{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T13:11:33Z","timestamp":1760447493656,"version":"build-2065373602"},"reference-count":36,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:00:00Z","timestamp":1760140800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Generative Artificial Intelligence (AI) has the potential to address the limited availability of dental radiographs for the development of Dental AI systems by creating clinically realistic synthetic dental radiographs (SDRs). Evaluation of artificially generated images requires both expert review and objective measures of fidelity. A stepwise approach was used to processing 10,000 dental radiographs. First, a single dentist screened images to determine if specific image selection criterion was met; this identified 225 images. From these, 200 images were randomly selected for training an AI image generation model. Second, 100 images were randomly selected from the previous training dataset and evaluated by four dentists; the expert review identified 57 images that met image selection criteria to refine training for two additional AI models. The three models were used to generate 500 SDRs each and the clinical realism of the SDRs was assessed through expert review. In addition, the SDRs generated by each model were objectively evaluated using quantitative metrics: Fr\u00e9chet Inception Distance (FID) and Kernel Inception Distance (KID). Evaluation of the SDR by a dentist determined that expert-informed curation improved SDR realism, and refinement of model architecture produced further gains. FID and KID analysis confirmed that expert input and technical refinement improve image fidelity. The convergence of subjective and objective assessments strengthens confidence that the refined model architecture can serve as a foundation for SDR image generation, while highlighting the importance of expert-informed data curation and domain-specific evaluation metrics.<\/jats:p>","DOI":"10.3390\/jimaging11100356","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T10:37:14Z","timestamp":1760438234000},"page":"356","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AI Diffusion Models Generate Realistic Synthetic Dental Radiographs Using a Limited Dataset"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7196-3101","authenticated-orcid":false,"given":"Brian","family":"Kirkwood","sequence":"first","affiliation":[{"name":"Organ Support and Automation Technologies, U.S. Army Institute of Surgical Research, 3698 Chambers Pass, Bldg 3611, Ft. Sam Houston, San Antonio, TX 78234, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4205-1442","authenticated-orcid":false,"given":"Byeong Yeob","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences, University of Texas Health San Antonio, 7703 Floyd Curl Drive, San Antonio, TX 78229, USA"}]},{"given":"James","family":"Bynum","sequence":"additional","affiliation":[{"name":"Department of Surgery, University of Texas Health San Antonio, 7703 Floyd Curl Drive, San Antonio, TX 78229, USA"}]},{"given":"Jose","family":"Salinas","sequence":"additional","affiliation":[{"name":"Organ Support and Automation Technologies, U.S. Army Institute of Surgical Research, 3698 Chambers Pass, Bldg 3611, Ft. Sam Houston, San Antonio, TX 78234, USA"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e232471","DOI":"10.1148\/radiol.232471","article-title":"Generating Synthetic Data for Medical Imaging","volume":"312","author":"Koetzier","year":"2024","journal-title":"Radiology"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Burgos, N., and Svoboda, D. (2022). Chapter 14\u2014Data Augmentation for Medical Image Analysis. Biomedical Image Synthesis and Simulation, Academic Press.","DOI":"10.1016\/B978-0-12-824349-7.00034-7"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1111\/1754-9485.13261","article-title":"A Review of Medical Image Data Augmentation Techniques for Deep Learning Applications","volume":"65","author":"Chlap","year":"2021","journal-title":"J. Med. Imaging Radiat. Oncol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"141032","DOI":"10.1109\/ACCESS.2024.3422650","article-title":"Recent Advances in Dental Panoramic X-Ray Synthesis and Its Clinical Applications","volume":"12","author":"Sunilkumar","year":"2024","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Burgos, N., and Svoboda, D. (2022). Chapter 1\u2014Introduction to Medical and Biomedical Image Synthesis. Biomedical Image Synthesis and Simulation, Academic Press.","DOI":"10.1016\/B978-0-12-824349-7.00008-6"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41551-021-00751-8","article-title":"Synthetic Data in Machine Learning for Medicine and Healthcare","volume":"5","author":"Chen","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kokomoto, K., Okawa, R., Nakano, K., and Nozaki, K. (2021). Intraoral Image Generation by Progressive Growing of Generative Adversarial Network and Evaluation of Generated Image Quality by Dentists. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-98043-3"},{"key":"ref_8","unstructured":"He, H., Zhao, S., Xi, Y., and Ho, J.C. (2023). MedDiff: Generating Electronic Health Records Using Accelerated Denoising Diffusion Model. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e220010","DOI":"10.1148\/ryai.220010","article-title":"Mitigating Bias in Radiology Machine Learning: 2. Model Development","volume":"4","author":"Zhang","year":"2022","journal-title":"Radiol. Artif. Intell."},{"key":"ref_10","unstructured":"Alaa, A., Breugel, B.V., Saveliev, E.S., and van der Schaar, M. (2022, January 28). How Faithful Is Your Synthetic Data? Sample-Level Metrics for Evaluating and Auditing Generative Models. Proceedings of the 39th International Conference on Machine Learning, Baltimore, MD, USA."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1038\/s41746-023-00773-3","article-title":"The Impact of Inconsistent Human Annotations on AI Driven Clinical Decision Making","volume":"6","author":"Sylolypavan","year":"2023","journal-title":"NPJ Digit. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"20220279","DOI":"10.1259\/dmfr.20220279","article-title":"Factors Affecting Interpretation of Dental Radiographs","volume":"52","author":"Hegde","year":"2023","journal-title":"Dentomaxillofacial Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1038\/s41405-024-00198-4","article-title":"Generative Artificial Intelligence: Synthetic Datasets in Dentistry","volume":"10","author":"Umer","year":"2024","journal-title":"BDJ Open"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Pedersen, S., Jain, S., Chavez, M., Ladehoff, V., de Freitas, B.N., and Pauwels, R. (2025). Pano-GAN: A Deep Generative Model for Panoramic Dental Radiographs. J. Imaging, 11.","DOI":"10.3390\/jimaging11020041"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1148\/radiol.2020192224","article-title":"Preparing Medical Imaging Data for Machine Learning","volume":"295","author":"Willemink","year":"2020","journal-title":"Radiology"},{"key":"ref_16","unstructured":"Rossum, G.V. (2024). Python Software Foundation Python Programming Language 2024, Python Software Foundation."},{"key":"ref_17","unstructured":"SurveyMonkey Inc. (2025). SurveyMonkey 2025, SurveyMonkey Inc."},{"key":"ref_18","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8\u201314). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Proceedings of the Advances in Neural Information Processing Systems 32 (NeurIPS 2019), Vancouver, BC, Canada."},{"key":"ref_19","unstructured":"(2025, June 03). R Core Team R: A Language and Environment for Statistical Computing 2023. Available online: https:\/\/www.scirp.org\/reference\/referencespapers?referenceid=3582659."},{"key":"ref_20","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (July, January 26). Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chong, M.J., and Forsyth, D. (2020, January 14\u201319). Effectively Unbiased FID and Inception Score and Where to Find Them. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00611"},{"key":"ref_22","unstructured":"Konz, N., Chen, Y., Gu, H., Dong, H., and Mazurowski, M.A. (2024). Rethinking Perceptual Metrics for Medical Image Translation 2024. arXiv."},{"key":"ref_23","unstructured":"Li, X., Ren, Y., Jin, X., Lan, C., Wang, X., Zeng, W., Wang, X., and Chen, Z. (2023). Diffusion Models for Image Restoration and Enhancement\u2014A Comprehensive Survey. Int. J. Comput., 1\u201331."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Khader, F., M\u00fcller-Franzes, G., Tayebi Arasteh, S., Han, T., Haarburger, C., Schulze-Hagen, M., Schad, P., Engelhardt, S., Bae\u00dfler, B., and Foersch, S. (2023). Denoising Diffusion Probabilistic Models for 3D Medical Image Generation. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-34341-2"},{"key":"ref_25","first-page":"1","article-title":"Cascaded Diffusion Models for High Fidelity Image Generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Karras, T., Aittala, M., Lehtinen, J., Hellsten, J., Aila, T., and Laine, S. (2024, January 16\u201322). Analyzing and Improving the Training Dynamics of Diffusion Models. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, Q., Fan, H., Wang, Y., Tang, Y., and Qu, L. (2024, January 16\u201322). Residual Denoising Diffusion Models. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.00268"},{"key":"ref_28","unstructured":"Ho, J., Jain, A., and Abbeel, P. (2020, January 6\u201312). Denoising Diffusion Probabilistic Models. Proceedings of the Advances in Neural Information Processing Systems 32 (NeurIPS 2019), Vancouver, BC, Canada."},{"key":"ref_29","unstructured":"Schmarje, L. (2024). Addressing the Challenge of Ambiguous Data in Deep Learning: A Strategy for Creating High-Quality Image Annotations with Human Reliability and Judgement Enhancement. [Ph.D. Thesis, Das Institut f\u00fcr Informatik der Christian-Albrechts-Universit\u00e4t zu Kiel]."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1093\/dmfr\/twae044","article-title":"An Attempt to Generate Panoramic Radiographs Including Jaw Cysts Using StyleGAN3","volume":"53","author":"Fukuda","year":"2024","journal-title":"Dentomaxillofacial Radiol."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Abell\u00f3, A., Vassiliadis, P., Romero, O., Wrembel, R., Bugiotti, F., Gamper, J., Solar, G.V., and Zumpano, E. (2023). Evaluating the Robustness of ML Models to Out-of-Distribution Data Through Similarity Analysis. New Trends in Database and Information Systems, Springer Nature.","DOI":"10.1007\/978-3-031-42941-5"},{"key":"ref_32","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Aittala, M., Aila, T., and Lehtinen, J. (2023). The Role of ImageNet Classes in Fr\u00e9chet Inception Distance. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Abell\u00f3, A., Vassiliadis, P., Romero, O., Wrembel, R., Bugiotti, F., Gamper, J., Vargas Solar, G., and Zumpano, E. (2023). Comparison of Selected Neural Network Models Used for Automatic Liver Tumor Segmentation. New Trends in Database and Information Systems, Springer Nature.","DOI":"10.1007\/978-3-031-42941-5"},{"key":"ref_34","unstructured":"Theis, L., van den Oord, A., and Bethge, M. (2016). A Note on the Evaluation of Generative Models. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.cogsys.2019.10.004","article-title":"Inception and ResNet Features Are (Almost) Equivalent","volume":"59","author":"Beveridge","year":"2020","journal-title":"Cogn. Syst. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1822","DOI":"10.58344\/jws.v2i11.472","article-title":"Influence of Pixel Size Difference on Imaging Plate Computed Radiography on the Quality of Digital Images in Intraoral Dental Radiography Examination","volume":"2","author":"Sismadi","year":"2023","journal-title":"J. World Sci."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/10\/356\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T12:41:29Z","timestamp":1760445689000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/10\/356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,11]]},"references-count":36,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["jimaging11100356"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11100356","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,11]]}}}