W+-Net: Derin Öğrenme Tabanlı W+-Net: Derin Öğrenme Tabanlı Görüntü Segmentasyonu ile Covid19 Tespiti ile Covid19 Tespiti

Yıl 2025, Cilt: 2 Sayı: 1, 20 - 25, 25.04.2025

Lütfü Bayrak , Kenan Koçkaya , Ahmet Çınar

https://doi.org/10.5281/zenodo.15278183

Öz

2019 yılında Çin’in Wuhan kentinde ortaya çıkan Covid19 hastalığı kısa sürede tüm dünyayı etkisi altına almış ve pandemi olarak nitelendirilmiştir. Hastalığın akciğerde ortaya çıkarak yakalanan kişilerde ölümcül etkiler oluşturması nedeniyle tüm dünyada ciddi tedbirlerin alınmasına sebep oluştur. Tüm dünyayı kısa sürede etkisine alması ve ölümlerin hızla artması tedavinin de hızlı bir şekilde bulunmasına neden olmuştur.
Hastalık tespitinde yapay zekâ destekli çalışmaların artması enfekte olan kişilerde ki anomalilerin tespitinde derin öğrenme tabanlı görüntü segmentasyonunun teşhis işlemlerinde önemli bir çözüm oluşturabileceğini göstermiştir. Yapılan bu çalışmada W-Net+ olarak nitelendirilen uyarlanmış bir mimari önerilmektedir. Önerilen bu mimari U-Net ve W-Net mimarileriyle kıyaslanmış ve başarımları deneysel sonuçlarla gösterilmiştir. Yapılan bu çalışmada Covid 19 anomolilerin tespitinde önerdiğimiz yöntemin diğer yöntemlere göre daha başarılı olduğu açık bir biçimde görülmektedir.

Anahtar Kelimeler

Görüntü Segmentasyonu , Derin Öğrenme , U-Net , W-Net

Etik Beyan

Çalışmanın tüm süreçlerinin araştırma ve yayın etiğine uygun olduğunu, etik kurallara ve bilimsel atıf gösterme ilkelerine uyduğumu beyan ederim.

Destekleyen Kurum

Bulunmamaktadır.

Proje Numarası

Proje kapsamında değildir.

W+-Net: Covid19 Detection with Deep Learning-Based Image Segmentation

Öz

The Covid19 disease, which emerged in Wuhan, China in 2019, quickly affected the entire world and was described as a pandemic. Since the disease occurs in the lungs and causes fatal effects in those who catch it, it has caused serious precautions to be taken all over the world. The fact that it affected the entire world in a short time and the rapid increase in deaths has also led to the rapid discovery of a treatment.
The increase in artificial intelligence-supported studies in disease detection has shown that deep learning-based image segmentation can be an important solution in diagnostic processes in the detection of anomalies in infected people. In this study, an adapted architecture called W-Net+ is proposed. This proposed architecture has been compared with U-Net and W-Net architectures and its successes have been demonstrated with experimental results. In this study, it is clearly seen that the method we proposed is more successful than other methods in detecting Covid-19 anomalies.

Anahtar Kelimeler

Image Segmentation , Deep Learning , U-Net , W-Net

Proje Numarası

Proje kapsamında değildir.

