Araştırma Makalesi
BibTex RIS Kaynak Göster

ÇEŞİTLİ VERİ KÜMELERİ ARASINDA RETİNAL GÖRÜNTÜ SEGMENTASYONU İÇİN YENİ BİR DİKKAT TABANLI U-NET YAKLAŞIMI

Yıl 2025, Cilt: 28 Sayı: 3, 1448 - 1467, 03.09.2025

Omar Abdelhamed , Ahmet Saygılı

https://doi.org/10.17780/ksujes.1685741

Öz

Retinal damar segmentasyonu, oftalmik ve sistemik hastalıkların erken tespiti ve tanısı için önemlidir. Bu çalışma, özellikle Att-UNet ve SA-UNet olmak üzere dikkat mekanizmalarının yeni entegrasyonları yoluyla yaygın olarak kullanılan U-Net mimarisinin segmentasyon performansını geliştirmeyi amaçlamaktadır. Bu yöntemleri sistematik olarak değerlendirmek için, üç kıyaslamalı retinal veri kümesinde karşılaştırmalı deneyler yürütülmüştür: DRIVE, STARE ve CHASE-DB1. Modeller, İkili Çapraz Entropi ve Dice kayıp fonksiyonlarını birleştiren bir hibrit kayıp fonksiyonu kullanılarak 80 epok boyunca eğitildi ve performans, Dice Benzerlik Katsayısı (DSC), Birleşim Üzerinden Kesişim (IoU) ve Doğruluk gibi metrikler kullanılarak titizlikle değerlendirildi. Deneysel sonuçlar, dikkatle geliştirilmiş varyantların segmentasyon kalitesi açısından standart U-Net'ten sürekli olarak daha iyi performans gösterdiğini göstermektedir. Özellikle, Att-UNet, DRIVE ve STARE veri kümelerinde en yüksek doğruluğu (%97,37) elde ederek optimum segmentasyon hassasiyeti sağlanırken, SA-UNet en düşük eğitim süreleriyle üstün hesaplama verimliliği göstermiştir. Bu bulgular, dikkat mekanizmalarıyla ilişkili veri kümesine bağlı faydaları ve hesaplamalı takasları vurgulamaktadır. Genel olarak, bu çalışma, dikkat mekanizmaları gibi yeni AI tekniklerinin entegre edilmesinin, retina damar segmentasyonunu önemli ölçüde iyileştirdiğini ve gerçek dünya mühendisliği ve klinik uygulamaları için potansiyel gösterdiğini doğrulamaktadır.

