国际口腔医学杂志

国际口腔医学杂志 ›› 2024, Vol. 51 ›› Issue (5): 630-641.doi: 10.7518/gjkq.2024061

• 综述 • 上一篇    下一篇

人工智能在头影测量自动定点算法上的研究进展

汪云毅1,2(),朱珠2,3,4,张峰1,2()   

  1. 1.浙江大学医学院附属儿童医院口腔科 杭州 310000
    2.国家儿童健康与疾病临床医学研究中心 杭州 310000
    3.浙江大学医学院附属儿童医院数据信息部 杭州 310000
    4.浙江 -芬兰儿童健康人工智能联合实验室 杭州 310000
  • 收稿日期:2023-12-10 修回日期:2024-04-12 出版日期:2024-09-01 发布日期:2024-09-14
  • 通讯作者: 张峰
  • 作者简介:汪云毅，住院医师，硕士，Email：22118765@zju.edu.cn
  • 基金资助:
    浙江省科学技术厅“尖兵”“领雁”研发攻关计划(2023C03101)

Progress of research on using artificial intelligence for cephalometric automatic-landmarking algorithms

Yunyi Wang1,2(),Zhu Zhu2,3,4,Feng Zhang1,2()   

  1. 1.Dept. of Stomatology, Children’s Hospital, Zhejiang University School of Medicine, Hangzhou 310000, China
    2.National Clinical Research Center for Child Health, Hangzhou 310000, China
    3.Dept. of Data and Information, Children’s Hospital, Zhejiang University School of Medicine, Hangzhou 310000, China
    4.Sino-Finland Joint AI Laboratory for Child Health of Zhejiang Province, Hangzhou 310000, China
  • Received:2023-12-10 Revised:2024-04-12 Online:2024-09-01 Published:2024-09-14
  • Contact: Feng Zhang
  • Supported by:
    Grants from “Pioneer” and “Leading Goose” Research and Development Program in Zhejiang ProvinceFoundation(2023C03101)

RichHTML

36

PDF (PC)

370

摘要：

头影测量是正畸诊断和治疗过程中不可或缺的分析手段。高精度定位头影测量的标志点对于确保正畸临床诊断的准确性和治疗目标的正确性至关重要。随着计算机辅助技术特别是人工智能的发展，头影测量标志点从手动标注逐渐进展到自动定点，并已应用于临床实践。从基于知识方法到基于模型和模板匹配方法，再到现在的机器学习及深度学习方法，人工智能在传统头颅侧位片上标志点检测的准确率已有显著提高，但在图像数据更精确的三维图像上，自动定点尚处于起步阶段。本文旨在综述人工智能在头影测量自动定点算法方面的研究进展，并对其未来研究方向进行展望。

关键词: 人工智能, 头影测量标志点, 自动定点, 机器学习, 深度学习, 自动化分析, 计算机视觉

Abstract:

Cephalometry is an indispensable tool in the diagnosis and treatment process of orthodontics. The high-precision localization of cephalometric landmarks is crucial to ensuring the accuracy of clinical orthodontic diagnosis and the correctness of treatment objectives. In clinical practice, doctors usually need to manually annotate these landmarks, which is time consuming and subjective. Over the past few decades, the concept of automated cephalometric landmark identification has emerged with the development of computer-assisted technology, particularly artificial intelligence. This auto-mated identification is gradually being applied in clinical practice. From the knowledge-based method to the model-based and template-based matching method, and subsequently to the current machine-learning and deep-learning methods, the accuracy of artificial intelligence in landmark detection on traditional lateral cephalogram has significantly improved. However, in three-dimensional images with more accurate image data, automatic landmarking remains in its infancy. This article aims to review the progress of research on artificial intelligence in automatic-landmarking algorithm for cephalo-metry, as well as to look forward to its future research directions.

