyele sahip olduğunu göstermektedir.

🔖

Cite This Article

Raza, M. O., Garip, Z., Ekinci, E. (2026). Automated Skin Lesion Segmentation in Medical Images Using U-Net Architectures. Zeki Sistemler Teori ve Uygulamaları Dergisi, Cilt: 9 Sayı: 2026, 1–12. https://doi.org/10.38016/jista.1671052

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (30)

  1. Albahli, S., Nida, N., Irtaza, A., Yousaf, M. H., & Mahmood, M. T. 2020. Melanoma lesion detection and segmentation using YOLOv4-DarkNet and active contour. IEEE access, 8, 198403-198414.
  2. American Academy of Dermatology Association. Skin cancer in people of color. 2022. Retrieved 25 September 2024, from https://www.aad.org/public/diseases/skin-cancer/types/common/melanoma/skin-color
  3. Codella, N. C., Gutman, D., Celebi, M. E., Helba, B., Marchetti, M. A., Dusza, S. W.,. and Halpern, A., 2018. Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). In 2018 IEEE 15th international symposium on biomedical imaging, 168-172.
  4. Dai, D., Dong, C., Xu, S., Yan, Q., Li, Z., Zhang, C., Luo, N., 2022. Ms RED: A novel multi-scale residual encoding and decoding network for skin lesion segmentation. Medical image analysis, 75, 102293.
  5. Ding, Y., Yi, Z., Xiao, J., Hu, M., Guo, Y., Liao, Z., and Wang, Y., 2024. CTH-Net: A CNN and Transformer hybrid network for skin lesion segmentation. Iscience, 27(4).
  6. Garcia-Arroyo, J. L., & Garcia-Zapirain, B. 2019. Segmentation of skin lesions in dermoscopy images using fuzzy classification of pixels and histogram thresholding. Computer methods and programs in biomedicine, 168, 11-19.
  7. Gonzalez-Diaz, I., 2018. Dermaknet: Incorporating the knowledge of dermatologists to convolutional neural networks for skin lesion diagnosis. IEEE journal of biomedical and health informatics. 23(2), 547-559.
  8. Gutman, D., Codella, N. C., Celebi, E., Helba, B., Marchetti, M., Mishra, N., and Halpern, A., 2016. Skin lesion analysis toward melanoma detection: A challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). arXiv preprint arXiv:1605.01397.
  9. Hasan, M. K., Dahal, L., Samarakoon, P. N., Tushar, F. I., and Martí, R.,2020. DSNet: Automatic dermoscopic skin lesion segmentation. Computers in biology and medicine, 120, 103738.
  10. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K. Q.,2017. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4700-4708.
  11. International Agency for Research on Cancer, World Health Organization. 2024. Retrieved 14 January 2024, from https://www.iarc.who.int/cancer-type/skin-cancer/.
  12. LeCun, Y., Bengio, Y., and Hinton, G., 2015. Deep learning, Nature, 521(7553), 436-444.
  13. Long, J., Shelhamer, E., and Darrell, T., 2015. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 3431-3440.
  14. Lou, A., Guan, S., Ko, H., and Loew, M. H., 2022. CaraNet: context axial reverse attention network for segmentation of small medical objects. In Medical Imaging 2022: Image Processing, 81-92.
  15. Mahbod, A., Tschandl, P., Langs, G., Ecker, R., and Ellinger, I., 2020. The effects of skin lesion segmentation on the performance of dermatoscopic image classification. Computer Methods and Programs in Biomedicine, 197, 105725.
  16. MedicalNewsToday. What to know about melanoma vs. skin cancer, 2024. Retrieved 10 January 2025, from https://www.medicalnewstoday.com/articles/melanoma-vs-skin-cancer.
  17. Melanoma Research Alliance. Melanoma Survival Rates. 2024. Retrieved 20 March 2025, from https://www.curemelanoma.org/about-melanoma/melanoma-staging/melanoma-survival-rates.
  18. Mohakud, R., & Dash, R. 2022. Skin cancer image segmentation utilizing a novel EN-GWO based hyper-parameter optimized FCEDN. Journal of King Saud University-Computer and Information Sciences, 34(10), 9889-9904.
  19. Nida, N., Irtaza, A., Javed, A., Yousaf, M. H., & Mahmood, M. T. 2019. Melanoma lesion detection and segmentation using deep region based convolutional neural network and fuzzy C-means clustering. International journal of medical informatics, 124, 37-48.
  20. Nguyen, D. K., Tran, T. T., Nguyen, C. P., and Pham, V. T., 2020. Skin lesion segmentation based on integrating efficientnet and residual block into u-net neural network. In 2020 5th International Conference on Green Technology and Sustainable Development (GTSD), 366-371.
  21. Oktay, O., Schlemper, J., Folgoc, L. L., Lee, M., Heinrich, M., Misawa, K., and Rueckert, D.,2018. Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999.
  22. Qi, W., Wei, M., Yang, W., Xu, C., and Ma, C.,2020. Automatic mapping of landslides by the ResU-Net. Remote Sensing, 12(15), 2487.
  23. Ronneberger, O., Fischer, P., and Brox, T.,2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, pp. 234-241.
  24. Ruan, J., Xie, M., Gao, J., Liu, T., and Fu, Y. 2023. Ege-unet: an efficient group enhanced unet for skin lesion segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 481-490.
  25. Sarvamangala, D. R., Kulkarni, R. V., 2022. Convolutional neural networks in medical image understanding: a survey. Evolutionary intelligence, 15(1), 1-22.
  26. Vesal, S., Ravikumar, N., and Maier, A., 2018. SkinNet: A deep learning framework for skin lesion segmentation. In 2018 IEEE nuclear science symposium and medical imaging conference proceedings (NSS/MIC), 1-3.
  27. World Cancer Research Fund International. Skin cancer statistics. 2024. Retrieved 14 January 2024. From https://www.wcrf.org/cancer-trends/skin-cancer-statistics/
  28. Zebari, N. A., & Tenekeci, E. 2022. Skin Lesion Segmentation Using K-means Clustering with Removal Unwanted Regions. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi, 9(18), 519-529.
  29. Zhou, Z., Rahman Siddiquee, M. M., Tajbakhsh, N., and Liang, J., 2018. Unet++: A nested u-net architecture for medical image segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision. 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Conjunction with MICCAI 2018, Granada, Spain, 3-11.
  30. Codella, N. C., Gutman, D., Celebi, M. E., Helba, B., Marchetti, M. A., Dusza, S. W.,. and Halpern, A., 2018. Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). In 2018 IEEE 15th international symposium on biomedical imaging, 168-172.