Application and research advance of deep learning in the diagnosis and treatment of dento-maxillofacial deformities

doi:10.19438/j.cjoms.2022.04.016

Abstract

Abstract: Digital technology provides an ideal auxiliary method for the diagnosis and treatment of dento-maxillofacial deformities. However, due to technical limitations, current digital orthognathic surgery has problems such as semi-automated image processing and insufficient utilization of 3D images. The urgent need for clinicians to improve efficiency and optimize the diagnosis and treatment has prompted a series of researches on deep learning-assisted diagnosis and treatment of dento-maxillofacial deformities, which demonstrated the great potential of applying deep learning in this field. Therefore, this paper reviewed the development history of interdisciplinary researches between deep learning and medicine at first, and then focused on the application and research advance of deep learning in the diagnosis and treatment of dento-maxillofacial deformities, and furthermore exploring the intelligent diagnosis and treatment.

Key words: Deep learning, Dento-maxillofacial deformity, Artificial intelligence, Surgical design, Three dimensional measurement

CLC Number:

R782.2

TAO Le-ran, ZHANG Rong-bin, LIN Yu-xin, LING Zong-xiang, CHENG Meng-jia, YU Hong-bo. Application and research advance of deep learning in the diagnosis and treatment of dento-maxillofacial deformities[J]. China Journal of Oral and Maxillofacial Surgery, 2022, 20(4): 405-409.

References

[1] Bouletreau P, Makaremi M, Ibrahim B, et al.Artificial intelligence: applications in orthognathic surgery[J]. J Stomatol Oral Maxillofac Surg, 2019, 120(4): 347-354.
[2] Zheng Z, Yan H, Setzer FC, et al.Anatomically constrained deep learning for automating dental CBCT segmentation and lesion detection[J]. IEEE T Autom Sci Eng, 2021, 18(2): 603-614.
[3] Wu L, Zhang J, Zhou W, et al.Randomised controlled trial of WISENSE, a real-time quality improving system for monitoring blind spots during esophagogastroduodenoscopy[J]. Gut, 2019, 68(12): 2161-2169.
[4] Bird D, Nix MG, Mccallum H, et al. Multicentre, deep learning, synthetic-CT generation for ano-rectal MR-only radiotherapy treatment planning [J]. Radiother Oncol, 2021(1), 156: 23-28.
[5] Hooshmand SA, Zarei Ghobadi M, Hooshmand SE, et al.A multimodal deep learning-based drug repurposing approach for treatment of COVID-19[J]. Mol Divers, 2021, 25(3): 1717-1730.
[6] Hwang HW, Park JH, Moon JH, et al.Automated identification of cephalometric landmarks: part 2- Might it be better than human?[J]. Angle Orthod, 2020, 90(1): 69-76.
[7] Chen X, Lian C, Deng HH, et al.Fast and accurate craniomaxillofacial landmark detection via 3D Faster R-CNN[J]. IEEE T Autom Sci Eng, 2021, 40(12): 3867-3878.
[8] Yankun L, Li W, Pew-thian Y, et al. Automatic detection of craniomaxillofacial anatomical landmarks on CBCT images using 3D mask R-CNN [C]//Zhang DQ, Zhou LP, Jie B, et al. Graph learning in medical imaging[M]. Springer, Cham,2019:130-137.
[9] Zhang J, Liu M, Wang L, et al.Joint craniomaxillofacial bone segmentation and landmark digitization by context-guided fully convolutional networks[J]. Med Image Comput Comput Assist Interv, 2017,10434:720-728.
[10] Lee S, Woo S, Yu J, et al.Automated CNN-based tooth segmentation in cone-beam CT for Dental implant planning[J]. IEEE Access, 2020, 8: 50507-50518.
[11] Wang H, Minnema J, Batenburg KJ, et al.Multiclass CBCT image segmentation for orthodontics with deep learning[J]. J Dent Res, 2021, 100(9): 943-949.
[12] Zhang X, Li Z, Lv P, et al.Registration algorithms of dental cast based on unorganized 3D point-cloud[J]. Comput Eng Appl, 2012, 48(19): 16-19.
[13] Chung M, Lee J, Song W, et al.Automatic registration between dental cone-beam CT and scanned surface via deep pose regression neural networks and clustered similarities[J]. IEEE T Autom Sci Eng, 2020, 39(12): 3900-3909.
[14] 朱玉佳, 许晴, 赵一姣,等. 深度学习算法辅助构建三维颜面正中矢状平面[J]. 北京大学学报(医学版), 2022, 54(1): 134-139.
Zhu YJ, Xu Q, Zhao YJ, et al.Deep learning-assisted construction of three-demensional facial midsagittal plane[J]. Journal of Peking University:Health Sciences, 2022, 54(1): 134-139.
[15] Dalvit Carvalho da Silva R, Jenkyn TR, Carranza VA. Convolutional neural networks and geometric moments to identify the bilateral symmetric midplane in facial skeletons from CT scans[J]. Biology, 2021, 10(3): 182-190.
[16] Kim I, Misra D, Rodriguez L, et al.Malocclusion classification on 3D cone-beam CT craniofacial images using multi-channel deep learning models[J].Ann Int Conf IEEE Eng Med Biol Soc, 2020:1294-1298.
[17] Murata S, Ishigaki K, Lee C, et al.Towards a smart dental healthcare: an automated assessment of orthodontic treatment need[J]. Health Info, 2017:35-39.
[18] Ma Q, Kobayashi E, Fan B, et al.Machine-learning-based approach for predicting postoperative skeletal changes for orthognathic surgical planning[J]. Int J Med Robot, 2022,18(3):e2379.
[19] Knoops PGM, Papaioannou A, Borghi A, et al.A machine learning framework for automated diagnosis and computer-assisted planning in plastic and reconstructive surgery[J]. Sci Rep, 2019, 9: 14597.
[20] Xiao D, Lian C, Deng H, et al.Estimating reference bony shape models for orthognathic surgical planning using 3D point-cloud deep learning[J]. IEEE J Biomed Health Inform, 2021, 25(8): 2958-2966.
[21] Li P, Kong D, Tang T, et al.Orthodontic treatment planning based on artificial neural networks[J]. Sci Rep, 2019, 9(1): 2037.
[22] Kim YH, Park JB, Chang MS, et al.Influence of the depth of the convolutional neural networks on an artificial intelligence model for diagnosis of orthognathic surgery[J]. J Pers Med, 2021, 11(5): 356-362.
[23] Ma L, Kim D, Lian C, et al.Deep simulation of facial appearance changes following craniomaxillofacial bony movements in orthognathic surgical planning[J]. Med Image Comput Comput Assist Interv, 2021, 12904: 459-468.
[24] Ter Horst R, Van weert H, Loonen T, et al. Three-dimensional virtual planning in mandibular advancement surgery: soft tissue prediction based on deep learning[J]. J Craniomaxillofac Surg, 2021, 49(9): 775-782.