KaydedilenlerDerginizi ekleyin

Dergiler / Mühendislik Bilimleri ve Tasarım Dergisi / 2026 / Cilt: 14 Sayı: 2

ÇOCUKLARIN DENTAL PANORAMİK RADYOGRAFİLERİNDE YAMA TABANLI DİŞ SEGMENTASYONU

PATCH-BASED TOOTH SEGMENTATION ON CHILDREN'S DENTAL PANORAMIC RADIOGRAPHS

Nida Kumbasar(TÜBİTAK-BİLGEM)0000-0001-5497-4618
Emin Argun Oral(Atatürk Üniversitesi)0000-0002-8120-9679
Yücel Özbek(Atatürk Üniversitesi)0000-0002-5734-7430
Sayfa
153–169
Yayın Tarihi
2026-06-30
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

Deneysel sonuçlar, PSPNet, DeepLabv3+ ve U-Net için en iyi segmentasyon performansının 8-yama yaklaşımıyla elde edildiğini, R2 U-Net'in ise 16-yama konfigürasyonuyla en iyi performansı gösterdiğini ortaya koymuştur.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Dental Panoramik Radyografisi (DPR), ağız sağlığını değerlendirmek için yaygın olarak kullanılan bir görüntüleme yöntemidir.
📊
Temel Bulgular & Veri:Bununla birlikte, süt dişlerinin değişken morfolojisi ve 2 boyutlu projeksiyonlarda üst üste binen anatomik yapıların doğasında var olan karmaşıklık nedeniyle, pediatrik DPR'lerde doğru diş segmentasyonu önemli bir zorluk olmaya devam etmektedir.
💡
Sonuç & Katkı:Deneysel sonuçlar, PSPNet, DeepLabv3+ ve U-Net için en iyi segmentasyon performansının 8-yama yaklaşımıyla elde edildiğini, R2 U-Net'in ise 16-yama konfigürasyonuyla en iyi performansı gösterdiğini ortaya koymuştur.
🔬Tür:Modelleme & Sayısal Simülasyon
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:Diş Segmentasyonu · Panoramik Radyografi · Görüntü Yamalama

Özet

Dental Panoramik Radyografisi (DPR), ağız sağlığını değerlendirmek için yaygın olarak kullanılan bir görüntüleme yöntemidir. Bununla birlikte, süt dişlerinin değişken morfolojisi ve 2 boyutlu projeksiyonlarda üst üste binen anatomik yapıların doğasında var olan karmaşıklık nedeniyle, pediatrik DPR'lerde doğru diş segmentasyonu önemli bir zorluk olmaya devam etmektedir. Bu çalışma, yama tabanlı derin öğrenme (DÖ) yaklaşımı kullanarak pediatrik DPR'lerde segmentasyon doğruluğunu artırmak amacıyla yapılmıştır. Modeller, 193 pediatrik DPR ve bunlara karşılık gelen gerçek maskelerden oluşan nispeten yeni CDPR veri seti kullanılarak eğitilmiştir. Optimal giriş boyutunu araştırmak için, görüntüler tam çözünürlüklü görüntülere ek olarak 2, 4, 8, 16 ve 32 yamaya bölünmüştür. Beş önde gelen DÖ modeli—PSPNet, DeepLabv3+, R2 U-Net, U-Net ve U-Net++—bu farklı yama konfigürasyonlarında eğitilmiş ve değerlendirilmiştir. Daha sonra, kapsamlı değerlendirme için tam boyutlu segmentlenmiş görüntüleri yeniden oluşturmak üzere özne tabanlı bir yama yeniden yapılandırma yöntemi uygulanmıştır. Deneysel sonuçlar, PSPNet, DeepLabv3+ ve U-Net için en iyi segmentasyon performansının 8-yama yaklaşımıyla elde edildiğini, R2 U-Net'in ise 16-yama konfigürasyonuyla en iyi performansı gösterdiğini ortaya koymuştur. Özellikle, 2-yama yaklaşımını kullanan U-Net++ modeli, diğer tüm modelleri ve konfigürasyonları geride bırakarak 0,9222'lik en yüksek Dice skoruna ulaşmıştır. Bu bulgular, yama tabanlı eğitimin pediatrik DPR'lerde segmentasyon performansını önemli ölçüde iyileştirdiğini göstermektedir; bu da özellikle sınırlı veri koşullarında son derece değerli bir sonuçtur. Bu yeni yaklaşım, segmentasyon doğruluğunu ve genel iş akışı verimliliğini artırarak pediatrik diş bakımını etkili bir şekilde desteklemek için klinik entegrasyon açısından umut verici sonuçlar sunmaktadır.

