DentaGAN: GAN-Based Synthetic Individual Dental Data Generation in Radiographic Images

Year 2024, , 1194 - 1204, 31.12.2024

Buse Yaren Kazangirler , Caner Özcan

https://doi.org/10.17798/bitlisfen.1540373

Abstract

Panoramic radiographs are a low radiation exposure type often used as a data source for many deep learning algorithms. On the other hand, the operational structure of a traditional deep learning algorithm requires a large amount of data, which is a major problem for many researchers. It is aimed to overcome this problem through deep GAN models, many versions of which have been developed recently. The main purpose of the study is to generate a two-stage GAN model for data with the same image dimensions. The study is carried out in the form of inputting panoramic images containing a whole view, as well as single tooth data whose performance is desired to be measured, to the architecture. The generator model created for each tooth object in all panoramic radiographs generates new tooth objects that the model has yet to encounter in the dataset. Fréchet Inception Distance was used as a performance metric by measuring the distance for the Inception-v3 activation distributions for the real samples in the generated and training set. Thus, the statistical similarity of these two groups obtained from the experimental results was observed in the part of the experimental results. The cropped individual tooth classes were much more successful than the entire panoramic dataset.

Keywords

Generative adversarial networks, Dental image generation, Synthetic data augmentation, Two-stage neural network, Panoramic images

Ethical Statement

The study is complied with research and publication ethics.

References

• J. Park et al., “Deep learning on time series laboratory test results from electronic health records for early detection of pancreatic cancer,” J. Biomed. Inform., vol. 131, p. 104095, Jul. 2022, doi: 10.1016/j.jbi.2022.104095.
• S. Vinayahalingam et al., “Automated chart filing on panoramic radiographs using deep learning,” J. Dent., vol. 115, p. 103864, Dec. 2021, doi: 10.1016/j.jdent.2021.103864.
• M. J. Cardoso, N. Houssami, G. Pozzi, and B. Séroussi, “Artificial intelligence (AI) in breast cancer care - Leveraging multidisciplinary skills to improve care,” Breast Off. J. Eur. Soc. Mastology, vol. 56, pp. 110–113, Dec. 2020, doi: 10.1016/j.breast.2020.11.012.
• B. Y. Tekin, C. Ozcan, A. Pekince, and Y. Yasa, “An enhanced tooth segmentation and numbering according to FDI notation in bitewing radiographs,” Comput. Biol. Med., vol. 146, p. 105547, 2022.
• G. Litjens et al., “A survey on deep learning in medical image analysis,” Med. Image Anal., vol. 42, pp. 60–88, Dec. 2017, doi: 10.1016/j.media.2017.07.005.
• D. Frejlichowski and R. Wanat, “Application of the Laplacian Pyramid Decomposition to the Enhancement of Digital Dental Radiographic Images for the Automatic Person Identification,” in Image Analysis and Recognition, A. Campilho and M. Kamel, Eds., Berlin, Heidelberg: Springer, 2010, pp. 151–160. doi: 10.1007/978-3-642-13775-4_16.
• Y. Lin et al., “DHI-GAN: Improving Dental-Based Human Identification Using Generative Adversarial Networks,” IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 12, pp. 9700–9712, Dec. 2023, doi: 10.1109/TNNLS.2022.3159781.
• S. Tian et al., “DCPR-GAN: Dental Crown Prosthesis Restoration Using Two-Stage Generative Adversarial Networks,” IEEE J. Biomed. Health Inform., vol. 26, no. 1, pp. 151–160, Jan. 2022, doi: 10.1109/JBHI.2021.3119394.
• R. Havale, B. S. Sheetal, R. Patil, R. Hemant Kumar, R. T. Anegundi, and K. R. Inushekar, “Dental notation for primary teeth: a review and suggestion of a novel system,” Eur. J. Paediatr. Dent., vol. 16, no. 2, pp. 163–166, Jun. 2015.
• N. K. Singh and K. Raza, “Medical Image Generation Using Generative Adversarial Networks: A Review,” in Health Informatics: A Computational Perspective in Healthcare, R. Patgiri, A. Biswas, and P. Roy, Eds., Singapore: Springer, 2021, pp. 77–96. doi: 10.1007/978-981-15-9735-0_5.
• “U-Patch GAN: A Medical Image Fusion Method Based on GAN | Journal of Imaging Informatics in Medicine.” Accessed: Nov. 29, 2024. [Online]. Available: https://link.springer.com/article/10.1007/s10278-022-00696-7
• Z. Hu et al., “Artifact correction in low‐dose dental CT imaging using Wasserstein generative adversarial networks,” Med. Phys., vol. 46, no. 4, pp. 1686–1696, Apr. 2019, doi: 10.1002/mp.13415.
• A. Creswell, T. White, V. Dumoulin, K. Arulkumaran, B. Sengupta, and A. A. Bharath, “Generative Adversarial Networks: An Overview,” IEEE Signal Process. Mag., vol. 35, no. 1, pp. 53–65, Jan. 2018, doi: 10.1109/MSP.2017.2765202.
• J. Gui, Z. Sun, Y. Wen, D. Tao, and J. Ye, “A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications,” IEEE Trans. Knowl. Data Eng., vol. 35, no. 4, pp. 3313–3332, Apr. 2023, doi: 10.1109/TKDE.2021.3130191.
• A. Borji, “Pros and cons of GAN evaluation measures: New developments,” Comput. Vis. Image Underst., vol. 215, p. 103329, 2022.
• T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, “Improved techniques for training gans,” Adv. Neural Inf. Process. Syst., vol. 29, 2016, Accessed: Aug. 24, 2024. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2016/hash/8a3363abe792db2d8761d6403605aeb7-Abstract.html
• A. Radford, L. Metz, and S. Chintala, “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” Jan. 07, 2016, arXiv: arXiv:1511.06434. doi: 10.48550/arXiv.1511.06434.
• A. Figueira and B. Vaz, “Survey on synthetic data generation, evaluation methods and GANs,” Mathematics, vol. 10, no. 15, p. 2733, 2022.
• A. Karaoglu, C. Ozcan, A. Pekince, Y. Yasa, B. Tekin, and D. Ozdemir, “Automatic dental segmentation module supported by artificial intelligence for dentistry students education,” Artif Intell Theory Appl, vol. 1, pp. 180–190, 2021.
• U. Ruby and V. Yendapalli, “Binary cross entropy with deep learning technique for image classification,” Int J Adv Trends Comput Sci Eng, vol. 9, no. 10, 2020, Accessed: Aug. 24, 2024. [Online]. Available: https://www.researchgate.net/profile/Vamsidhar-Yendapalli/publication/344854379_Binary_cross_entropy_with_deep_learning_technique_for_Image_classification/links/5f93eed692851c14bce1ac68/Binary-cross-entropy-with-deep-learning-technique-for-Image-classification.pdf
• N. Shibuya, “Understanding generative adversarial networks,” Retrieved Internet, 2017.
• M. Lucic, K. Kurach, M. Michalski, S. Gelly, and O. Bousquet, “Are gans created equal? a large-scale study,” Adv. Neural Inf. Process. Syst., vol. 31, 2018, Accessed: Aug. 24, 2024. [Online]. Available: https://proceedings.neurips.cc/paper/2018/hash/e46de7e1bcaaced9a54f1e9d0d2f800d-Abstract.html
• J. Liu, C. Gu, J. Wang, G. Youn, and J.-U. Kim, “Multi-scale multi-class conditional generative adversarial network for handwritten character generation,” J. Supercomput., vol. 75, no. 4, pp. 1922–1940, Apr. 2019, doi: 10.1007/s11227-017-2218-0.