Key words: artificial intelligence, cephalometric landmarks, automatic landmarking, machine learning, deep learning, automated analysis, computer vision

中图分类号: 

  • R783.5

表 1

二维头影测量自动定点方法摘要"

定点方法参考文献样本量标志点数量自动定点误差
基于知识的方法[15]测试样本：2张X线片36定位23个标志点，具体不详
[16]测试样本：5张X线片279个标志点平均误差2.06 mm，误差<1 mm者占18%，<2 mm占58%
[17]训练样本：28张X线片4鼻腔区域3个标志点平均误差约4.5 mm
测试样本：58张X线片颅骨中部区域1个标志点平均误差约3 mm
基于模型的方法[18]

训练样本：63张X线片

测试样本：63张X线片

16误差<1 mm者占13%，<2 mm占35%，<5 mm占74%
[19]训练样本：60张X线片17平均误差1.68 mm
测试样本：60张X线片
基于模板匹配的方法[21]

训练样本：40张X线片

测试样本：40张X线片

202 mm内识别率平均为85%
[22]

训练样本：20张X线片

测试样本：20张X线片

17平均误差1.1 mm，2 mm内检出率平均为90.3%
基于ML的方法[23]

训练样本：150张X线片

测试样本：150张X线片

19MRE为（1.67±1.65） mm，2 mm SDR为74.95%
[24]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

192 mm SDR为80.21%
基于DL的方法
区域提议分类[25]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：2 mm SDR为75.37%

Test 2：2 mm SDR为 67.68%

[26]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：2 mm SDR为82.5%

Test 2：2 mm SDR为 72.4%

[27]

训练样本：150张X线片

测试样本：250张X线片

192 mm SDR约38%，4 mm SDR约80%
坐标回归[28]

训练样本：150张X线片

测试样本：150张X线片

19效果一般
[29]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：MRE为（1.01±0.85） mm，2 mm SDR为88.32%

Test 2：MRE为（1.33±0.74） mm，2 mm SDR为77.05%

[30]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：MRE为1.04 mm，2 mm SDR为88.49%，

Test 2：MRE为1.43 mm，2 mm SDR为76.57%

[31]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：MRE为（1.34±0.92） mm，2 mm SDR为81.37%

Test 2：MRE为（1.64±0.91） mm，2 mm SDR为70.58%

热图回归[32]

训练样本：150张X线片

测试样本：250张X线片

192 mm SDR为73.33%
[33]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：MRE为（1.12±0.88） mm，2 mm SDR为86.91%

Test 2：MRE为（1.42±0.84） mm，2 mm SDR为86.06%

[35]

训练样本：3 150张X线片

测试样本：100张X线片

20MRE为（1.36±0.98） mm
[36]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：MRE为1.12 mm，2 mm SDR为86.91%

Test 2：MRE为1.41 mm，2 mm SDR为77.16%

[37]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：MRE为（1.17±1.19） mm，2 mm SDR为86.67%

Test 2：MRE为（1.48±0.77） mm，2 mm SDR为75.05%

[38]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：2 mm SDR为86.2%

Test 2：2 mm SDR为75.89%

[39]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：MRE为1.15 mm，2 mm SDR为87.61%

Test 2：MRE为1.43 mm，2 mm SDR为76.32%

[40]

训练样本：150张X线片

测试样本：250张X线片

19MRE为（1.54±2.37） mm，2 mm SDR为77.79%
[41]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：MRE为1.09 mm，2 mm SDR为88.98%

Test 2：MRE为1.33 mm，2 mm SDR为78.68%

[43]

训练样本：9 870张X线片

测试样本：9 870张X线片

30MRE为（0.94±0.74） mm，2 mm SDR为91.73%
其他[44]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test 1：MRE为1.06 mm，2 mm SDR为87.93%

Test 2：MRE为1.37 mm，2 mm SDR为76.11%

表 2

三维头影测量自动定点方法摘要"

定点方法参考文献样本量标志点数量自动定点误差
基于知识的方法[45]测试样本：30例CBCT20总平均误差为（2.01±1.23） mm，2 mm SDR为64.67%
[46]测试样本：30例CBCT20总体平均误差为（1.88±1.10） mm，2 mm SDR为64.16%

基于模型的方法

基于ML的方法

[47]

训练样本：8例CBCT

测试样本：20例CBCT

14平均误差为3.40 mm，3 mm SDR为63.57%
[48]

训练样本：24 例 CBCT

测试样本：24 例 CBCT

18平均误差为（3.64±1.43） mm
[49]

训练样本：24 例 CBCT

测试样本：24 例 CBCT

18平均误差为（2.51±1.61） mm
[50]

训练样本：41例CBCT，30例多层螺旋CT

测试样本：41例CBCT

15平均误差为1.44 mm
[51]