Abstract

Dental Panoramic Radiography (DPR) is a widely utilized imaging modality for assessing oral health. However, accurate tooth segmentation in pediatric DPRs remains a significant challenge due to the variable morphology of deciduous teeth and the inherent complexity of overlapping anatomical structures in 2D projections. This study was conducted to enhance segmentation accuracy in pediatric DPRs by employing a patch-based deep learning (DL) approach. The models were trained using the relatively recent CDPR dataset, which consists of 193 pediatric DPRs and their corresponding ground truth masks. To investigate the optimal input size, the images were divided into 2, 4, 8, 16, and 32 patches, in addition to the full-resolution images. Five prominent DL models—PSPNet, DeepLabv3+, R2 U-Net, U-Net, and U-Net++—were trained and evaluated across these different patch configurations. A subject-based patch reconstruction method was subsequently implemented to rebuild the full-size segmented images for comprehensive evaluation. Experimental results indicated that the optimal segmentation performance for PSPNet, DeepLabv3+, and U-Net was achieved with the 8-patch approach, while R2 U-Net performed best with the 16-patch configuration. Notably, the U-Net++ model using a 2-patch approach outperformed all other models and configurations, achieving the highest Dice score of 0.9222. These findings demonstrate that patch-based training significantly improves segmentation performance in pediatric DPRs, which is a particularly valuable outcome under limited data conditions. This novel approach offers promising results for clinical integration, effectively supporting pediatric dental care by enhancing segmentation accuracy and overall workflow efficiency.

🔖

Bu Makaleye Atıf Yap

Kumbasar, N., Oral, E. A., Özbek, Y. (2026). ÇOCUKLARIN DENTAL PANORAMİK RADYOGRAFİLERİNDE YAMA TABANLI DİŞ SEGMENTASYONU. Mühendislik Bilimleri ve Tasarım Dergisi, Cilt: 14 Sayı: 2, 153–169. https://doi.org/10.21923/jesd.1779687

📄 Tam Metin PDF Okuyucu

📄

PDF görüntüleyici hazırlanıyor...

Kaynakça (45)

