Challenges and strategies for artificial intelligence-based quantitative measurement in oral implant

doi:10.3877/cma.j.issn.1674-1366.2026.01.001

Abstract

Abstract:

The advancement of digital technologies in oral implantology has facilitated the progress of precise implant treatment, generating numerous quantitative indices relevant to clinical decision-making. In the transformation from digital implant to intelligent implant, accurate quantification of hard and soft tissues serves as the foundation for intelligent and precise implant therapy, and artificial intelligence (AI) has demonstrated potential applications in this field. However, the clinical translation of AI-based quantitative analysis in oral implantology remains constrained by challenges related to data acquisition, task specificity, algorithm design, and clinical validation. Drawing upon current evidence from domestic and international studies and our research findings in this area, this article elucidates the characteristics of quantitative tasks in oral implantology, summarizes the technical pathways for AI-based quantitative analysis, and discusses existing challenges and future directions, with the aim of providing a reference for the clinical development of intelligent quantitative analysis in oral implantology.

Key words: Dental implant, Quantitative analysis, Artificial intelligence, End-to-end, Key-point detection, Object detection, Segmentation

Zetao Chen, Longshiyu Qiu, Zhuohong Gong, Hengyi Liu, Peisheng Zeng, Mengru Shi. Challenges and strategies for artificial intelligence-based quantitative measurement in oral implant[J]. Chinese Journal of Stomatological Research(Electronic Edition), doi: 10.3877/cma.j.issn.1674-1366.2026.01.001.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://zhkqyxyjzz.cma-cmc.com.cn/EN/10.3877/cma.j.issn.1674-1366.2026.01.001