训练样本：20例 CT

测试样本：7例 CT

7x 轴：0.49 mm，y 轴：1.02 mm，z 轴 ： 1.40 mm，平 均 误 差 1.80 mm
基于DL的方法
区域提议分类[53]

训练样本：39例CBCT

测试样本：10例CBCT

105平均误差为（1.75±0.91） mm
[54]

训练样本：170 例 CBCT

测试样本：30例 CBCT

13精确度与专家无异
[55]

训练样本：39例CBCT

测试样本：10例CBCT

105平均误差为（1.38±0.95） mm
热图回归[56]

训练与测试样本：77例CBCT，5折交叉验证

额外训练样本：30例CT

15平均误差为（1.10±0.71） mm
[57]

训练样本：60例CBCT

测试样本：80例CBCT

18平均误差为（0.89±0.64） mm
[58]

训练样本：160例CT

测试样本：38例CT

33平均误差为（1.0±1.3） mm，2 mm SDR为90.4%
其他[59]

训练样本：150张X线片

测试样本1：150张X线片

测试样本2：100张X线片

19

Test1：2 mm SDR为86.7%

Test2：2 mm SDR为73.7%

[60]

训练样本：930例CBCT

测试样本：115例CBCT

35平均误差为2.73 mm
[61]测试样本：24组成对数据（CT图像和标志点坐标）和229个匿名标志点数据90平均误差为2.88 mm
[62]

