DeepImageSegmentationApp: Deep Learning Application for Image Segmentation

Yıl 2025, Cilt: 15 Sayı: 1, 88 - 100, 30.06.2025

Lütfü Bayrak , Kenan Koçkaya , Ahmet Çınar

https://doi.org/10.54370/ordubtd.1651665

Öz

There are many methods to examine a specific region or object in images. One of the most important of these methods is image segmentation. Image segmentation involves dividing images (or video frames) into multiple sections or objects. There are many different model architectures developed in the field of image segmentation.
In this study, a deep learning-based image segmentation application interface has been developed. The performance of the proposed application has been analyzed on the COVID-19 dataset obtained from Kaggle. The performance results of the application are presented in a comparative analysis of the U-NET and V-NET models, which are known for their accuracy, for various system parameters. In the analysis results, it is seen that the V-NET architecture is better than the U-NET architecture. The developed application environment has revealed the difference between the models and the usability of the application environment. This standalone software can be downloaded at: https://github.com/lbayrak/DeepImageSegmentationApp.

Anahtar Kelimeler

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

Etik Beyan

There are no ethical issues related to the publication of this article.

DeepImageSegmentationApp: Görüntü Segmentasyonu için Derin Öğrenme Uygulaması

Öz

Görüntülerde belirli bir bölgeyi veya nesneyi incelemek için birçok yöntem vardır. Bu yöntemlerin en önemlilerinden biri görüntü segmentasyonudur. Görüntü segmentasyonu, görüntüleri (veya video karelerini) birden fazla bölüme veya nesneye ayırmayı içerir. Görüntü segmentasyonu alanında geliştirilen birçok farklı model mimarisi vardır. Bu çalışmada, derin öğrenme tabanlı bir görüntü segmentasyonu uygulama arayüzü geliştirilmiştir. Önerilen uygulamanın performansı Kaggle'dan elde edilen Covid19 veri kümesi üzerinde analiz edilmiştir. Uygulamanın performans sonuçları, farklı sistem parametreleri için bilinen doğrulukla U-NET ve V-NET modelleri üzerinde karşılaştırmalı olarak sunulmuştur. Analiz sonuçlarında V-NET mimarisinin U-NET mimarisine göre daha iyi olduğu açıkça görülmektedir. Geliştirilen uygulama ortamı modeller arasındaki farkı ve uygulama ortamının kullanışlılığını ortaya koymuştur. Bu bağımsız yazılım şu adresten indirilebilir: https://github.com/lbayrak/DeepImageSegmentationApp.

Anahtar Kelimeler

Görüntü Bölümlendirme , Derin Öğrenme , U-Net , V-Net

Kaynakça

• Dang, T., Nguyen, T. T., McCall, J., Elyan, E., & Moreno-García, C. F. (2024). Two-layer ensemble of deep learning models for medical image segmentation. Cognitive Computation, 16(3), 1141-1160. https://doi.org/10.1007/s12559-024-10257-5
• Gupta, M., & Mishra, A. (2024). A systematic review of deep learning based image segmentation to detect polyp. Artificial Intelligence Review, 57(1), 7. https://doi.org/10.1007/s10462-023-10621-1
• Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90. https://doi.org/10.1145/3065386
• LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
• Li, J., Cai, Y., Li, Q., Kou, M., & Zhang, T. (2024). A review of remote sensing image segmentation by deep learning methods. International Journal of Digital Earth, 17(1), 2328827. https://doi.org/10.1080/17538947.2024.2328827
• Liu, X., Li, S., Zou, X., Chen, X., Xu, H., Yu, Y., ... & Zhang, Y. (2024). Development and clinical validation of a deep learning‐based knee CT image segmentation method for robotic‐assisted total knee arthroplasty. The International Journal of Medical Robotics and Computer Assisted Surgery, 20(4), e2664. https://doi.org/10.1002/rcs.2664
• Milletari, F., Navab, N., & Ahmadi, S. A. (2016, October). V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV) (pp. 565-571). IEEE. https://doi.org/10.1109/3DV.2016.79
• Peng, Y., & Yang, H. D. (2024). Aggregate boundary recognition of asphalt mixture CT images based on convolutional neural networks. Road Materials and Pavement Design, 25(5), 1127-1143. https://doi.org/10.1080/14680629.2023.2233630
• 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: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18 (pp. 234-241). Springer international publishing. https://doi.org/10.1007/978-3-319-24574-4_28
• Wang, Z., Zhang, T., & Huang, X. (2024). Explainable deep learning for image-driven fire calorimetry. Applied Intelligence, 54(1), 1047-1062. https://doi.org/10.1007/s10489-023-05231-x
• Xu, G., Yue, Q., Liu, X., & Chen, H. (2024). Investigation on the effect of data quality and quantity of concrete cracks on the performance of deep learning-based image segmentation. Expert Systems with Applications, 237, 121686. https://doi.org/10.1016/j.eswa.2023.121686
• Ye, R. Z., Noll, C., Richard, G., Lepage, M., Turcotte, É. E., & Carpentier, A. C. (2022). DeepImageTranslator: A free, user-friendly graphical interface for image translation using deep-learning and its applications in 3D CT image analysis. SLAS technology, 27(1), 76-84. https://doi.org/10.1016/j.slast.2021.10.014
• Zhang, H., Li, M., Zhong, J., & Qin, J. (2024). CNet: A novel seabed coral reef image segmentation approach based on deep learning. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 767-775). https://doi.org/10.1109/WACVW60836.2024.00090
• Zi, Y., Wang, Q., Gao, Z., Cheng, X., & Mei, T. (2024). Research on the application of deep learning in medical image segmentation and 3d reconstruction. Academic Journal of Science and Technology, 10(2), 8-12. https://pdfs.semanticscholar.org/d900/71bda4ad95986fbe508238a19e755cceff9d.pdf