Anahtar Kelimeler

derin öğrenme retina damar segmentasyonu U-Net Dikkat U-net SA-Unet

Kaynakça

  • Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. Paper presented at the Proceedings of the European conference on computer vision (ECCV).
  • Fraz, M. M., Remagnino, P., Hoppe, A., Uyyanonvara, B., Rudnicka, A. R., Owen, C. G., & Barman, S. A. (2012). An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Transactions on Biomedical Engineering, 59(9), 2538-2548.
  • Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., & Lu, H. (2019). Dual attention network for scene segmentation. Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.
  • Saygılı, A., Cihan, P., Ermutlu, C. Ş., Aydın, U., & Aksoy, Ö. (2024). CattNIS: Novel identification system of cattle with retinal images based on feature matching method. Computers and Electronics in Agriculture, 221, 108963. https://doi.org/10.1016/j.compag.2024.108963
  • Cihan, P., Saygılı, A., Ermutlu, C. Ş., Aydın, U., & Aksoy, Ö. (2024). AI-aided cardiovascular disease diagnosis in cattle from retinal images: Machine learning vs. deep learning models. Computers and Electronics in Agriculture, 226, 109391. https://doi.org/10.1016/j.compag.2024.109391
  • Cihan, P., Saygılı, A., Akyüzlü, M., Özmen, N. E., Ermutlu, C. Ş., Aydın, U., & Aksoy, Ö. (2024). Extraction of Cattle Retinal Vascular Patterns with Different Segmentation Methods. Sakarya University Journal of Computer and Information Sciences, 7(3), 378–388. https://doi.org/10.35377/saucis.1509150
  • Cihan, P., Saygılı, A., Akyüzlü, M., Özmen, N. E., Ermutlu, C. Ş., Aydın, U., & Aksoy, Ö. (2025). Performance of machine learning methods for cattle identification and recognition from retinal images. Applied Intelligence, 55(6), 1–20. https://doi.org/10.1007/s10489-025-06398-1
  • Cihan, P., Saygılı, A., Akyüzlü, M., Özmen, N. E., Ermutlu, C. Ş., Aydın, U., Yılmaz, A., & Aksoy, Ö. (2025). U-Net-Based Approaches for Biometric Identification and Recognition in Cattle. Kafkas Üniversitesi Veteriner Fakültesi Dergisi, 31(3), 425–436. https://doi.org/10.9775/kvfd.2025.34130
  • Guo, C., Szemenyei, M., Yi, Y., Zhou, W., & Bian, H. (2020). Residual spatial attention network for retinal vessel segmentation. Paper presented at the International Conference on Neural Information Processing.
  • He, X., Wang, T., & Yang, W. (2024). Research on Retinal Vessel Segmentation Algorithm Based on a Modified U-Shaped Network. Applied Sciences, 14(1), 465.
  • Hoover, A., Kouznetsova, V., & Goldbaum, M. (2000). Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE transactions on medical imaging, 19(3), 203-210.
  • Jin, Q., Meng, Z., Pham, T. D., Chen, Q., Wei, L., & Su, R. (2019). DUNet: A deformable network for retinal vessel segmentation. Knowledge-Based Systems, 178, 149-162.
  • Kaluri, R., & Ch, P. R. (2018). Optimized feature extraction for precise sign gesture recognition using self-improved genetic algorithm. International Journal of Engineering and Technology Innovation, 8(1), 25-37.
  • Kande, G. B., Savithri, T. S., & Subbaiah, P. V. (2008). Retinal vessel segmentation using histogram matching. Paper presented at the APCCAS 2008-2008 IEEE Asia Pacific Conference on Circuits and Systems.
  • Li, X., Wang, W., Hu, X., & Yang, J. (2019). Selective kernel networks. Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.
  • Mardani, K., & Maghooli, K. (2021). Enhancing retinal blood vessel segmentation in medical images using combined segmentation modes extracted by DBSCAN and morphological reconstruction. Biomedical Signal Processing and Control, 69, 102837.
  • Marín, D., Aquino, A., Gegúndez-Arias, M. E., & Bravo, J. M. (2010). A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features. IEEE transactions on medical imaging, 30(1), 146-158.
  • Pattisapu, V. K., Daunhawer, I., Weikert, T., Sauter, A., Stieltjes, B., & Vogt, J. E. (2021). Pet-guided attention network for segmentation of lung tumors from pet/ct images. Paper presented at the Pattern Recognition: 42nd DAGM German Conference, DAGM GCPR 2020, Tübingen, Germany, September 28–October 1, 2020, Proceedings 42.
  • Ricci, E., & Perfetti, R. (2007). Retinal blood vessel segmentation using line operators and support vector classification. IEEE transactions on medical imaging, 26(10), 1357-1365.
  • Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Paper presented at the Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18.
  • Sinaga, K. P., & Yang, M.-S. (2020). Unsupervised K-means clustering algorithm. IEEE access, 8, 80716-80727.
  • Staal, J., Abràmoff, M. D., Niemeijer, M., Viergever, M. A., & Van Ginneken, B. (2004). Ridge-based vessel segmentation in color images of the retina. IEEE transactions on medical imaging, 23(4), 501-509.
  • Wang, S., Li, L., & Zhuang, X. (2021). AttU-Net: attention U-Net for brain tumor segmentation. Paper presented at the International MICCAI brainlesion workshop.
  • Wu, Y., Xia, Y., Song, Y., Zhang, D., Liu, D., Zhang, C., & Cai, W. (2019). Vessel-Net: Retinal vessel segmentation under multi-path supervision. Paper presented at the Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part I 22.
  • Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017). Scene parsing through ade20k dataset. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
  • Zhang, S., Fu, H., Yan, Y., Zhang, Y., Qingxiao, W., Yang, M., Tan, M., & Xu, Y. (2019). AG-net: Attention Guided Network for Retinal Image Segmentation. arXiv preprint arXiv:1907.12390.
  • Guo, C., Szemenyei, M., Pei, Y., Yi, Y., & Zhou, W. (2019). SD-UNet: A Structured Dropout U-Net for Retinal Vessel Segmentation. In 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE) (pp. 439–444). IEEE. DOI: 10.1109/BIBE.2019.00085.
  • Guo, C., Szemenyei, M., Yi, Y., Wang, W., Chen, B., & Fan, C. (2021). SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation. In 2020 25th International Conference on Pattern Recognition (ICPR) (pp. 1236–1242). DOI: 10.1109/ICPR48806.2021.9413346.
  • Lv, Y., Ma, H., Li, J., & Liu, S. (2020). Attention Guided U-Net With Atrous Convolution for Accurate Retinal Vessels Segmentation. IEEE Access, 8, 32826–32839. DOI: 10.1109/ACCESS.2020.2974027.
  • Wang, D., Haytham, A., Pottenburgh, J., Saeedi, O., & Tao, Y. (2020). Hard Attention Net for Automatic Retinal Vessel Segmentation. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) (pp. 1–5). IEEE. DOI: 10.1109/ISBI45749.2020.9098511.

