Application of Mask-RCNN and Mimics in Maxillary Sinus Modeling

doi:10.13701/j.cnki.kqyxyj.2024.06.014

Abstract

Abstract: Objective: To compare the application of Mask RCNN deep learning model and Mimics 3D software in maxillary sinus modeling. Methods: Mask-RCNN and Mimics were applied to reconstruct the maxillary sinus and measure the volume of maxillary sinus from conical beam CT images in 50 patients included. The reconstruction effects of the two methods were compared, and the volume of the maxillary sinus was analyzed. Results: In the process of modeling the maxillary sinus, using Mask-RCNN for image segmentation, post-processing, and reconstruction only took more than 30 seconds, and using Mimics for manual threshold segmentation and reconstruction of maxillary sinus images for each patient took about tens of minutes. There was no significant difference in the volume of the maxillary sinus measured between two methods (P>0.05). Conclusion: The Mask RCNN deep learning algorithm is superior to Mimics and can reconstruct the maxillary sinus more quickly and accurately, reflecting the auxiliary diagnostic value of artificial intelligence in the field of oral and maxillofacial medical imaging.

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

WANG Rong, Pakezhati·SEYITI, WANG Tiemei, ZHANG Yi, QIAN Kun. Application of Mask-RCNN and Mimics in Maxillary Sinus Modeling[J]. Journal of Oral Science Research, 2024, 40(6): 550-554.

References

[1] 帕克扎提·色依提,王铁梅,徐子能,等.基于深度学习在曲面体层图像中人工智能辅助诊断系统初步研究[J].口腔医学研究,2021,37(9):845-849.
[2] Hu JF, Sun J, Lin Z, et al. APANet: Auto-path aggregation for future instance segmentation prediction [J]. IEEE Trans Pattern Anal Mach Intell, 2022, 44(7):3386-3403.
[3] He K, Gkioxari G, Dollar P, et al. Mask R-CNN [J]. IEEE Trans Pattern Anal Mach Intell, 2020, 42(2):386-397.
[4] Yue N, Zhang J, Zhao J, et al. Detection and classification of bronchiectasis based on improved Mask-RCNN [J]. Bioengineering (Basel), 2022, 9(8):359.
[5] Li YZ, Wang Y, Fang KB, et al. Automated meniscus segmentation and tear detection of knee MRI with a 3D mask-RCNN [J]. Eur J Med Res, 2022, 27(1): 247.
[6] 方威扬,林东鑫,寇万福,等.医学图像三维重建系统的研究进展[J].中国医学物理学杂志,2022,39(7): 823-827.
[7] Alqahtani H, Basuhail S, Alsulaimani F, et al. The relationship between maxillary sinus volume and different cephalometric characteristics in orthodontics [J]. Contemp Clin Dent, 2023, 14(3): 191-200.
[8] Aşantoğrol F, Coşgunarslan A. The effect of anatomical variations of the sinonasal region on maxillary sinus volume and dimensions: a three-dimensional study [J]. Braz J Otorhinolaryngol, 2022, 88 Suppl 1(Suppl 1):S118-S127.
[9] Göksel S, Güler AY. Is there a relationship between maxillary sinus’s inferior pneumatisation and sinonasal variations? A retrospective CBCT study [J]. J Oral Maxillofac Res, 2023, 14(3): e3.
[10] Bandong S, Nazaruddin YY, Joelianto E. Faster RCNN mixed-integer optimization with weighted cost function for container detection in port automation [J]. Heliyon, 2023, 9(2):e13213.
[11] Dandekeri SS, Hegde C, Kavassery P, et al. CBCT study of morphologic variations of maxillary sinus septa in relevance to sinus augmentation procedures [J]. Ann Maxillofac Surg, 2020, 10(1): 51-56.
[12] Möhlhenrich SC, Heussen N, Peters F, et al. Is the maxillary sinus really suitable in sex determination? A three-dimensional analysis of maxillary sinus volume and surface depending on sex and dentition [J]. J Craniofac Surg, 2015, 26(8):e723-e726.
[13] 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.
[14] Christoloukas N, Mitsea A, Rontogianni A, et al. Gender determination based on CBCT maxillary sinus analysis: A systematic review [J]. Diagnostics (Basel), 2023, 13(23):3536.
[15] Lessa AMG, Oliveira VS, Costa RBA, et al. Anatomical study of the maxillary sinus: which characteristics can influence its volume? [J]. Surg Radiol Anat, 2022, 45(1): 81-87.