 |
Publisher: Peytchinski Publishing Ltd.
ISSN: 1312-773X (Online)
Issue: 2026, vol. 32, issue3
Subject Area: Dental Medicine
-
DOI: 10.5272/jimab.2026323.7043
Published online: 21 August 2026
Review article
J of IMAB. 2026 Jul-Sep;32(3):7043-7050
IMPACT OF DATASET SIZE ON GANS USED FOR THE GENERATION OF PROSTHETIC CONSTRUCTIONS. A NARRATIVE REVIEW
Aleksandar Naydenov1
, Todor Uzunov1, Elka Radeva2
, Georgi Kostadinov3, Rumen Radev1,
1) Department of Prosthetic Dental Medicine, Faculty of Dental Medicine, Medical University – Sofia, Bulgaria.
2) Department of Conservative Dentistry, Faculty of Dental Medicine, Medical University – Sofia, Bulgaria.
3) Department of Information Technologies, New Bulgarian University – Sofia, Bulgaria.
ABSTRACT:
Purpose: To examine the reporting and influence of dataset quantity and quality in generative adversarial network (GAN)-based dental prosthetic generation and to summarize the evidence available through 16 July 2026.
Material/Methods: A structured literature search was conducted in PubMed, Scopus, Web of Science, IEEE Xplore, SpringerLink, arXiv, and Google Scholar. Fifteen original GAN or explicitly adversarial studies of prosthetic generation or validation were included in the focused qualitative synthesis. Nine non-GAN generative or automated artificial-intelligence studies published in 2025-2026 were analyzed separately as contextual evidence.
Results: Dataset definitions ranged from small three-dimensional collections to more than 1500 depth-map cases. ToothGAN used 814 natural-tooth and technician-designed cases and showed that the dataset composition affected anatomical features, groove depth, and occlusal contact characteristics. A 3D GAN implant-crown study demonstrated that overlap metrics should be interpreted together with clinically relevant emergence-profile parameters. Contextual transformer, point-cloud, diffusion, and commercial-system studies reported increasingly explicit data splits and clinical endpoints, although several proprietary systems did not disclose their training data.
Conclusions: No universal minimum dataset size can be established. Dataset composition, anatomical diversity, ground-truth definition, resolution, augmentation, independent testing, and clinical validation are at least as important as sample count.
Keywords: Generative Adversarial Networks, Dental Prosthesis Design, Dental Crowns, Dataset, Artificial Intelligence, Digital Dentistry,
- Download FULL TEXT /PDF 801 KB/
Please cite this article as: Naydenov A, Uzunov T, Radeva E, Kostadinov G, Radev R. Impact of Dataset Size on GANs used for the generation of prosthetic constructions. A narrative review. J of IMAB. 2026 Jul-Sep;32(3):7043-7050. [Crossref - 10.5272/jimab.2026323.7043]
Correspondence to: Prof. Elka Radeva, DMD, PhD, Department of Conservative Dentistry, Faculty of Dental Medicine, MU-Sofia; 1, G. Sofijski Blvd., Sofia 1431, Bulgaria. E-mail: eliradeva@abv.bg
REFERENCES:
1. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. Adv Neural Inf Process Syst. 2014;27:2672-2680.
2. Aggarwal A, Mittal M, Battineni G. Generative adversarial network: an overview of theory and applications. Int J Inf Manag Data Insights. 2021 Apr;1(1):100004. [Crossref]
3. Broll A, Goldhacker M, Hahnel S, Rosentritt M. Generative deep learning approaches for the design of dental restorations: a narrative review. J Dent. 2024 Jun;145:104988. [Crossref]
4. Kong HJ, Kim YL. Application of artificial intelligence in dental crown prosthesis: a scoping review. BMC Oral Health. 2024 Aug 13;24(1):937. [PubMed]
5. Karras T, Aittala M, Hellsten J, Laine S, Lehtinen J, Aila T. Training generative adversarial networks with limited data. Adv Neural Inf Process Syst. 2020;33:12104-12114.
6. Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning. J Big Data. 2019;6:60. [Crossref]
7. Schwendicke F, Samek W, Krois J. Artificial intelligence in dentistry: chances and challenges. J Dent Res. 2020 Jul;99(7):769-774. [PubMed]
8. Borji A. Pros and cons of GAN evaluation measures. Comput Vis Image Underst. 2019 Feb;179:41-65. [Crossref]
9. Hodson TO. Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not. GMD. 2022;15(14):5481-5487. [Crossref]
10. Taha AA, Hanbury A. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging. 2015 Aug;15:29. [PubMed]
11. Hwang JJ, Azernikov S, Efros AA, Yu SX. Learning beyond human expertise with generative models for dental restorations. arXiv. 2018:1804.00064. [Crossref]
12. Yuan F, Dai N, Tian S, Zhang B, Sun Y, Yu Q, et al. Personalized design technique for the dental occlusal surface based on conditional generative adversarial networks. Int J Numer Methods Biomed Eng. 2020 May;36(5):e3321. [PubMed]
13. Lee H, Thoummala N, Park HJ, Ham SH, Yu JW, Hwang JH, et al. [AI-based dental prostheses fabrication using generative adversarial networks.] [in Korean] Quant Bio-Sci. 2021;40(1):39-44. [Crossref]
14. Tian S, Wang M, Yuan F, Dai N, Sun Y, Xie W, et al. Efficient computer-aided design of dental inlay restoration: a deep adversarial framework. IEEE Trans Med Imaging. 2021 Sep;40(9):2415-2427. [Crossref]
15. Tian S, Wang M, Dai N, Ma H, Li L, Fiorenza L, et al. DCPR-GAN: dental crown prosthesis restoration using two-stage generative adversarial networks. IEEE J Biomed Health Inform. 2022 Jan;26(1):151-160. [Crossref]
16. Tian S, Huang R, Li Z, Fiorenza L, Dai N, Sun Y, et al. A dual discriminator adversarial learning approach for dental occlusal surface reconstruction. J Healthc Eng. 2022;2022:1933617. [Crossref]
17. Ding H, Cui Z, Maghami E, Chen Y, Matinlinna JP, Pow EHN, et al. Morphology and mechanical performance of dental crown designed by 3D-DCGAN. Dent Mater. 2023 Mar;39(3):320-332. [PubMed]
18. Gu Z, Wu Z, Dai N. Image generation technology for functional occlusal pits and fissures based on a conditional generative adversarial network. PLoS One. 2023 Sep 19;18(9):e0291728. [PubMed]
19. Chau RCW, Hsung RTC, McGrath C, Pow EHN, Lam WYH. Accuracy of artificial intelligence-designed single-molar dental prostheses: a feasibility study. J Prosthet Dent. 2024 Jun;131(6):1111-1117. [Crossref]
20. Broll A, Rosentritt M, Schlegl T, Goldhacker M. A data-driven approach for the partial reconstruction of individual human molar teeth using generative deep learning. Front Artif Intell. 2024 Apt 16;7:1339193. [PubMed]
21. Chafi I, Cheriet F, Keren J, Zhang Y, Guibault F. 3D generation of dental crown bottoms using context learning. Proc SPIE. 2024;12931:129310I. [Crossref]
22. Roh J, Kim J, Lee J. Two-stage deep learning framework for occlusal crown depth image generation. Comput Biol Med. 2024 Dec;183:109220. [Crossref]
23. Kostadinov G, Naydenov A. 3D cycle-consistent adversarial network for designing dental implant crown. In: Zlateva T, Tuparov G, editors. Computer Science and Education in Computer Science. Springer, Cham. 2025 14 March;609:183-200. [Crossref]
24. Zhao W, Liu Y, Lam WYH, Cheung CF, Ding H, Tsoi JKH. Tooth generative adversarial network: anatomical optimization using Wasserstein generative adversarial network for tooth generation hyphenated dental 3-dimensional precision printing. Eng Appl Artif Intell. 2026 Apr 15;170:114215. [Crossref]
25. Naydenov AV, Uzunov TT, Kostadinov G. Role of prosthetic parameters for validating an AI designed crown. Folia Med (Plovdiv). 2026;68(3):e177266. [Crossref]
26. Broll A, Goldhacker M, Hahnel S, Rosentritt M. Morphological effects of input data quantity in AI-powered dental crown design. J Dent. 2025 Aug;159:105767. [PubMed]
27. Ren S, Wu T, Zhou D, Jiang X, Di P. A deep learning system on monolithic implant-supported crown design: evaluating AI-generated models against conventional software outputs. J Prosthodont. 2026 Jun;35(5):712-720. [PubMed]
28. Du X, Sun W, Yao C, Gao Y, Hu J, Song K. AI-driven automation of occlusal surface design in digital prosthodontics: a clinically validated workflow. BMC Oral Health. 2026 Feb 16;26:513. [PubMed]
29. Shu Z, Tian M, Wei H. AI-driven crown generation: a comparative analysis of point cloud completion models for mandibular first molar restoration. J Dent. 2026 May;168:106581. [Crossref]
30. Chai XH, Wei ST, Chen RJ, Jiang TMQ, Wu S, Wang PS, et al. [Intelligent generation of occlusal surface morphology of dental crown using an octree-based diffusion model.] [in Chinese] Zhonghua Kou Qiang Yi Xue Za Zhi. 2026;61(6):839-846. [Crossref]
31. Ying S, Huang F, Yin J, Liu W, He F. Tooth3dNet: a preliminary exploration for automatic 3D morphology design of dental crowns with a deep generative network. J Dent. 2026 Jul;170:106696. [PubMed]
32. Nagata K, Inoue E, Nakashizu T, Seimiya K, Atsumi M, Kimoto K, et al. Verification of the accuracy and design time of crowns designed with artificial intelligence. J Adv Prosthodont. 2025 Feb;17(1):1-10. [PubMed]
33. Win TT, Mai HN, Kim SY, Cho SH, Kim JE, Srimaneepong V, et al. Fit accuracy of complete crowns fabricated by generative artificial intelligence design: a comparative clinical study. J Adv Prosthodont. 2025 Aug;17(4):224-234. [PubMed]
34. Hlaing NHMM, Cakmak G, Karasan D, Kim SJ, Sailer I, Lee JH. Artificial intelligence-driven automated design of anterior and posterior crowns under diverse occlusal scenarios. J Esthet Restor Dent. 2026;38(1):129-142. [Crossref]
Received: 04 October 2025
Published online: 21 August 2026