A NOVEL ATTENTION-BASED U-NET APPROACH FOR RETINAL IMAGE SEGMENTATION ACROSS DIVERSE DATASETS

Yıl 2025, Cilt: 28 Sayı: 3, 1448 - 1467, 03.09.2025

Omar Abdelhamed , Ahmet Saygılı

https://doi.org/10.17780/ksujes.1685741

Öz

Retinal vessel segmentation is essential for the early detection and diagnosis of ophthalmic and systemic diseases. This study aims to enhance the segmentation performance of the widely used U-Net architecture through novel integrations of attention mechanisms, specifically Attention U-Net (Att-UNet) and Spatial Attention U-Net (SA-UNet). To systematically evaluate these methods, comparative experiments were conducted across three benchmark retinal datasets: DRIVE, STARE, and CHASE-DB1. Models were trained for 80 epochs using a hybrid loss combining Binary Cross-Entropy and Dice loss functions, and performance was rigorously assessed using metrics such as Dice Similarity Coefficient (DSC), Intersection over Union (IoU), and Accuracy. The experimental results indicate that attention-enhanced variants consistently outperform standard U-Net in terms of segmentation quality. Specifically, Att-UNet achieved the highest accuracy (97.37%) on DRIVE and STARE datasets, providing optimal segmentation precision, whereas SA-UNet demonstrated superior computational efficiency with the lowest training times. These findings highlight the dataset-dependent benefits and computational trade-offs associated with attention mechanisms. Overall, this study confirms that integrating novel AI techniques, such as attention mechanisms, significantly improves retinal vessel segmentation, showcasing potential for real-world engineering and clinical applications.