Figures/Tables 4

References 39

[1]	Schwendicke F，Krois J. Precision dentistry-what it is，where it fails （yet），and how to get there [J]. Clin Oral Investig，2022，26（4）：3395-403. DOI：10.1007/s00784-022-04420-1.
[2]	Mun SB，Yoo SR，Kim YJ，et al. AI-driven prediction of dental implant numbers to be placed for patient-specific treatment planning [J]. Int Dent J，2025，75（6）：103896. DOI：10.1016/j.identj.2025.103896.
[3]	Kurt Bayrakdar S，Orhan K，Bayrakdar IS，et al. A deep learning approach for dental implant planning in cone-beam computed tomography images [J]. BMC Med Imaging，2021，21（1）：86. DOI：10.1186/s12880-021-00618-z.
[4]	Esteva A，Robicquet A，Ramsundar B，et al. A guide to deep learning in healthcare [J]. Nat Med，2019，25（1）：24-29. DOI：10.1038/s41591-018-0316-z.
[5]	Lawand G，Gonzaga L，Issa J，et al. Artificial intelligence segmentation errors in implant planning software programs：An overview[J]. Clin Implant Dent Relat Res，2025，27（5）：e70095. DOI：10.1111/cid.70095.
[6]	Alshenaiber R，Cowan C，Barclay C，et al. Analysis of residual ridge morphology in a group of edentulous patients seeking NHS dental implant provision：A retrospective observational lateral cephalometric study [J]. Diagnostics （Basel），2021，11（12）：2348. DOI：10.3390/diagnostics11122348.
[7]	Cawood JI，Howell RA. A classification of the edentulous jaws [J]. Int J Oral Maxillofac Surg，1988，17（4）：232-236. DOI：10.1016/s0901-5027(88)80047-x.
[8]	Palomino-Zorrilla JJ，Córdova-Limaylla NE，Rosas-Díaz JC，et al. Jawbone quality classification in dental implant planning and placement studies. A scoping review[J]. J Int Soc Prev Community Dent，2024，14（2）：89-97. DOI：10.4103/jispcd.JISPCD_4_22.
[9]	Troiano G，Rapani A，Fanelli F，et al. Inter and intra-operator reliability of Lekholm and Zarb classification and proposal of a novel radiomic data-driven clustering for qualitative assessment of edentulous alveolar ridges [J]. Clin Oral Implants Res，2024，35（7）：729-738. DOI：10.1111/clr.14271.
[10]	Goiato MC，dos Santos DM，Santiago JF Jr，et al. Longevity of dental implants in type Ⅳ bone：A systematic review [J]. Int J Oral Maxillofac Surg，2014，43（9）：1108-1116. DOI：10.1016/j.ijom.2014.02.016.
[11]	Carneiro ALE，Reis INR，Bitencourt FV，et al. Accuracy of linear measurements for implant planning based on low-dose cone beam CT protocols：A systematic review and Meta-analysis [J]. Dentomaxillofac Radiol，2024，53（4）：207-221. DOI：10.1093/dmfr/twae007.
[12]	Macrì M，D'Albis V，D'Albis G，et al. The role and applications of artificial intelligence in dental implant planning：A systematic review [J]. Bioengineering （Basel），2024，11（8）：778. DOI：10.3390/bioengineering11080778.
[13]	Gong Z，Li X，Shi M，et al. Measuring the binary thickness of buccal bone of anterior maxilla in low-resolution cone-beam computed tomography via a bilinear convolutional neural network [J]. Quant Imaging Med Surg，2023，13（12）：8053-8066. DOI：10.21037/qims-23-744.
[14]	Lin Y，Shi M，Xiang D，et al. Construction of an end-to-end regression neural network for the determination of a quantitative index sagittal root inclination [J]. J Periodontol，2022，93（12）：1951-1960. DOI：10.1002/jper.21-0492.
[15]	Kim YH，Shin JY，Lee A，et al. Automated cortical thickness measurement of the mandibular condyle head on CBCT images using a deep learning method [J]. Sci Rep，2021，11（1）：14852. DOI：10.1038/s41598-021-94362-7.
[16]	Kim SH，Kim J，Yang S，et al. Automatic and quantitative measurement of alveolar bone level in OCT images using deep learning [J]. Biomed Opt Express，2022，13（10）：5468-5482. DOI：10.1364/boe.468212.
[17]	Liu H，Duan J，Zeng P，et al. Intelligently quantifying the entire irregular dental structure [J]. J Dent Res，2024，103（4）：378-387. DOI：10.1177/00220345241226871.
[18]	Ma J，He Y，Li F，et al. Segment anything in medical images [J]. Nat Commun，2024，15（1）：654. DOI：10.1038/s41467-024-44824-z.
[19]	Ayzenberg V，Sener SB，Novick K，et al. Fast and robust visual object recognition in young children [J]. Sci Adv，2025，11（27）：eads6821. DOI：10.1126/sciadv.ads6821.
[20]	Petersen LB，Olsen KR，Christensen J，et al. Image and surgery-related costs comparing cone beam CT and panoramic imaging before removal of impacted mandibular third molars [J]. Dentomaxillofac Radiol，2014，43（6）：20140001. DOI：10.1259/dmfr.20140001.
[21]	Kim YH，Lee C，Han SS，et al. Quantitative analysis of metal artifact reduction using the auto-edge counting method in cone-beam computed tomography [J]. Sci Rep，2020，10（1）：8872. DOI：10.1038/s41598-020-65644-3.
[22]	Cheplygina V，de Bruijne M，Pluim JPW. Not-so-supervised：A survey of semi-supervised，multi-instance，and transfer learning in medical image analysis [J]. Med Image Anal，2019，54：280-296. DOI：10.1016/j.media.2019.03.009.
[23]	Kim HE，Cosa-Linan A，Santhanam N，et al. Transfer learning for medical image classification：A literature review [J]. BMC Med Imaging，2022，22（1）：69. DOI：10.1186/s12880-022-00793-7.
[24]	Shi M，Gong Z，Zeng P，et al. Multi-quantifying maxillofacial traits via a demographic parity-based AI model [J]. BME Front，2024，5：0054. DOI：10.34133/bmef.0054.
[25]	Park CS，Kang SR，Kim JE，et al. Validation of bone mineral density measurement using quantitative CBCT image based on deep learning [J]. Sci Rep，2023，13（1）：11921. DOI：10.1038/s41598-023-38943-8.
[26]	Bardhan S，Nagar G，Adapala K，et al. Validation of an AI model for automated detection of alveolar bone changes post-orthodontics using cone-beam computed tomography[J]. Cureus，2025，17（10）：e94809. DOI：10.7759/cureus.94809.
[27]	Çoban G，Öztürk T，Hashimli N，et al. Comparison between cephalometric measurements using digital manual and web-based artificial intelligence cephalometric tracing software [J]. Dental Press J Orthod，2022，27（4）：e222112. DOI：10.1590/2177-6709.27.4.e222112.oar.
[28]	Jeon S，Lee KC. Comparison of cephalometric measurements between conventional and automatic cephalometric analysis using convolutional neural network [J]. Prog Orthod，2021，22（1）：14. DOI：10.1186/s40510-021-00358-4.
[29]	Cha JY，Yoon HI，Yeo IS，et al. Peri-implant bone loss measurement using a region-based convolutional neural network on dental periapical radiographs [J]. J Clin Med，2021，10（5）：1009. DOI：10.3390/jcm10051009.
[30]	Hao J，Nalley A，Yeung AWK，et al. Characteristics，licensing，and ethical considerations of openly accessible oral-maxillofacial imaging datasets：A systematic review [J]. NPJ Digit Med，2025，8（1）：412. DOI：10.1038/s41746-025-01818-5.
[31]	Vilcapoma P，Parra Meléndez D，Fernández A，et al. Comparison of Faster R-CNN，YOLO，and SSD for third molar angle detection in dental panoramic X-rays [J]. Sensors （Basel），2024，24（18）：6053. DOI：10.3390/s24186053.
[32]	Widiasri M，Arifin AZ，Suciati N，et al. Dental-YOLO：Alveolar bone and mandibular canal detection on cone beam computed tomography images for dental implant planning[J]. IEEE Access，2022，10：101483-101494. DOI：10.1109/ACCESS.2022.3208350.
[33]	Chen CC，Wu YF，Aung LM，et al. Automatic recognition of teeth and periodontal bone loss measurement in digital radiographs using deep-learning artificial intelligence [J]. J Dent Sci，2023，18（3）：1301-1309. DOI：10.1016/j.jds.2023.03.020.
[34]	Nguyen KT，Le BM，Li M，et al. Localization of cementoenamel junction in intraoral ultrasonographs with machine learning [J]. J Dent，2021，112：103752. DOI：10.1016/j.jdent.2021.103752.
[35]	Liu T，Ye Y，Liu C，et al. Key-point based automated diagnosis for alveolar dehiscence in mandibular incisors using convolutional neural network [J]. Biomedical Signal Processing and Control，2023，85：105082. DOI：10.1016/j.bspc.2023.105082.
[36]	Kazerouni A，Aghdam EK，Heidari M，et al. Diffusion models in medical imaging：A comprehensive survey [J]. Med Image Anal，2023，88：102846. DOI：10.1016/j.media.2023.102846.
[37]	Te Lin Y，Li C，Korostoff J，et al. Three-dimensional digital quantitative analysis of periodontal and peri-implant phenotype：A narrative review [J]. Periodontol 2000，2025. DOI：10.1111/prd.12639.
[38]	Yang L，Zhu Z，Li Y，et al. Clinical-oriented 3D visualization and quantitative analysis of gingival thickness using convolutional neural networks and CBCT[J]. Front Dent Med，2025，6：1635155. DOI：10.3389/fdmed.2025.1635155.
[39]	Chen YC，Chen L，Lai YL，et al. AI-driven detection and measurement of keratinized gingiva in dental photographs：Validation using reference retainers [J]. J Clin Periodontol，2025，52（7）：1056-1067. DOI：10.1111/jcpe.14164.