  1. Almalki, S.A., Alsubai, S., Alqahtani, A., Alenazi, A.A., 2023. Denoised Encoder-Based Residual U-Net for Precise Teeth Image Segmentation and Damage Prediction on Panoramic Radiographs. Journal of Dentistry, 137, 104651.
  2. Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T.M., Asari, V.K., 2018. Recurrent Residual Convolutional Neural Network Based on U-Net (R2U-Net) for Medical Image Segmentation. ArXiv Preprint, ArXiv:1802.06955.
  3. Ammar, H.H., Ngan, P., Crout, R.J., Mucino, V.H., Mukdadi, O.M., 2011. Three-Dimensional Modeling and Finite Element Analysis in Treatment Planning for Orthodontic Tooth Movement. American Journal of Orthodontics and Dentofacial Orthopedics, 139 (1), e59–e71.
  4. Cha, J.-Y., Yoon, H.-I., Yeo, I.-S., Huh, K.-H., Han, J.-S., 2021. Panoptic Segmentation on Panoramic Radiographs: Deep Learning-Based Segmentation of Various Structures Including Maxillary Sinus and Mandibular Canal. Journal of Clinical Medicine, 10 (12), 2577.
  5. Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L., 2017a. Deeplab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40 (4), 834–848.
  6. Chen, L.-C., Papandreou, G., Schroff, F., Adam, H., 2017b. Rethinking Atrous Convolution for Semantic Image Segmentation. ArXiv, abs/1706.05587.
  7. Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H., 2018. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the European Conference on Computer Vision (ECCV), 801–818.
  8. Cordier, N., Menze, B., Delingette, H., Ayache, N., 2013. Patch-Based Segmentation of Brain Tissues. MICCAI Challenge on Multimodal Brain Tumor Segmentation, 6–17.
  9. Cui, Z., Yang, J., Qiao, Y., 2016. Brain MRI Segmentation with Patch-Based CNN Approach. 35th Chinese Control Conference (CCC), 7026–7031.
  10. Day, B., Üzen, H., Çiçek, İ.B., Duman, Ş.B., 2023. A Novel Deep Learning-Based Approach for Segmentation of Different Type Caries Lesions on Panoramic Radiographs. Diagnostics, 13 (2), 202.
  11. Güller, M.T., Kumbasar, N., Miloğlu, Ö., 2024. Evaluation of the Effectiveness of Panoramic Radiography in Impacted Mandibular Third Molars on Deep Learning Models Developed with Findings Obtained with Cone Beam Computed Tomography. Oral Radiology, 1–16.
  12. Güller, M.T., Kumbasar, N., Miloğlu, Ö., Özbek, İ.Y., Oral, E.A., 2026. Winter Classification of Mandibular Impacted Third Molars Based On Convolutional Neural Networks. Current Research in Dental Sciences, 36 (2), 133–139.
  13. Jader, G., Fontineli, J., Ruiz, M., Abdalla, K., Pithon, M., Oliveira, L., 2018. Deep Instance Segmentation of Teeth in Panoramic X-Ray Images. 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 400–407.
  14. Kim, H., Jung, J., Kim, J., Cho, B., Kwak, J., Jang, J.Y., Lee, S., Lee, J.-G., Yoon, S.M., 2020. Abdominal Multi-Organ Auto-Segmentation Using 3D-Patch-Based Deep Convolutional Neural Network. Scientific Reports, 10 (1), 6204.
  15. Koch, T.L., Perslev, M., Igel, C., Brandt, S.S., 2019. Accurate Segmentation of Dental Panoramic Radiographs with U-Nets. IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 15–19.
  16. Kumari, A.R., Rao, S.N., Reddy, P.R., 2022. Design of Hybrid Dental Caries Segmentation and Caries Detection with Meta-Heuristic-Based ResneXt-RNN. Biomedical Signal Processing and Control, 78, 103961.
  17. Kumbasar, N., Güller, M.T., Miloğlu, Ö., Oral, E.A., Ozbek, I.Y., 2025. Deep-Learning Based Fusion of Spatial Relationship Classification Between Mandibular Third Molar and Inferior Alveolar Nerve Using Panoramic Radiograph Images. Biomedical Signal Processing and Control, 100, 107059.
  18. Kumbasar, N., Oral, E.A., Ozbek, I.Y., 2026. Fusion Based Collective Intelligence Segmentation Using Panoramic Radiograph Images. Human-Intelligent Systems Integration, 1–18.
  19. Lai, Y., Fan, F., Wu, Q., Ke, W., Liao, P., Deng, Z., Chen, H., Zhang, Y., 2020. Lcanet: Learnable Connected Attention Network for Human Identification Using Dental Images. IEEE Transactions on Medical Imaging, 40 (3), 905–915.
  20. Miloğlu, Ö., Kumbasar, N., Tosun, Z.T., Güller, M.T., Özbek, İ.Y., 2025. Gender Classification With Hand-Wrist Radiographs Using the Deep Learning Method. Current Research in Dental Sciences, 35 (1), 2–7.
  21. Mohan, R., Arunmozhi, R., Rajinikanth, V., 2023. Deep-Learning Segmentation and Recognition of Tooth in Thresholded Panoramic X-Ray. Winter Summit on Smart Computing and Networks (WiSSCoN), 1–5.
  22. Müller, D., Soto-Rey, I., Kramer, F., 2022. Towards a Guideline for Evaluation Metrics in Medical Image Segmentation. BMC Research Notes, 15 (1), 1–8.
  23. Nafiiyah, N., Fatichah, C., Herumurti, D., Astuti, E.R., Putra, R.H., Prakasa, E., 2022. Mandibular Segmentation on Panoramic Radiographs with CNN Transfer Learning. IEEE International Conference on Communication, Networks and Satellite (COMNETSAT), 190–194.