1）内部数据集：89例CBCT

2）公开数据集PDDCA：48例CT

17

内部数据集：MRE为（1.64±1.13） mm，2 mm SDR为74.28%

公开数据集：MRE为（2.37±1.60） mm，2 mm SDR为56.36%

1 Broadbent B. A new X-ray technique and its application to orthodontia[J]. Angle Orthod, 2009, 1: 45-66.
2 Yao J, Zeng W, He T, et al. Automatic localization of cephalometric landmarks based on convolutional neural network[J]. Am J Orthod Dentofacial Orthop, 2022, 161(3): e250-e259.
3 Mahto RK, Kafle D, Giri A, et al. Evaluation of fully automated cephalometric measurements obtained from web-based artificial intelligence driven platform[J]. BMC Oral Health, 2022, 22(1): 132.
4 Duran GS, Gökmen Ş, Topsakal KG, et al. Evaluation of the accuracy of fully automatic cephalome-tric analysis software with artificial intelligence algorithm[J]. Orthod Craniofac Res, 2023, 26(3): 481-490.
5 Panesar S, Zhao A, Hollensbe E, et al. Precision and accuracy assessment of cephalometric analyses performed by deep learning artificial intelligence with and without human augmentation[J]. Appl Sci, 2023, 13(12): 6921.
6 Indermun S, Shaik S, Nyirenda C, et al. Human exa-mination and artificial intelligence in cephalometric landmark detection-is AI ready to take over[J]. Dentomaxillofac Radiol, 2023, 52(6): 20220362.
7 Rajaraman V. JohnMcCarthy-father of artificial intelligence[J]. Resonance, 2014, 19(3): 198-207.
8 Kiełczykowski M, Kamiński K, Perkowski K, et al. Application of artificial intelligence (AI) in a cephalometric analysis: a narrative review[J]. Diagnostics, 2023, 13(16): 2640.
9 Wang HC, Fu TF, Du YQ, et al. Scientific discovery in the age of artificial intelligence[J]. Nature, 2023, 620(7972): 47-60.
10 Hosny A, Parmar C, Quackenbush J, et al. Artificial intelligence in radiology[J]. Nat Rev Cancer, 2018, 18(8): 500-510.
11 Yasaka K, Akai H, Kunimatsu A, et al. Deep lear-ning with convolutional neural network in radiology[J]. Jpn J Radiol, 2018, 36(4): 257-272.
12 Schwendicke F, Chaurasia A, Arsiwala L, et al. Deep learning for cephalometric landmark detection: systematic review and meta-analysis[J]. Clin Oral Investig, 2021, 25(7): 4299-4309.
13 Schwendicke F, Golla T, Dreher M, et al. Convolutional neural networks for dental image diagnostics: a scoping review[J]. J Dent, 2019, 91: 103226.
14 Wang CW, Huang CT, Lee JH, et al. A benchmark for comparison of dental radiography analysis algorithms[J]. Med Image Anal, 2016, 31: 63-76.
15 Lévy-Mandel AD, Venetsanopoulos AN, Tsotsos JK. Knowledge-based landmarking of cephalograms[J]. Comput Biomed Res, 1986, 19(3): 282-309.
16 Parthasarathy S, Nugent ST, Gregson PG, et al. Automatic landmarking of cephalograms[J]. Comput Biomed Res, 1989, 22(3): 248-269.
17 Desvignes M, Romaniuk B, Clouard R, et al. First steps toward automatic location of landmarks on X-ray images[C/OL]//Proceedings 15th International Conference on Pattern Recognition. ICPR-2000. Barcelona, Spain: IEEE, 2000: 275-278. .
18 Hutton TJ, Cunningham S, Hammond P. An evaluation of active shape models for the automatic identification of cephalometric landmarks[J]. Eur J Orthod, 2000, 22(5): 499-508.
19 Vucinić P, Trpovski Z, Sćepan I. Automatic landmarking of cephalograms using active appearance models[J]. Eur J Orthod, 2010, 32(3): 233-241.
20 Kaur A, Singh C. Automatic cephalometric landmark detection using Zernike moments and template matching[J]. Signal Image Video Process, 2015, 9(1): 117-132.
21 Cardillo J, Sid-Ahmed MA. An image processing system for locating craniofacial landmarks[J]. IEEE Trans Med Imaging, 1994, 13(2): 275-289.
22 Grau V, Alcañiz M, Juan MC, et al. Automatic loca-lization of cephalometric landmarks[J]. J Biomed Inform, 2001, 34(3): 146-156.
23 Lindner C, Wang CW, Huang CT, et al. Fully automatic system for accurate localisation and analysis of cephalometric landmarks in lateral cephalograms[J]. Sci Rep, 2016, 6: 33581.
24 Urschler M, Ebner T, Štern D. Integrating geometric configuration and appearance information into a unified framework for anatomical landmark localization[J]. Med Image Anal, 2018, 43: 23-36.
25 Arık SÖ, Ibragimov B, Xing L. Fully automated quantitative cephalometry using convolutional neural networks[J]. J Med Imaging, 2017, 4(1): 014501.
26 Qian JH, Cheng M, Tao YB, et al. CephaNet: an improved faster R-CNN for cephalometric landmark detection[C/OL]//2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). Venice, Italy: IEEE, 2019: 868-871. .