特征	多维量化	全局量化	虚拟量化	精准量化
定义	同一区域多个独立一维指标的同时获取	目标区域整体形态特征的量化输出	缺乏直接解剖实体支撑的指标推断	毫米级微小解剖结构的定量分析
示例	种植术前剩余骨宽度与高度多指标测量	骨增量术前骨缺损范围评估	种植体长轴与咬合平面夹角	即刻种植唇侧骨壁厚度测量
特点	支持多指标联合评估	获取目标区域整体指标	估计无实体对应指标	精细测量毫米级结构
挑战	切面选择与标志点误差累积	标注成本与算力需求较高	依赖校准假设且偏倚风险高	对分辨率与伪影高度敏感

特征	多维量化	全局量化	虚拟量化	精准量化
定义	同一区域多个独立一维指标的同时获取	目标区域整体形态特征的量化输出	缺乏直接解剖实体支撑的指标推断	毫米级微小解剖结构的定量分析
示例	种植术前剩余骨宽度与高度多指标测量	骨增量术前骨缺损范围评估	种植体长轴与咬合平面夹角	即刻种植唇侧骨壁厚度测量
特点	支持多指标联合评估	获取目标区域整体指标	估计无实体对应指标	精细测量毫米级结构
挑战	切面选择与标志点误差累积	标注成本与算力需求较高	依赖校准假设且偏倚风险高	对分辨率与伪影高度敏感

优劣势	区域分割	端到端回归	关键点检测	目标检测	混合方法
优势	1.适用于二维与三维图像	1.标注需求低	1.适用于点相关的测量任务	1.一维指标量化精度高	1.融合多网络输出结果
	2.适用于全量化任务	2.流程复杂度较低			2.减少无关信息干扰
	3.适用于不规则结构
劣势	1.标注成本高	1.可解释性不足	1.可获取信息有限	1.不规则结构量化精度较低	1.模型设计复杂
	2.计算资源需求大	2.输出指标单一	2.需额外引入定量算法	2.二维指标定量精度不足	2.标注成本高
		3.定量精度较低

优劣势	区域分割	端到端回归	关键点检测	目标检测	混合方法
优势	1.适用于二维与三维图像	1.标注需求低	1.适用于点相关的测量任务	1.一维指标量化精度高	1.融合多网络输出结果
	2.适用于全量化任务	2.流程复杂度较低			2.减少无关信息干扰
	3.适用于不规则结构
劣势	1.标注成本高	1.可解释性不足	1.可获取信息有限	1.不规则结构量化精度较低	1.模型设计复杂
	2.计算资源需求大	2.输出指标单一	2.需额外引入定量算法	2.二维指标定量精度不足	2.标注成本高
		3.定量精度较低

Please choose a citation manager

Content to export