Araştırma Makalesi
BibTex RIS Kaynak Göster

Ağız İçi Görüntüleme Kullanarak Diş Hastalıklarının Erken Tespiti için Yapay Zeka Destekli Mobil Uygulama

Yıl 2025, Cilt: 8 Sayı: 2, 133 - 146, 30.11.2025
https://doi.org/10.34088/kojose.1685185

Öz

Ağız sağlığı, kardiyovasküler bozukluklar, diabetes mellitus ve solunum yolu enfeksiyonları gibi çok sayıda sistemik hastalığın doğrudan veya dolaylı olarak ağız koşullarıyla ilişkili olması nedeniyle genel refahın temel bir bileşenini oluşturmaktadır. Diş hastalıklarının teşhis ve tedavisindeki gecikmeler sadece ağız komplikasyonlarını şiddetlendirmekle kalmaz, aynı zamanda bu sistemik hastalıkların ilerlemesine katkıda bulunarak hem bireysel sağlık yüklerini hem de sağlık sistemleri üzerindeki yükü artırabilir. Yapay zeka (AI) alanındaki son gelişmeler, özellikle tıbbi görüntü analizi alanında, teşhis doğruluğunu ve hızını artırma konusunda önemli bir potansiyel ortaya koymuştur. Büyük ölçüde ağız içi yapıların görsel değerlendirmesine dayanan diş hekimliği, yapay zeka güdümlü teşhis araçlarının entegrasyonu için umut verici bir alan sunmaktadır. YZ kullanımı, dental anomalilerin erken tespitini kolaylaştırabilir, zamanında müdahaleyi mümkün kılabilir ve ilk tarama için özel klinik ortamlara bağımlılığı azaltabilir. Bu çalışma, kullanıcılar tarafından çekilen ağız içi fotoğrafların analizi yoluyla yaygın diş hastalıklarını tespit etmek için tasarlanmış yapay zeka tabanlı bir mobil uygulamanın geliştirilmesini önermektedir. Uygulama, bireylerin ağız boşluğunun görüntülerini yüklemelerine, otomatik tanısal geri bildirim almalarına ve gerekirse belirlenen koşullara göre diş hekimi randevuları planlamalarına olanak tanır. Böyle bir sistemin günlük sağlık hizmeti rutinlerine entegrasyonu, kullanıcıları erişilebilir, gerçek zamanlı dental değerlendirmelerle güçlendirirken, diş hekimliği uzmanlarını da objektif bulgulara dayalı olarak hasta bakımına öncelik vermeleri konusunda desteklemektedir. Önerilen çözüm, erken teşhis ve önleyici bakımı teşvik ederek yalnızca ağız ve sistemik sağlık sonuçlarının iyileştirilmesine katkıda bulunmakla kalmıyor, aynı zamanda mobil ve akıllı teknolojiler aracılığıyla sağlık hizmeti sunumunu dijitalleştirme ve optimize etme yönündeki çağdaş çabalarla da uyum sağlıyor.

