|
Abstract.
The article presents important aspects of the design and results of the evaluation of an intelligent decision support system for diagnostics in dental practice. A modified U-Net architecture is proposed, with a loss function optimized for detecting various pathologies in dental radiographs. The developed mathematical model for the neural network includes components of sensitivity, specificity, F-measure, binary cross-entropy, and probability calibration with adaptive weighting coefficients. The system integrates attention blocks, deep supervision, and spatial dropout, ensuring effective diagnosis of both common and rare dental pathologies. Experimental evaluation demonstrates the superiority of the developed system over existing Russian analogs based on key metrics. The implemented architecture and methods significantly enhance the reliability of predictions and, consequently, the accuracy of automated diagnostic results.
Keywords:
intelligent decision support system, dental diagnostics, U-Net, neural networks, rare pathologies, probability calibration, radiographic diagnostics, automated diagnostics, machine learning.
DOI 10.14357/20718632250303
EDN LWUJCO
PP. 22-33.
References
1. Russian Systems of Artificial Intelligence for Healthcare (In Russ.). Available from: https://webiomed.ru/blog/obzor-rossiiskikh-sistem-iskusstvennogo-intellekta-dlia-zdravookhraneniia/ [Accessed 14 Marth 2025]. 2. Litmanovich D.L., Karmazanovsky G.G., Morozov S.P. Artificial intelligence in radiology: state of the problem, challenges and solutions // Vestnik rentgenologii i radiologii; 2022; 103(2): 98-110 (In Russ.). 3. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation // Medical Image Computing and Computer-Assisted Intervention (MICCAI); 2015. P. 234-241. 4. DENTEX: Datasets for Dental X-ray Analysis. Available from: https://huggingface.co/datasets/ibrahimhamamci/DENTEX [Accessed 14 Marth 2025]. 5. Guo C., Pleiss G., Sun Y., Weinberger K.Q. On Calibration of Modern Neural Networks // Proceedings of the 34th International Conference on Machine Learning; 2017. P. 1321-1330. 6. Schwendicke F., Samek W., Krois J. Artificial Intelligence in Dentistry: Chances and Challenges // Journal of Dental Research; 2023; 99(7):769-774. 7. Diagnocat: Virtual assistant for dental image analysis (In Russ.). Available from: https://diagnocat.com/ru/ [Accessed 15 Marth 2025]. 8. Lin T.Y., Goyal P., Girshick R., He K., Dollár P. Focal Loss for Dense Object Detection // IEEE International Conference on Computer Vision (ICCV); 2017. P. 2980-2988. 9. Wang G., Li W., Aertsen M., Deprest J., Ourselin S., Vercauteren T. Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks // Neurocomputing; 2019; 338:34-45. 10. Taha A., Hanbury A. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool // BMC Medical Imaging; 2015; 15(1):29. 11. Weng Z., Zhou H., He L., Liu C., Yang H. Attention U-Net: A Novel U-Net with Attention Mechanism for Stomatological Image Segmentation // Healthcare; 2022; 10(2):388. 12. Oktay O., Schlemper J., Folgoc L.L., Lee M., Heinrich M., Misawa K., Mori K., McDonagh S., Hammerla N.Y., Kainz B., Glocker B., Rueckert D. Attention U-Net: Learning Where to Look for the Pancreas // Medical Imaging with Deep Learning; 2018. 13. Sudakov D.V., Sudakov O.V., Bogacheva E.V. Application of neural networks in the diagnosis of dental diseases // Bulletin of New Medical Technologies; 2021; 28(1):54-59 (In Russ.). 14. Jundaeng J., Chamchong R., Nithikathkul C. Artificial intelligence-powered innovations in periodontal diagnosis: a new era in dental healthcare // Frontiers in Medical Technology; 2024; 6:1469852. 15. Dentomo: Software product for dental image recognition (In Russ.). Available from: https://dentomo.ru/ [Accessed 15 Marth 2025]. 16. Ulybnis.Ai: Telemedicine AI application for early detection of enamel demineralization, gum diseases, caries, and plaque from dental photos (In Russ.). Available from: https://www.smile-ai-market.ru/ [Accessed 15 Marth 2025]. 17. How artificial intelligence detected malocclusion anomalies compared to orthodontists. Available from: https://www.drbicuspid.com/dental-specialties/orthodontics/article/15677083/how-ai-performed-in-malocclusiondetection-vs-orthodontists [Accessed 15 Marth 2025]. 18. Staroverov N.E., Gryaznov A.Y., Kamyshanskaya I.G., Potrakhov N.N., Kholopova E.D. The method of increasing the information content of microfocus X-ray images // Russian Technological Journal; 2021; 9(6):57-63 (In Russ.).
|