Kaynakça

• [1] Redmon, J., Divvala, S., Girshick, R., Farhadi, A., “You only look once: Unified, real-time object detection”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Sayfa 779-788, 2016.
• [2] Sethy, P. K., Behera, S. K., Ratha, P. K., Biswas, P., “Detection of coronavirus disease (COVID-19) based on deep features and support vector machine”, 2020.
• [3] Szegedy, C., Toshev, A., Erhan, D., “Deep neural networks for object detection”, Advances in Neural Information Processing Systems, Cilt 26, Sayfa 779-788, 2013.
• [4] Wang, Y., Zhang, Y., Liu, Y., Tian, J., Zhong, C., Shi, Z., Zhang, Y., He, Z., “Does non-COVID-19 lung lesion help? Investigating transferability in COVID-19 CT image segmentation”, Computer Methods and Programs in Biomedicine, Cilt 202, Sayfa 106004, 2021.
• [5] Saeedizadeh, N., Minaee, S., Kafieh, R., Yazdani, S., Sonka, M., “COVID TV-Unet: Segmenting COVID-19 chest CT images using connectivity imposed Unet”, Computer Methods and Programs in Biomedicine Update, Cilt 1, Sayfa 100007, 2021.
• [6] Fung, D. L., Liu, Q., Zammit, J., Leung, C. K. S., Hu, P., “Self-supervised deep learning model for COVID-19 lung CT image segmentation highlighting putative causal relationship among age, underlying disease and COVID-19”, Journal of Translational Medicine, Cilt 19, Sayfa 1-18, 2021.
• [7] Tahir, A. M., Chowdhury, M. E. H., Khandakar, A., Rahman, T., Qiblawey, Y., Khurshid, U., Kiranyaz, S., Ibtehaz, N., Rahman, M. S., Al-Maadeed, S., Mahmud, S., Ezeddin, M., Hameed, K., Hamid, T., “COVID-19 infection localization and severity grading from chest X-ray images”, Computers in Biology and Medicine, Cilt 139, Sayfa 105002, 2021.
• [8] Wu, Y. H., Gao, S. H., Mei, J., Xu, J., Fan, D. P., Zhang, R. G., Cheng, M. M., “JCS: An explainable COVID-19 diagnosis system by joint classification and segmentation”, IEEE Transactions on Image Processing, Cilt 30, Sayfa 3113-3126, 2021.
• [9] Qi, A., Zhao, D., Yu, F., Heidari, A. A., Wu, Z., Cai, Z., Alenezi, F., Mansour, R. F., Chen, H., Chen, M., “Directional mutation and crossover boosted ant colony optimization with application to COVID-19 X-ray image segmentation”, Computers in Biology and Medicine, Cilt 148, Sayfa 105810, 2022.
• [10] Ma, J., Wang, Y., An, X., Ge, C., Yu, Z., Chen, J., Zhu, Q., Dong, G., He, J., He, Z., Cao, T., Zhu, Y., Nie, Z., Yang, X., “Toward data‐efficient learning: A benchmark for COVID‐19 CT lung and infection segmentation”, Medical Physics, Cilt 48, Sayfa 1197-1210, 2021.
• [11] Zhang, P., Zhong, Y., Deng, Y., Tang, X., Li, X., “CoSinGAN: learning COVID-19 infection segmentation from a single radiological image”, Diagnostics, Cilt 10, Sayı 11, Sayfa 901, 2020.
• [12] R-Prabha, M., Prabhu, R., Suganthi, S. U., Sridevi, S., Senthil, G. A., Babu, D. V., “Design of hybrid deep learning approach for COVID-19 infected lung image segmentation”, Journal of Physics: Conference Series, Cilt 2040, Sayı 1, Sayfa 012016, 2021.
• [13] Antar, S., Abd El-Sattar, H. K. H., Abdel-Rahman, M. H., Ghaleb, F. M., “COVID-19 infection segmentation using hybrid deep learning and image processing techniques”, Scientific Reports, Cilt 13, Sayı 1, Sayfa 22737, 2023.
• [14] Fan, D.-P., Zhou, T., Ji, G.-P., Zhou, Y., Chen, G., Fu, H., Shen, J., Shao, L., “Inf-Net: Automatic COVID-19 lung infection segmentation from CT images”, IEEE Transactions on Medical Imaging, Cilt 39, Sayı 8, Sayfa 2626-2637, 2020.
• [15] Müller, D., Rey, I. S., Kramer, F., “Automated chest CT image segmentation of COVID-19 lung infection based on 3D U-Net”, arXiv preprint arXiv:2007.04774, 2020.
• [16] Yan, Q., Wang, B., Gong, D., Luo, C., Zhao, W., Shen, J., Shi, Q., Zhang, Y., Zhang, L., You, Z., “COVID-19 chest CT image segmentation network by multi-scale fusion and enhancement operations”, IEEE Transactions on Big Data, Cilt 7, Sayı 1, Sayfa 13-24, 2021.
• [17] Rahman, T., Khandakar, A., Qiblawey, Y., Tahir, A., Kiranyaz, S., Bin Abul Kashem, S., Islam, M. T., Al Maadeed, S., Zughaier, S. M., Khan, M. S., Chowdhury, M. E., “Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images”, Computers in Biology and Medicine, Cilt 132, Sayfa 104319, 2021.
• [18] Aggarwal, P., Mishra, N. K., Fatimah, B., Singh, P., Gupta, A., Joshi, S. D., “COVID-19 image classification using deep learning: Advances, challenges and opportunities”, Computers in Biology and Medicine, Cilt 144, Sayfa 105350, 2022.
• [19] Saood, A., Hatem, I., “COVID-19 lung CT image segmentation using deep learning methods: U-Net versus SegNet”, BMC Medical Imaging, Cilt 21, Sayfa 1-10, 2021.
• [20] Amyar, A., Modzelewski, R., Li, H., Ruan, S., “Multi-task deep learning based CT imaging analysis for COVID-19 pneumonia: Classification and segmentation”, Computers in Biology and Medicine, Cilt 126, Sayfa 104037, 2020.
• [21] Khalifa, N. E. M., Manogaran, G., Taha, M. H. N., Loey, M., “A deep learning semantic segmentation architecture for COVID-19 lesions discovery in limited chest CT datasets”, Expert Systems, Cilt 39, Sayı 6, Sayfa e12742, 2022.
• [22] Kaggle, “COVID-19 Image Dataset”, https://www.kaggle.com/datasets.
• [23] Ronneberger, O., Fischer, P. ve Brox, T., “U-net: Convolutional networks for biomedical image segmentation”, Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III, Springer International Publishing, 18, 2015.
• [24] Xia, X. ve Kulis, B., “W-net: A deep model for fully unsupervised image segmentation”, arXiv preprint arXiv:1711.08506, 2017.