Kaynakça

  • [1] Schwendicke F., Rossi J.G., Göstemeyer G., Elhennawy K., Cantu A.G., Gaudin R., Krois J., 2021. Cost-Effectiveness of Artificial Intelligence for Proximal Caries Detection. Journal of Dental Research, 100(4), pp. 369–376.
  • [2] Cantu A.G., Gehrung S., Krois J., Chaurasia A., Rossi J.G., Gaudin R., Schwendicke F., 2020. Detecting Caries Lesions of Different Radiographic Extension on Bitewings Using Deep Learning. Journal of Dentistry, 100, 103425.
  • [3] Srivastava M.M., Kumar P., Pradhan L., Varadarajan S., 2017. Detection of Tooth Caries in Bitewing Radiographs Using Deep Learning. arXiv preprint arXiv:1711.07312.
  • [4] Lee J.H., Kim D.H., Jeong S.N., Choi S.H., 2018. Detection and Diagnosis of Dental Caries Using a Deep Learning-Based Convolutional Neural Network Algorithm. Journal of Dentistry, 77, pp. 106–111.
  • [5] Revilla-León M., Gómez-Polo M., Vyas S., Barmak A.B., Özcan M., Att W., Krishnamurthy V.R., 2022. Artificial Intelligence Applications in Restorative Dentistry: A Systematic Review. The Journal of Prosthetic Dentistry, 128(5), pp. 867–875.
  • [6] Samadzadegan F., Bashizadeh Fakhar H., Hahn M., Ramzi P., 2003. Automatic Registration of Dental Radiograms. Journal of Dental Research, 2–3.
  • [7] Takahashi T., Nozaki K., Gonda T., Mameno T., Ikebe K., 2021. Deep Learning-Based Detection of Dental Prostheses and Restorations. Scientific Reports, 11(1), 1960.
  • [8] Lee J.S., Adhikari S., Liu L., Jeong H.G., Kim H., Yoon S.J., 2019. Osteoporosis Detection in Panoramic Radiographs Using a Deep Convolutional Neural Network-Based Computer-Assisted Diagnosis System: A Preliminary Study. Dentomaxillofacial Radiology, 48(1), 20170344.
  • [9] Bilgir E., Bayrakdar İ.Ş., Çelik Ö., Orhan K., Akkoca F., Sağlam H., Rozylo-Kalinowska I., 2021. An Artificial Intelligence Approach to Automatic Tooth Detection and Numbering in Panoramic Radiographs. BMC Medical Imaging, 21, pp. 1–9.
  • [10] Durmuş M., Ergen B., Çelebi A., Türkoğlu M., 2024. ResNet Tabanlı PSPNet Kullanarak Panoramik Görüntülerde Gömülü Diş Segmentasyon Analizi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 36(1), pp. 159–166.
  • [11] Ünsal Ü., Adem K., 2022. Diş Görüntüleri Üzerinde Görüntü İşleme ve Derin Öğrenme Yöntemleri Kullanılarak Çürük Seviyesinin Sınıflandırılması. Uluslararası Sivas Bilim ve Teknoloji Üniversitesi Dergisi, 2(2), pp. 30–53.
  • [12] Çelik Ö., Odabaş A., Bayrakdar İ.Ş., Bilgir E., Akkoca F., 2019. Derin Öğrenme Yöntemi ile Panoramik Radyografiden Diş Eksikliklerinin Tespiti: Bir Yapay Zekâ Pilot Çalışması. Selçuk Dental Journal, 6(4), pp. 168–172.
  • [13] Wang Y., Sun L., Zhang Y., Lv D., Li Z., Qi W., 2020. An Adaptive Enhancement Based Hybrid CNN Model for Digital Dental X-Ray Positions Classification. arXiv preprint arXiv:2005.01509.
  • [14] Lee J.H., Kim D.H., Jeong S.N., Choi S.H., 2018. Diagnosis and Prediction of Periodontally Compromised Teeth Using a Deep Learning-Based Convolutional Neural Network Algorithm. Journal of Periodontal & Implant Science, 48(2), pp. 114-123.
  • [15] Schwendicke F., Elhennawy K., Paris S., Friebertshäuser P., Krois J., 2020. Deep Learning for Caries Lesion Detection in Near-Infrared Light Transillumination Images: A Pilot Study. Journal of Dentistry, 92, 103260.
  • [16] Tuzoff D.V., Tuzova L.N., Bornstein M.M., Krasnov A.S., Kharchenko M.A., Nikolenko S.I., Sveshnikov M.M., Bednenko G.B., 2019. Tooth Detection and Numbering in Panoramic Radiographs Using Convolutional Neural Networks. Dentomaxillofacial Radiology, 48(4), 20180051.
  • [17] Beser, B. et al. (2024). YOLO-V5 based deep learning approach for tooth detection and segmentation on pediatric panoramic radiographs in mixed dentition. BMC medical imaging, 24(1), 172.
  • [18] Hua, Y., Chen, R., & Qin, H. (2025). YOLO-DentSeg: A Lightweight Real-Time Model for Accurate Detection and Segmentation of Oral Diseases in Panoramic Radiographs. Electronics, 14(4), 805.
  • [19] Hasnain, M. A., Ali, S., Malik, H., Irfan, M., & Maqbool, M. S. (2023). Deep learning-based classification of dental disease using x-rays. Journal of Computing & Biomedical Informatics, 5(01), 82-95.
  • [20] Mei, S., Ma, C., Shen, F., & Wu, H. (2023). YOLOrtho--A Unified Framework for Teeth Enumeration and Dental Disease Detection. arXiv preprint arXiv:2308.05967.
  • [21] Haghanifar, A., Majdabadi, M. M., & Ko, S. B. (2020). Paxnet: Dental caries detection in panoramic x-ray using ensemble transfer learning and capsule classifier. arXiv preprint arXiv:2012.13666.
  • [22] Oral Diseases Dataset, Kaggle Platform, https://www.kaggle.com/datasets/salmansajid05/oral-diseases, (Visiting date: 13.01.2025)
  • [23] Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258.
  • [24] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4510–4520). Salt Lake City, UT, USA.
  • [25] Demir, F. (2021). Derin öğrenme tabanlı yaklaşımla kötü huylu deri kanserinin dermatoskopik görüntülerden saptanması [Detection of malignant skin cancer from dermoscopic images with a deep learning-based approach]. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 33, 617–624.
  • [26] Alhichri, H., Alswayed, A. S., Bazi, Y., Ammour, N., & Alajlan, N. A. (2021). Classification of remote sensing images using EfficientNetB3 CNN model with attention. IEEE Access, 9, 14078–14094.
  • [27] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826.
  • [28] Karadağ, B., Arı, A., & Karadağ, M. (2021). Derin öğrenme modellerinin sinirsel stil aktarımı performanslarının karşılaştırılması [Comparison of neural style transfer performances of deep learning models]. Politeknik Dergisi, 24(4), 1611–1622.
  • [29] Mukti, I. Z., & Biswas, D. (2019). Transfer learning based plant diseases detection using ResNet50. In 2019 4th International Conference on Electrical Information and Communication Technology (EICT), pp. 1–6.
  • [30] Talo, M. (2019). Convolutional neural networks for multi-class histopathology image classification. arXiv Preprint arXiv:1903.10035, 1–16.
  • [31] Koonce, B. (2021). ResNet 50. In Convolutional neural networks with Swift for TensorFlow: Image recognition and dataset categorization, pp. 63–72. Apress.
  • [32] The Annotated ResNet-50. Towards Data Science. Retrieved from https://towardsdatascience.com/the-annotated-resnet-50-a6c536034758/, (Visiting date: 13.01.2025)
  • [33] Liu, L., Xu, J., Huan, Y., Zou, Z., Yeh, S. C., & Zheng, L. R. (2019). A smart dental health-IoT platform based on intelligent hardware, deep learning, and mobile terminal. IEEE Journal of Biomedical and Health Informatics, 24(3), 898–906.
  • [34] Garg, A., Lu, J., & Maji, A. (2023). Towards earlier detection of oral diseases on smartphones using oral and dental RGB images. arXiv Preprint arXiv: 2308.15705.
  • [35] Malaviya, P. (2024). Oral classification using Attention U-Net VGG16 [Jupyter Notebook]. Kaggle. https://www.kaggle.com/code/priyanshumalaviya228/ oral-classification-attention-u-net-vgg16/notebook.