  24. Nishitani, Y., Nakayama, R., Hayashi, D., Hizukuri, A., Murata, K., 2021. Segmentation of Teeth in Panoramic Dental X-Ray Images Using U-Net with a Loss Function Weighted on the Tooth Edge. Radiological Physics and Technology, 14, 64–69.
  25. Oktay, A.B., Gurses, A., 2021. Detection, Segmentation, and Numbering of Teeth in Dental Panoramic Images with Mask Regions with Convolutional Neural Network Features. State of the Art in Neural Networks and their Applications, içinde (s. 73–90). Elsevier.
  26. Panetta, K., Rajendran, R., Ramesh, A., Rao, S.P., Agaian, S., 2021. Tufts Dental Database: A Multimodal Panoramic X-Ray Dataset for Benchmarking Diagnostic Systems. IEEE Journal of Biomedical and Health Informatics, 26 (4), 1650–1659.
  27. Perschbacher, S., 2012. Interpretation of Panoramic Radiographs. Australian Dental Journal, 57, 40–45.
  28. Ronneberger, O., Fischer, P., Brox, T., 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015, 18, 234–241.
  29. Sedik, A., Kolivand, H., Albeedan, M., 2024. An Efficient Image Classification and Segmentation Method for Crime Investigation Applications. Multimedia Tools and Applications, 1–25.
  30. Sengun, B., Iscan, Y., Ozbulak, G.A.T., Kumbasar, N., Egriboz, E., Sormaz, I.C., Aksakal, N., Deniz, S.M., Haklidir, M., Tunca, F., et al., 2023. Artificial Intelligence in Minimally Invasive Adrenalectomy: Using Deep Learning to Identify the Left Adrenal Vein. Surgical Laparoscopy Endoscopy & Percutaneous Techniques, 33 (4), 327–331.
  31. Sheng, C., Wang, L., Huang, Z., Wang, T., Guo, Y., Hou, W., Xu, L., Wang, J., Yan, X., 2023. Transformer-Based Deep Learning Network for Tooth Segmentation on Panoramic Radiographs. Journal of Systems Science and Complexity, 36 (1), 257–272.
  32. Silva, G., Oliveira, L., Pithon, M., 2018. Automatic Segmenting Teeth in X-Ray Images: Trends, a Novel Data Set, Benchmarking and Future Perspectives. Expert Systems with Applications, 107, 15–31.
  33. Tosun, Z.T., Kumbasar, N., Sumbullu, M.A., Miloglu, O., 2025. Evaluation of the Effectiveness of Artificial Intelligence Models in Radiopaque and Radiolucent Lesions of the Maxillofacial Region on Panoramic Radiographs. Oral Radiology, 1–15.
  34. Vural, Ş.F., Kumbasar, N., 2025. Comparison of VT-Based and CNN-Based Models on Teeth Segmentation. Balkan Journal of Electrical and Computer Engineering, 13 (2), 148–156.
  35. Wang, C., Zhao, Z., Ren, Q., Xu, Y., Yu, Y., 2019. Dense U-Net Based on Patch-Based Learning for Retinal Vessel Segmentation. Entropy, 21 (2), 168.
  36. Wang, X., Gao, S., Jiang, K., Zhang, H., Wang, L., Chen, F., Yu, J., Yang, F., 2023. Multi-Level Uncertainty Aware Learning for Semi-Supervised Dental Panoramic Caries Segmentation. Neurocomputing, 540, 126208.
  37. Wirtz, A., Mirashi, S.G., Wesarg, S., 2018. Automatic Teeth Segmentation in Panoramic X-Ray Images Using a Coupled Shape Model in Combination with a Neural Network. Medical Image Computing and Computer Assisted Intervention–MICCAI 2018, 11, 712–719.
  38. Xie, Z., Gillies, D., 2016. Patch Forest: A Hybrid Framework of Random Forest and Patch-Based Segmentation. Medical Imaging 2016: Image Processing, 9784, 598–605.
  39. Xu, X., Liu, C., Zheng, Y., 2018. 3D Tooth Segmentation and Labeling Using Deep Convolutional Neural Networks. IEEE Transactions on Visualization and Computer Graphics, 25 (7), 2336–2348.
  40. Yu, D., Hu, J., Feng, Z., Song, M., Zhu, H., 2022. Deep Learning Based Diagnosis for Cysts and Tumors of Jaw with Massive Healthy Samples. Scientific Reports, 12 (1), 1855.
  41. Zhang, Y., Ye, F., Chen, L., Xu, F., Chen, X., Wu, H., Cao, M., Li, Y., Wang, Y., Huang, X., 2023. Children’s Dental Panoramic Radiographs Dataset for Caries Segmentation and Dental Disease Detection. Scientific Data, 10 (1), 380.
  42. Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J., 2017. Pyramid Scene Parsing Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2881–2890.
  43. Zhao, X., Xu, T., Peng, L., Li, S., Zhao, Y., Liu, H., He, J., Liang, S., 2023. Recognition and Segmentation of Teeth and Mandibular Nerve Canals in Panoramic Dental X-Rays by Mask RCNN. Displays, 78, 102447.
  44. Zhao, Y., Li, P., Gao, C., Liu, Y., Chen, Q., Yang, F., Meng, D., 2020. TSASNet: Tooth Segmentation on Dental Panoramic X-Ray Images by Two-Stage Attention Segmentation Network. Knowledge-Based Systems, 206, 106338.
  45. Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., Liang, J., 2018. UNet++: A Nested U-Net Architecture for Medical Image Segmentation. D. Stoyanov, Z. Taylor, G. Carneiro, T. Syeda-Mahmood, A. Martel, L. Maier-Hein, J.M.R.S. Tavares, A. Bradley, J.P. Papa, V. Belagiannis, J.C. Nascimento, Z. Lu, S. Conjeti, M. Moradi, H. Greenspan, A. Madabhushi (Edt.), Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support içinde (s. 3–11). Berlin: Springer International Publishing