Deep Learning Applications in Cone-Beam Computed Tomography (CBCT) for Automatic Detection and Segmentation of Periapical Lesions: A Comprehensive Clinical and Radiographic Evaluation
Main Article Content
Abstract
Proper diagnosis and segmentation of periapical lesions using Cone Beam Computed Tomography (CBCT) imaging play an important role in determining the best possible strategy for treatment of such pathologies. Even though CBCT provides a better three-dimensional visualization than regular two-dimensional X-ray images, multi-planar analysis still requires much time and depends on the observer's experience. Deep learning (DL) techniques, especially Convolutional Neural Networks (CNNs), provide an advanced tool that can help solve these issues. In the current research, the clinical performance, segmentation accuracy, and practical issues of modern DL methods are discussed, specifically the 3D DL models, such as 3D U-Net and ResNet, which were used on CBCT images from 2021 to 2026. High sensitivity (higher than 92%), high specificity, and small time needed to conduct the diagnostic procedure have been identified. However, some limitations, such as restoration artifacts, different sizes of voxels, and heterogeneity of datasets, still exist.
Article Details
Issue
Section
How to Cite
References
1. Karamifar, K., Tondari, A., & Saghiri, M. A. (2020). Endodontic Periapical Lesion: An Overview on the Etiology, Diagnosis and Current Treatment Modalities. European Endodontic Journal, 5(2), 54–67. https://doi.org/10.14744/eej.2020.42714.
2. Reiser, Y., Marković, L., Pelivan, I., Ivanišević, A., & Gabrić, D. (2026). Periapical Lesions: Diagnosis, Pathophysiology, and Management. Encyclopedia, 6(6), 125. https://doi.org/10.3390/encyclopedia6060125.
3. Antony, D. P., Thomas, T., & Nivedhitha, M. S. (2020). Two-dimensional Periapical, Panoramic Radiography Versus Three-dimensional Cone-beam Computed Tomography in the Detection of Periapical Lesion After Endodontic Treatment: A Systematic Review. Cureus, 12(4), e7736. https://doi.org/10.7759/cureus.7736.
4. Talakeri, A., Kumar, P., P, S., Chugh, V. K., Sharma, R., & Patnana, A. (2026). Comparative Evaluation of the Accuracy of Two-Dimensional and Three-Dimensional Radiographic Assessment of Bony Defects Before and After Endodontic Surgery. Cureus, 18(1), e101835. https://doi.org/10.7759/cureus.101835.
5. Osterhoff, G., Morgan, E. F., Shefelbine, S. J., Karim, L., McNamara, L. M., & Augat, P. (2016). Bone mechanical properties and changes with osteoporosis. Injury, 47 Suppl 2(Suppl 2), S11–S20. https://doi.org/10.1016/S0020-1383(16)47003-8.
6. Baccher, S., Gowdar, I. M., Guruprasad, Y., Solanki, R. N., Medhi, R., Shah, M. J., & Mehta, D. N. (2024). CBCT: A Comprehensive Overview of its Applications and Clinical Significance in Dentistry. Journal of pharmacy & bioallied sciences, 16(Suppl 3), S1923–S1925. https://doi.org/10.4103/jpbs.jpbs_19_24.
7. Khader, A., Jain, S., Sarah, Mishra, S., Saleem, S., & Vijayan, A. (2024). Comparing Radiation Doses in CBCT and Medical CT Imaging for Dental Applications. Journal of pharmacy & bioallied sciences, 16(Suppl 2), S1795–S1797. https://doi.org/10.4103/jpbs.jpbs_1145_23.
8. Venkatesh, E., & Elluru, S. V. (2017). Cone beam computed tomography: basics and applications in dentistry. Journal of Istanbul University Faculty of Dentistry, 51(3 Suppl 1), S102–S121. https://doi.org/10.17096/jiufd.00289
9. Gosavi, S., Marwaha, J., Binmuhana, N. O., Caliaperoumal, S. K., Alkhalifah, B., & Mustafa, M. (2025). Comparison of AI-based radiographic interpretation versus endodontic specialists for identifying periapical lesions: An in vitro study. Bioinformation, 21(12),4831–4836. https://doi.org/10.6026/973206300214831.
10. John F. Emery, Minh-Khang Le, Joshua Levy, Louis Vaickus, Xiaoying Liu, Machine learning, deep learning, and artificial intelligence as applied to the field of cytopathology: a comprehensive review, Journal of the American Society of Cytopathology, Volume 15, Issue 1, 2026, Pages 4-22, ISSN 2213-2945, https://doi.org/10.1016/j.jasc.2025.07.004.