AI-Powered Mobile Application for Early Detection of Dental Diseases Using Intraoral Imaging

Yıl 2025, Cilt: 8 Sayı: 2, 133 - 146, 30.11.2025
https://doi.org/10.34088/kojose.1685185

Öz

Oral health constitutes a fundamental component of overall well-being, with numerous systemic diseases, such as cardiovascular disorders, diabetes mellitus, and respiratory tract infections, being directly or indirectly associated with oral conditions. Delays in the diagnosis and treatment of dental diseases not only exacerbate oral complications but may also contribute to the progression of these systemic disorders, increasing both individual health burdens and the strain on healthcare systems. Recent advancements in artificial intelligence (AI), particularly in the domain of medical image analysis, have demonstrated significant potential in enhancing diagnostic accuracy and speed. Dentistry, which heavily relies on the visual assessment of intraoral structures, presents a promising field for the integration of AI-driven diagnostic tools. The use of AI can facilitate early detection of dental anomalies, enable timely intervention, and reduce the dependency on specialized clinical settings for initial screening. This study proposes the development of an AI-based mobile application that utilizes the ResNet50 model to detect common dental diseases through the analysis of intraoral photographs captured by users. Our model achieved an accuracy of 99.00%, a precision of 0.99, a recall of 0.99, and an F1-score of 0.99 on the test dataset. The application enables individuals to upload images of their oral cavity, receive automated diagnostic feedback, and, if necessary, schedule dental appointments based on the identified conditions. The integration of such a system into daily healthcare routines empowers users with accessible, real-time dental evaluations while supporting dental professionals in prioritizing patient care based on objective findings. By promoting early diagnosis and preventive care, the proposed solution not only contributes to improved oral and systemic health outcomes but also aligns with contemporary efforts to digitalize and optimize healthcare delivery through mobile and intelligent technologies.