27 Dai XB, Zhao H, Liu TL, et al. Locating anatomical landmarks on 2D lateral cephalograms through adversarial encoder-decoder networks[J]. IEEE Access, 2019, 7: 132738-132747.
28 Lee H, Park M, Kim J. Cephalometric landmark detection in dental X-ray images using convolutional neural networks[C/OL]//Medical imaging 2017: computer-aided diagnosis. Orlando, United States: SPIE, 2017: 494-499. .
29 Gilmour L, Ray N. Locating cephalometric X-ray landmarks with foveated pyramid attention[EB/OL]. arXiv: 2008.04428. .
30 Li WJ, Lu YH, Zheng K, et al. Structured landmark detection via topology-adapting deep graph learning[C]//European Conference on Computer Vision. Cham: Springer, 2020: 266-283.
31 Zeng MM, Yan ZL, Liu S, et al. Cascaded convolutional networks for automatic cephalometric landmark detection[J]. Med Image Anal, 2021, 68: 101904.
32 Payer C, Štern D, Bischof H, et al. Integrating spatial configuration into heatmap regression based CNNs for landmark localization[J]. Med Image Anal, 2019, 54: 207-219.
33 Zhong Z, Li J, Zhang Z, et al. An attention-guided deep regression model for landmark detection in cephalograms[C/OL]//Shen D, Liu T, Peters TM, et al. Medical image computing and computer assisted intervention-MICCAI 2019. Cham: Springer International Publishing, 2019: 540-548. .
34 Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation[C/OL]//Navab N, Hornegger J, Wells WM, et al. Medical image computing and computer-assisted intervention-MICCAI 2015. Cham: Springer International Publishing, 2015: 234-241. .
35 Kim J, Kim I, Kim YJ, et al. Accuracy of automated identification of lateral cephalometric landmarks using cascade convolutional neural networks on la-teral cephalograms from nationwide multi-centres[J]. Orthod Craniofac Res, 2021, 24(): 59-67.
36 Kwon HJ, Koo HI, Park J, et al. Multistage probabilistic approach for the localization of cephalometric landmarks[J]. IEEE Access, 2021, 9: 21306-21314.
37 Chen R, Ma Y, Chen N, et al. Cephalometric landmark detection by attentive feature pyramid fusion and regression-voting[C/OL]//Shen D, Liu T, Peters TM, et al. Medical image computing and computer assisted intervention-MICCAI 2019. Cham: Sprin-ger International Publishing, 2019: 873-881. .
38 Oh K, Oh IS, Le VNT, et al. Deep anatomical context feature learning for cephalometric landmark detection[J]. IEEE J Biomed Health Inform, 2021, 25(3): 806-817.
39 Qian JH, Luo WZ, Cheng M, et al. CephaNN: a multi-head attention network for cephalometric landmark detection[J]. IEEE Access, 2020, 8: 112633-112641.
40 Zhu H, YAO Q, XIAO L, et al. You only learn once: universal anatomical landmark detection[C/OL]//de Bruijne M, Cattin PC, Cotin S, et al. Medical image computing and computer assisted intervention-MICCAI 2021. Cham: Springer International Publishing, 2021: 85-95.
41 Wang XL, Rigall E, Chen QM, et al. Efficient and stable cephalometric landmark localization using two-stage heatmaps’ regression[J]. IEEE Trans Instrum Meas, 2022, 71: 2518816.
42 Sun K, Xiao B, Liu D, et al. Deep high-resolution representation learning for human pose estimation[C/OL]//2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR). Long Beach, USA: IEEE, 2019: 5686-5696.
43 Jiang FL, Guo YT, Yang C, et al. Artificial intelligence system for automated landmark localization and analysis of cephalometry[J]. Dentomaxillofac Radiol, 2023, 52(1): 20220081.
44 Lu G, Zhang YX, Kong YY, et al. Landmark locali-zation for cephalometric analysis using multiscale image patch-based graph convolutional networks[J]. IEEE J Biomed Health Inform, 2022, 26(7): 3015-3024.
45 Gupta A, Kharbanda OP, Sardana V, et al. A know-ledge-based algorithm for automatic detection of cephalometric landmarks on CBCT images[J]. Int J Comput Assist Radiol Surg, 2015, 10(11): 1737-1752.
46 Neelapu BC, Kharbanda OP, Sardana V, et al. Automatic localization of three-dimensional cephalome-tric landmarks on CBCT images by extracting symmetry features of the skull[J]. Dentomaxillofac Radiol, 2018, 47(2): 20170054.
47 Shahidi S, Bahrampour E, Soltanimehr E, et al. The accuracy of a designed software for automated locali-zation of craniofacial landmarks on CBCT images[J]. BMC Med Imaging, 2014, 14: 32.