11. Hamdan, M. H., Uribe, S. E., Tuzova, L., Tuzoff, D., Badr, Z., Mol, A., & Tyndall, D. A. (2025). The influence of a deep learning tool on the performance of oral and maxillofacial radiologists in the detection of apical radiolucencies. Dento maxillo facial radiology, 54(2), 118–124. https://doi.org/10.1093/dmfr/twae054.
12. Sarvamangala, D. R., & Kulkarni, R. V. (2022). Convolutional neural networks in medical image understanding: a survey. Evolutionary Intelligence, 15(1), 1–22. https://doi.org/10.1007/s12065-020-00540-3.
13. Fan, W., Zhang, J., Wang, N., Li, J., & Hu, L. (2023). The Application of Deep Learning on CBCT in Dentistry. Diagnostics (Basel, Switzerland), 13(12), 2056. https://doi.org/10.3390/diagnostics13122056.
14. Gao, S., Wang, X., Xia, Z., Zhang, H., Yu, J., & Yang, F. (2025). Artificial Intelligence in Dentistry: A Narrative Review of Diagnostic and Therapeutic Applications. Medical Science Monitor: International Medical Journal of Experimental and Clinical Research, 31, e946676. https://doi.org/10.12659/MSM.946676.
15. Rašić, M., Tropčić, M., Karlović, P., Gabrić, D., Subašić, M., & Knežević, P. (2023). Detection and Segmentation of Radiolucent Lesions in the Lower Jaw on Panoramic Radiographs Using Deep Neural Networks. Medicina (Kaunas, Lithuania), 59(12), 2138. https://doi.org/10.3390/medicina59122138.
16. Moorthy, C., Shafeek, A., Gurunathan, V., & Sudhakar, R. (2026). 3D CSFA-UNet: a unified attention-driven deep learning framework for accurate knee MRI segmentation and osteoarthritis severity classification. Scientific reports, 16(1), 6878. https://doi.org/10.1038/s41598-026-37847-7.
17. Aloufi A. S. (2026). Detection of Periapical Lesions Using Artificial Intelligence: A Narrative Review. Diagnostics (Basel, Switzerland), 16(2), 301. https://doi.org/10.3390/diagnostics16020301.
18. Sarker I. H. (2021). Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. SN Computer Science, 2(6), 420. https://doi.org/10.1007/s42979-021-00815-1.
19. Eguren, M., Holguin, A., Diaz, K., Vidalon, J., Linan, C., Pacheco-Pereira, C., & Lagravere Vich, M. O. (2022). Can gray values be converted to Hounsfield units? A systematic review. Dento Maxillo Facial Radiology, 51(1), 20210140. https://doi.org/10.1259/dmfr.20210140.
20. Cheng, H., Zhang, Y., Meng, M., Liu, S., Yang, Y., Ran, Y., & Kou, Y. (2026). Artificial intelligence in osteoporosis assessment using CT imaging: a scoping review. Frontiers in Medicine, 13, 1779483. https://doi.org/10.3389/fmed.2026.1779483.
21. Gaêta-Araujo, H., Nascimento, E. H. L., Fontenele, R. C., Mancini, A. X. M., Freitas, D. Q., & Oliveira-Santos, C. (2020). Magnitude of beam-hardening artifacts produced by gutta-percha and metal posts on cone-beam computed tomography with varying tube current. Imaging science in dentistry, 50(1), 1–7. https://doi.org/10.5624/isd.2020.50.1.1.
22. Dennis, D., Suebnukarn, S., Vicharueang, S., & Limprasert, W. (2024). Development and evaluation of a deep learning segmentation model for assessing non-surgical endodontic treatment outcomes on periapical radiographs: A retrospective study. PloS one, 19(12), e0310925. https://doi.org/10.1371/journal.pone.0310925.
23. Yoganathan, S. A., Aouadi, S., Ahmed, S., Paloor, S., Torfeh, T., Al-Hammadi, N., & Hammoud, R. (2023). Generating synthetic images from cone beam computed tomography using self-attention residual UNet for head and neck radiotherapy. Physics and imaging in radiation oncology, 28, 100512. https://doi.org/10.1016/j.phro.2023.100512.
24. Afzal, M., Agarwal, S., Elshaikh, R. H., Babker, A. M. A., Osman, E. A. I., Choudhary, R. K., Jaiswal, S., Zahir, F., Prabhakar, P. K., Abbas, A. M., Shalabi, M. G., & Sah, A. K. (2025). Innovative Diagnostic Approaches and Challenges in the Management of HIV: Bridging Basic Science and Clinical Practice. Life (Basel, Switzerland), 15(2), 209. https://doi.org/10.3390/life15020209.