Anahtar Kelimeler

deep learning retinal vessel segmentation U-Net Attention U-Net SA-UNet

Kaynakça

  • Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. Paper presented at the Proceedings of the European conference on computer vision (ECCV).
  • Fraz, M. M., Remagnino, P., Hoppe, A., Uyyanonvara, B., Rudnicka, A. R., Owen, C. G., & Barman, S. A. (2012). An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Transactions on Biomedical Engineering, 59(9), 2538-2548.
  • Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., & Lu, H. (2019). Dual attention network for scene segmentation. Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.
  • Saygılı, A., Cihan, P., Ermutlu, C. Ş., Aydın, U., & Aksoy, Ö. (2024). CattNIS: Novel identification system of cattle with retinal images based on feature matching method. Computers and Electronics in Agriculture, 221, 108963. https://doi.org/10.1016/j.compag.2024.108963
  • Cihan, P., Saygılı, A., Ermutlu, C. Ş., Aydın, U., & Aksoy, Ö. (2024). AI-aided cardiovascular disease diagnosis in cattle from retinal images: Machine learning vs. deep learning models. Computers and Electronics in Agriculture, 226, 109391. https://doi.org/10.1016/j.compag.2024.109391
  • Cihan, P., Saygılı, A., Akyüzlü, M., Özmen, N. E., Ermutlu, C. Ş., Aydın, U., & Aksoy, Ö. (2024). Extraction of Cattle Retinal Vascular Patterns with Different Segmentation Methods. Sakarya University Journal of Computer and Information Sciences, 7(3), 378–388. https://doi.org/10.35377/saucis.1509150
  • Cihan, P., Saygılı, A., Akyüzlü, M., Özmen, N. E., Ermutlu, C. Ş., Aydın, U., & Aksoy, Ö. (2025). Performance of machine learning methods for cattle identification and recognition from retinal images. Applied Intelligence, 55(6), 1–20. https://doi.org/10.1007/s10489-025-06398-1
  • Cihan, P., Saygılı, A., Akyüzlü, M., Özmen, N. E., Ermutlu, C. Ş., Aydın, U., Yılmaz, A., & Aksoy, Ö. (2025). U-Net-Based Approaches for Biometric Identification and Recognition in Cattle. Kafkas Üniversitesi Veteriner Fakültesi Dergisi, 31(3), 425–436. https://doi.org/10.9775/kvfd.2025.34130
  • Guo, C., Szemenyei, M., Yi, Y., Zhou, W., & Bian, H. (2020). Residual spatial attention network for retinal vessel segmentation. Paper presented at the International Conference on Neural Information Processing.
  • He, X., Wang, T., & Yang, W. (2024). Research on Retinal Vessel Segmentation Algorithm Based on a Modified U-Shaped Network. Applied Sciences, 14(1), 465.
  • Hoover, A., Kouznetsova, V., & Goldbaum, M. (2000). Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE transactions on medical imaging, 19(3), 203-210.
  • Jin, Q., Meng, Z., Pham, T. D., Chen, Q., Wei, L., & Su, R. (2019). DUNet: A deformable network for retinal vessel segmentation. Knowledge-Based Systems, 178, 149-162.
  • Kaluri, R., & Ch, P. R. (2018). Optimized feature extraction for precise sign gesture recognition using self-improved genetic algorithm. International Journal of Engineering and Technology Innovation, 8(1), 25-37.
  • Kande, G. B., Savithri, T. S., & Subbaiah, P. V. (2008). Retinal vessel segmentation using histogram matching. Paper presented at the APCCAS 2008-2008 IEEE Asia Pacific Conference on Circuits and Systems.
  • Li, X., Wang, W., Hu, X., & Yang, J. (2019). Selective kernel networks. Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.
  • Mardani, K., & Maghooli, K. (2021). Enhancing retinal blood vessel segmentation in medical images using combined segmentation modes extracted by DBSCAN and morphological reconstruction. Biomedical Signal Processing and Control, 69, 102837.
  • Marín, D., Aquino, A., Gegúndez-Arias, M. E., & Bravo, J. M. (2010). A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features. IEEE transactions on medical imaging, 30(1), 146-158.
  • Pattisapu, V. K., Daunhawer, I., Weikert, T., Sauter, A., Stieltjes, B., & Vogt, J. E. (2021). Pet-guided attention network for segmentation of lung tumors from pet/ct images. Paper presented at the Pattern Recognition: 42nd DAGM German Conference, DAGM GCPR 2020, Tübingen, Germany, September 28–October 1, 2020, Proceedings 42.
  • Ricci, E., & Perfetti, R. (2007). Retinal blood vessel segmentation using line operators and support vector classification. IEEE transactions on medical imaging, 26(10), 1357-1365.
  • Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Paper presented at the Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18.
  • Sinaga, K. P., & Yang, M.-S. (2020). Unsupervised K-means clustering algorithm. IEEE access, 8, 80716-80727.
  • Staal, J., Abràmoff, M. D., Niemeijer, M., Viergever, M. A., & Van Ginneken, B. (2004). Ridge-based vessel segmentation in color images of the retina. IEEE transactions on medical imaging, 23(4), 501-509.
  • Wang, S., Li, L., & Zhuang, X. (2021). AttU-Net: attention U-Net for brain tumor segmentation. Paper presented at the International MICCAI brainlesion workshop.
  • Wu, Y., Xia, Y., Song, Y., Zhang, D., Liu, D., Zhang, C., & Cai, W. (2019). Vessel-Net: Retinal vessel segmentation under multi-path supervision. Paper presented at the Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part I 22.
  • Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017). Scene parsing through ade20k dataset. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
  • Zhang, S., Fu, H., Yan, Y., Zhang, Y., Qingxiao, W., Yang, M., Tan, M., & Xu, Y. (2019). AG-net: Attention Guided Network for Retinal Image Segmentation. arXiv preprint arXiv:1907.12390.
  • Guo, C., Szemenyei, M., Pei, Y., Yi, Y., & Zhou, W. (2019). SD-UNet: A Structured Dropout U-Net for Retinal Vessel Segmentation. In 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE) (pp. 439–444). IEEE. DOI: 10.1109/BIBE.2019.00085.
  • Guo, C., Szemenyei, M., Yi, Y., Wang, W., Chen, B., & Fan, C. (2021). SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation. In 2020 25th International Conference on Pattern Recognition (ICPR) (pp. 1236–1242). DOI: 10.1109/ICPR48806.2021.9413346.
  • Lv, Y., Ma, H., Li, J., & Liu, S. (2020). Attention Guided U-Net With Atrous Convolution for Accurate Retinal Vessels Segmentation. IEEE Access, 8, 32826–32839. DOI: 10.1109/ACCESS.2020.2974027.
  • Wang, D., Haytham, A., Pottenburgh, J., Saeedi, O., & Tao, Y. (2020). Hard Attention Net for Automatic Retinal Vessel Segmentation. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) (pp. 1–5). IEEE. DOI: 10.1109/ISBI45749.2020.9098511.
Toplam 30 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Görüntü İşleme
Bölüm Bilgisayar Mühendisliği
Yazarlar

Omar Abdelhamed 0009-0003-1182-6561

Ahmet Saygılı 0000-0001-8625-4842

Yayımlanma Tarihi 3 Eylül 2025
Gönderilme Tarihi 28 Nisan 2025
Kabul Tarihi 4 Temmuz 2025
Yayımlandığı Sayı Yıl 2025 Cilt: 28 Sayı: 3

Kaynak Göster

APA Abdelhamed, O., & Saygılı, A. (2025). A NOVEL ATTENTION-BASED U-NET APPROACH FOR RETINAL IMAGE SEGMENTATION ACROSS DIVERSE DATASETS. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(3), 1448-1467. https://doi.org/10.17780/ksujes.1685741
 Kapak Resmi İndir