Kaynakça

  • [1] Schwendicke F., Rossi J.G., Göstemeyer G., Elhennawy K., Cantu A.G., Gaudin R., Krois J., 2021. Cost-Effectiveness of Artificial Intelligence for Proximal Caries Detection. Journal of Dental Research, 100(4), pp. 369–376.
  • [2] Cantu A.G., Gehrung S., Krois J., Chaurasia A., Rossi J.G., Gaudin R., Schwendicke F., 2020. Detecting Caries Lesions of Different Radiographic Extension on Bitewings Using Deep Learning. Journal of Dentistry, 100, 103425.
  • [3] Srivastava M.M., Kumar P., Pradhan L., Varadarajan S., 2017. Detection of Tooth Caries in Bitewing Radiographs Using Deep Learning. arXiv preprint arXiv:1711.07312.
  • [4] Lee J.H., Kim D.H., Jeong S.N., Choi S.H., 2018. Detection and Diagnosis of Dental Caries Using a Deep Learning-Based Convolutional Neural Network Algorithm. Journal of Dentistry, 77, pp. 106–111.
  • [5] Revilla-León M., Gómez-Polo M., Vyas S., Barmak A.B., Özcan M., Att W., Krishnamurthy V.R., 2022. Artificial Intelligence Applications in Restorative Dentistry: A Systematic Review. The Journal of Prosthetic Dentistry, 128(5), pp. 867–875.
  • [6] Samadzadegan F., Bashizadeh Fakhar H., Hahn M., Ramzi P., 2003. Automatic Registration of Dental Radiograms. Journal of Dental Research, 2–3.
  • [7] Takahashi T., Nozaki K., Gonda T., Mameno T., Ikebe K., 2021. Deep Learning-Based Detection of Dental Prostheses and Restorations. Scientific Reports, 11(1), 1960.
  • [8] Lee J.S., Adhikari S., Liu L., Jeong H.G., Kim H., Yoon S.J., 2019. Osteoporosis Detection in Panoramic Radiographs Using a Deep Convolutional Neural Network-Based Computer-Assisted Diagnosis System: A Preliminary Study. Dentomaxillofacial Radiology, 48(1), 20170344.
  • [9] Bilgir E., Bayrakdar İ.Ş., Çelik Ö., Orhan K., Akkoca F., Sağlam H., Rozylo-Kalinowska I., 2021. An Artificial Intelligence Approach to Automatic Tooth Detection and Numbering in Panoramic Radiographs. BMC Medical Imaging, 21, pp. 1–9.
  • [10] Durmuş M., Ergen B., Çelebi A., Türkoğlu M., 2024. ResNet Tabanlı PSPNet Kullanarak Panoramik Görüntülerde Gömülü Diş Segmentasyon Analizi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 36(1), pp. 159–166.
  • [11] Ünsal Ü., Adem K., 2022. Diş Görüntüleri Üzerinde Görüntü İşleme ve Derin Öğrenme Yöntemleri Kullanılarak Çürük Seviyesinin Sınıflandırılması. Uluslararası Sivas Bilim ve Teknoloji Üniversitesi Dergisi, 2(2), pp. 30–53.
  • [12] Çelik Ö., Odabaş A., Bayrakdar İ.Ş., Bilgir E., Akkoca F., 2019. Derin Öğrenme Yöntemi ile Panoramik Radyografiden Diş Eksikliklerinin Tespiti: Bir Yapay Zekâ Pilot Çalışması. Selçuk Dental Journal, 6(4), pp. 168–172.
  • [13] Wang Y., Sun L., Zhang Y., Lv D., Li Z., Qi W., 2020. An Adaptive Enhancement Based Hybrid CNN Model for Digital Dental X-Ray Positions Classification. arXiv preprint arXiv:2005.01509.
  • [14] Lee J.H., Kim D.H., Jeong S.N., Choi S.H., 2018. Diagnosis and Prediction of Periodontally Compromised Teeth Using a Deep Learning-Based Convolutional Neural Network Algorithm. Journal of Periodontal & Implant Science, 48(2), pp. 114-123.
  • [15] Schwendicke F., Elhennawy K., Paris S., Friebertshäuser P., Krois J., 2020. Deep Learning for Caries Lesion Detection in Near-Infrared Light Transillumination Images: A Pilot Study. Journal of Dentistry, 92, 103260.
  • [16] Tuzoff D.V., Tuzova L.N., Bornstein M.M., Krasnov A.S., Kharchenko M.A., Nikolenko S.I., Sveshnikov M.M., Bednenko G.B., 2019. Tooth Detection and Numbering in Panoramic Radiographs Using Convolutional Neural Networks. Dentomaxillofacial Radiology, 48(4), 20180051.
  • [17] Beser, B. et al. (2024). YOLO-V5 based deep learning approach for tooth detection and segmentation on pediatric panoramic radiographs in mixed dentition. BMC medical imaging, 24(1), 172.
