Application of Deep Learning in Maxillary Sinus Modeling

doi:10.13701/j.cnki.kqyxyj.2026.03.006

Abstract

Abstract: Objective: To explore the effect of SegFormer deep learning model in maxillary sinus modeling. Methods: SegFormer was applied to automatically segment and reconstruct the maxillary sinus from cone-beam CT images of 33 included patients, and the maxillary sinus volume was measured and compared with manual measurements for statistical analysis. Results: Using SegFormer for automated segmentation, reconstruction, and measurement of the maxillary sinus volume takes only about 30 seconds, and is substantially faster than manual measurement, while showing no statistically significant difference in maxillary sinus volume (P>0.05). Conclusion: The SegFormer deep learning model can reconstruct the maxillary sinus more quickly and accurately, reflecting the auxiliary diagnostic value of artificial intelligence in the field of dentistry

Key words: artificial intelligence, maxillary sinus volume, cone-beam computer tomography, three-dimensional reconstruction

LI Fang, PAN Yan, HAN Shuang, ZHUANG Shuo. Application of Deep Learning in Maxillary Sinus Modeling[J]. Journal of Oral Science Research, 2026, 42(3): 206-212.

References

[1] Tarce M, Zhou Y, Antonelli A, et al. The application of artificial intelligence for tooth segmentation in CBCT images: a systematic review[J]. Appl Sci, 2024, 14(14):6298.
[2] Perera S, Navard P, Yilmaz A. SegFormer3D: an efficient transformer for 3D medical image segmentation[J]. IEEE, 2024.
[3] 李学盛.上颌窦底解剖形态的CBCT影像学分析[J].口腔医学研究,2025,41(1):55-59.
[4] Zhang L, Zhang Y, Xu Q, et al. Increased risks of maxillary sinus mucosal thickening in Chinese patients with periapical lesions[J]. Heliyon, 2023, 9(7):e18050.
[5] Oruç K, Akkurt A, Tuncer MC. Relation between orthodontic malocclusion and maxillary sinus volume[J].Folia Morphol (Warsz), 2025, 84(1):200-215.
[6] Taschieri S, Morandi B, Giovarruscio M, et al. Microsurgical endodontic treatment of the upper molar teeth and their relationship with the maxillary sinus: a retrospective multicentric clinical study[J]. BMC Oral Health, 2021, 21(1): 252.
[7] Whyte A, Boeddinghaus R. The maxillary sinus: physiology, development and imaging anatomy[J]. Dentomaxillofac Radiol, 2019, 48 (8):20190205c.
[8] Dinç, K, içöz, D. Maxillary sinus volume changes in individuals with different craniofacial skeletal patterns: CBCT study[J]. BMC Oral Health, 2024,24(1):1516.
[9] Nair AK, Jose M, Sreela LS, et al. Prevalence and pattern of proximity of maxillary posterior teeth to maxillary sinus with mucosal thickening: A cone beam computed tomography based retrospective study[J]. Ann Afr Med, 2023, 22(3):327-332.
[10] Iliescu VI, Nimigean VR, Preoteasa CT, et al. Evaluation of the proximity of the maxillary teeth root apices to the maxillary sinus floor in romanian subjects: A cone-beam computed tomography study[J]. Diagnostics (Basel), 2025, 15(14):1741.
[11] Xue K, Tao Y, Pan D, et al. Cone-beam computed tomography evaluation of maxillary sinus changes in orthodontic patients treated with extraction of four first premolars[J]. Cureus, 2024, 16(7): e65029.
[12] Sun W, Xia K, Huang X. et al. Knowledge of orthodontic tooth movement through the maxillary sinus: a systematic review[J]. BMC Oral Health, 2018, 18(1): 91.
[13] Li S, Bao H, Su X, et al. Orthodontic maxillary molar movement-induced zygomatic pillar remodeling and its consequences on occlusal characteristics and stress distribution[J]. Clin Oral Invest, 2024, 28(7):374.
[14] Chunduru R, Rachel P, Kailasam V, et al. The evaluation of maxillary sinus dimensions in different craniofacial patterns:A systematic review and meta-analysis[J]. Turk J Orthod, 2023, 36(3):208-215.
[15] Tanaka LEB, Franco A, Abib RF, et al. Age- and sex-related changes of the volume of maxillary sinuses quantified via cone beam computed tomography[J]. Res Soc Dev, 2021, 10(14):e31210142222.
[16] Houkes AE. Biological sex variation of the maxillary sinus utilizing 3D computerized tomography within a modern United States population[J]. Forensic Imag, 2024, 36:200570.
[17] Iturralde-Garrote A, Sanz JL, Forner L, et al. Volumetric changes of the paranasal sinuses with age: A systematic review[J]. J Clin Med, 2023, 12(10):3355.
[18] Lessa AMG, Oliveira VS, Costa RBA, et al. Anatomical study of the maxillary sinus: which characteristics can influence its volume?[J]. Surg Radiol Anat, 2023, 45(1): 81-87.
[19] Zhang J, Liu L, Yang L, et al. Diagnosis of odontogenic maxillary sinusitis by cone-beam computed tomography: a critical review[J]. J Endod, 2023, 49(11):1445-1456.
[20] Li M, Jiang Y, Zhang Y,et al. Medical image analysis using deep learning algorithms[J]. Front Public Health, 2023, 11:1273253.
[21] Bayrakdar IS, Elfayome NS, Hussien RA, et al. Artificial intelligence system for automatic maxillary sinus segmentation on cone beam computed tomography images[J]. Dentomaxillofac Radiol, 2024, 53(4):256-266.
[22] Hwang IK, Kang SR, Yang S, et al. SinusC-Net for automatic classification of surgical plans for maxillary sinus augmentation using a 3D distance-guided network[J]. Sci Rep, 2023, 13(1):11653.
[23] Tao B, Xu J, Gao J, et al. Deep learning-based automatic segmentation of bone graft material after maxillary sinus augmentation[J]. Clin Oral Implants Res, 2024, 35(8):964-972.
[24] Kim Y, Lee KJ, Sunwoo L, et al. Deep learning in diagnosis of maxillary sinusitis using conventional radiography[J]. Invest Radiol, 2019, 54(1):7-15.