48 Montúfar J, Romero M, Scougall-Vilchis RJ. Automatic 3-dimensional cephalometric landmarking based on active shape models in related projections[J]. Am J Orthod Dentofacial Orthop, 2018, 153(3): 449-458.
49 Montúfar J, Romero M, Scougall-Vilchis RJ. Hybrid approach for automatic cephalometric landmark annotation on cone-beam computed tomography volumes[J]. Am J Orthod Dentofacial Orthop, 2018, 154(1): 140-150.
50 Zhang J, Liu MX, Shen DG. Detecting anatomical landmarks from limited medical imaging data using two-stage task-oriented deep neural networks[J]. IEEE Trans Image Process, 2017, 26(10): 4753-4764.
51 Lee SM, Kim HP, Jeon K, et al. Automatic 3D ce-phalometric annotation system using shadowed 2D image-based machine learning[J]. Phys Med Biol, 2019, 64(5): 055002.
52 He K, Gkioxari G, Dollár P, et al. Mask R-CNN[C/OL]//2017 IEEE international conference on computer vision (ICCV). Venice, Italy: IEEE, 2017: 2980-2988. .
53 Lang Y, Wang L, Yap PT, et al. Automatic detection of craniomaxillofacial anatomical landmarks on CBCT images using 3D mask R-CNN[C/OL]//Zhang D, Zhou L, Jie B, et al. International workshop on graph learning in medical imaging. Cham: Springer International Publishing, 2019: 130-137. .
54 Ahn J, Nguyen TP, Kim YJ, et al. Automated analysis of three-dimensional CBCT images taken in na-tural head position that combines facial profile processing and multiple deep-learning models[J]. Comput Methods Programs Biomed, 2022, 226: 107123.
55 Lang YK, Lian CF, Xiao DQ, et al. Localization of craniomaxillofacial landmarks on CBCT images using 3D mask R-CNN and local dependency learning[J]. IEEE Trans Med Imaging, 2022, 41(10): 2856-2866.
56 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.
57 Chen XY, Lian CF, Deng HH, et al. Fast and accurate craniomaxillofacial landmark detection via 3D faster R-CNN[J]. IEEE Trans Med Imaging, 2021, 40(12): 3867-3878.
58 Dot G, Schouman T, Chang S, et al. Automatic 3-dimensional cephalometric landmarking via deep learning[J]. J Dent Res, 2022, 101(11): 1380-1387.
59 Huang YX, Fan FX, Syben C, et al. Cephalogram synthesis and landmark detection in dental cone-beam CT systems[J]. Med Image Anal, 2021, 70: 102028.
60 Blum FMS, Möhlhenrich SC, Raith S, et al. Evaluation of an artificial intelligence-based algorithm for automated localization of craniofacial landmarks[J]. Clin Oral Investig, 2023, 27(5): 2255-2265.
61 Yun HS, Hyun CM, Baek SH, et al. A semi-supervised learning approach for automated 3D cephalometric landmark identification using computed tomography[J]. PLoS One, 2022, 17(9): e0275114.
62 Chen RN, Ma YX, Chen NL, et al. Structure-aware long short-term memory network for 3D cephalometric landmark detection[J]. IEEE Trans Med Ima-ging, 2022, 41(7): 1791-1801.
63 Torres HR, Morais P, Fritze A, et al. 3D facial landmark localization for cephalometric analysis[C/OL]//2022 44th annual international conference of the IEEE engineering in medicine & biology society (EMBC). Glasgow, United Kingdom: IEEE, 2022: 1016-1019..
64 van der Velden BHM, Kuijf HJ, Gilhuijs KGA, et al. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis[J]. Med Ima-ge Anal, 2022, 79: 102470.
65 李媛, 秦金炜, 侯伟, 等. CBCT三维头影测量常用指标的初步探索[J]. 口腔医学, 2021, 41(8): 720-723.
Li Y, Qin JW, Hou W, et al. A preliminary study on the common indexes of the CBCT 3D cephalome-tric analysis[J]. Stomatology, 2021, 41(8): 720-723.
66 Dosovitskiy A, Beyer L, Kolesnikov A, et al. An ima-ge is worth 16x16 words: transformers for image recognition at scale[EB/OL]//e-printsarXiv. arXiv:2010.11929..
67 Tjoa E, Guan CT. A survey on explainable artificial intelligence (XAI): toward medical XAI[J]. IEEE Trans Neural Netw Learn Syst, 2021, 32(11): 4793-4813.
[1] 陈新月,潘晓予,杨燕,贾媛媛,陈亮. 卷积神经网络在牙体牙髓病学中的应用进展[J]. 国际口腔医学杂志, 2024, 51(4): 483-488.
[2] 朱可石,廖安琪,余优成. 机器学习在口腔种植学中的应用研究进展[J]. 国际口腔医学杂志, 2023, 50(4): 491-498.
[3] 林慧平,徐婷,林军. 人工智能在口腔癌和口腔潜在恶性疾病诊断中的研究进展[J]. 国际口腔医学杂志, 2023, 50(2): 138-145.
[4] 唐粤亭,代佳琪,董雯萱,王虎,郭际香,游梦. 基于机器学习的牙龄评测研究进展[J]. 国际口腔医学杂志, 2023, 50(2): 146-151.
[5] 罗恩. 人工智能正颌外科的探索与临床初步应用[J]. 国际口腔医学杂志, 2022, 49(2): 125-131.
[6] 刘力嘉,毛婧,龙欢,蒲亚龙,王军. 二维与三维头影测量自动定点的研究进展[J]. 国际口腔医学杂志, 2022, 49(1): 100-108.
[7] 田而慷,向倩蓉,赵欣然,彭佳涵,舒睿. 口腔诊疗中人工智能的运用[J]. 国际口腔医学杂志, 2021, 48(4): 475-484.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!