  • [18] Hua, Y., Chen, R., & Qin, H. (2025). YOLO-DentSeg: A Lightweight Real-Time Model for Accurate Detection and Segmentation of Oral Diseases in Panoramic Radiographs. Electronics, 14(4), 805.
  • [19] Hasnain, M. A., Ali, S., Malik, H., Irfan, M., & Maqbool, M. S. (2023). Deep learning-based classification of dental disease using x-rays. Journal of Computing & Biomedical Informatics, 5(01), 82-95.
  • [20] Mei, S., Ma, C., Shen, F., & Wu, H. (2023). YOLOrtho--A Unified Framework for Teeth Enumeration and Dental Disease Detection. arXiv preprint arXiv:2308.05967.
  • [21] Haghanifar, A., Majdabadi, M. M., & Ko, S. B. (2020). Paxnet: Dental caries detection in panoramic x-ray using ensemble transfer learning and capsule classifier. arXiv preprint arXiv:2012.13666.
  • [22] Oral Diseases Dataset, Kaggle Platform, https://www.kaggle.com/datasets/salmansajid05/oral-diseases, (Visiting date: 13.01.2025)
  • [23] Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258.
  • [24] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4510–4520). Salt Lake City, UT, USA.
  • [25] Demir, F. (2021). Derin öğrenme tabanlı yaklaşımla kötü huylu deri kanserinin dermatoskopik görüntülerden saptanması [Detection of malignant skin cancer from dermoscopic images with a deep learning-based approach]. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 33, 617–624.
  • [26] Alhichri, H., Alswayed, A. S., Bazi, Y., Ammour, N., & Alajlan, N. A. (2021). Classification of remote sensing images using EfficientNetB3 CNN model with attention. IEEE Access, 9, 14078–14094.
  • [27] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826.
  • [28] Karadağ, B., Arı, A., & Karadağ, M. (2021). Derin öğrenme modellerinin sinirsel stil aktarımı performanslarının karşılaştırılması [Comparison of neural style transfer performances of deep learning models]. Politeknik Dergisi, 24(4), 1611–1622.
  • [29] Mukti, I. Z., & Biswas, D. (2019). Transfer learning based plant diseases detection using ResNet50. In 2019 4th International Conference on Electrical Information and Communication Technology (EICT), pp. 1–6.
  • [30] Talo, M. (2019). Convolutional neural networks for multi-class histopathology image classification. arXiv Preprint arXiv:1903.10035, 1–16.
  • [31] Koonce, B. (2021). ResNet 50. In Convolutional neural networks with Swift for TensorFlow: Image recognition and dataset categorization, pp. 63–72. Apress.
  • [32] The Annotated ResNet-50. Towards Data Science. Retrieved from https://towardsdatascience.com/the-annotated-resnet-50-a6c536034758/, (Visiting date: 13.01.2025)
  • [33] Liu, L., Xu, J., Huan, Y., Zou, Z., Yeh, S. C., & Zheng, L. R. (2019). A smart dental health-IoT platform based on intelligent hardware, deep learning, and mobile terminal. IEEE Journal of Biomedical and Health Informatics, 24(3), 898–906.
  • [34] Garg, A., Lu, J., & Maji, A. (2023). Towards earlier detection of oral diseases on smartphones using oral and dental RGB images. arXiv Preprint arXiv: 2308.15705.
  • [35] Malaviya, P. (2024). Oral classification using Attention U-Net VGG16 [Jupyter Notebook]. Kaggle. https://www.kaggle.com/code/priyanshumalaviya228/ oral-classification-attention-u-net-vgg16/notebook.
Toplam 35 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Bilgisayar Görüşü ve Çoklu Ortam Hesaplama (Diğer)
Bölüm Araştırma Makalesi
Yazarlar

Burçin Güngör Bu kişi benim 0009-0001-9798-5752

Uğur Yüzgeç 0000-0002-5364-6265

Zafer Serin Bu kişi benim 0000-0002-5213-8517

Yayımlanma Tarihi 30 Kasım 2025
Gönderilme Tarihi 27 Nisan 2025
Kabul Tarihi 1 Haziran 2025
Yayımlandığı Sayı Yıl 2025 Cilt: 8 Sayı: 2

Kaynak Göster

APA Güngör, B., Yüzgeç, U., & Serin, Z. (2025). AI-Powered Mobile Application for Early Detection of Dental Diseases Using Intraoral Imaging. Kocaeli Journal of Science and Engineering, 8(2), 133-146. https://doi.org/10.34088/kojose.1685185