Use of Convolutional Neural Networks for Detection of Pathologies in Dental X-Ray Images in Clinical Decision Support Systems
DOI:
https://doi.org/10.6000/1929-6029.2025.14.83Keywords:
Medical data, neural networks, neural network training, dentistry, x-rays, image processing, object detectionAbstract
Relevance: The relevance of the study is determined by the need for automated, scalable solutions for processing large volumes of dental radiological images, which provide precise segmentation, detection, and classification of pathologies in the integrated Clinical Decision Support System (CDSS) modules.
Aim: The aim of the study is to develop, optimize, and verify a HITL-CDSS framework for dental radiology with multi-level integration of Convolutional Neural Network (CNN) models, ensuring architectural consistency, metric validity, and expert adaptability.
Methods: Research methods: critical architectural and functional analysis of CNN models, metric and indicator modelling of efficiency, synthesis and Unified Modelling Language-based (UML)modelling of the CDSS framework, UML optimization with Human-in-the-loop (HITL) integration, metric and indicator verification of HITL-CDSS.
Results: Architectural and functional, metric and indicator, as well as UML modelling of CNN architectures was carried out for the purpose of integration into the dental radiology CDSS. The resultant HITL-optimized framework based on DenseNet/EfficientNet, HRNet, YOLOv8 provided AUC = 0.96–0.98, F1@t = 0.91–0.94, DSC = 0.89–0.92, mAP = 0.72–0.77 at ECE = 0.02–0.04. Integration of HITL mechanisms increased Explainable Artificial Intelligence (XAI) interpretability, resistance to domain shifting, and clinical validity, indicating the appropriateness of multi-modular construction of CDSS with the inclusion of expert feedback.
Conclusion: The academic novelty of the study is the development of a HITL-CDSS framework with multi-level CNN integration, which provides metrically verified interpretability, domain-stable generalizability, and clinical relevance in dental radiology tasks.
References
Sum HYO. A chronological narrative review of AI evolution in dentistry. Pak J Life Soc Sci 2025; 23(1). DOI: https://doi.org/10.57239/PJLSS-2025-23.1.00597
Shekarappa C, Dasu L, Preethi P, Devi SK, Arampurath A. Artificial intelligence-powered dentistry: Enhancing patient care and efficiency. CODS J Dent 2025; 16(1): 15–19. DOI: https://doi.org/10.5005/jp-journals-10063-0161
Akram HM. Artificial intelligence in dentistry: Advancements in periodontology and other specialties, diagnosis, treatment planning, and ethical considerations. Dent Rev 2025; 5(2): 100157. DOI: https://doi.org/10.1016/j.dentre.2025.100157
Hong Y, Pan T, Zhu S, Hu M, Zhou Z, Xu T. A visualization system for intelligent diagnosis and statistical analysis of oral diseases based on panoramic radiography. Sci Rep 2025; 15(1). DOI: https://doi.org/10.1038/s41598-025-01733-5
Nour SM, Shehab RS, Said SA, Abdel Halim IT. Harnessing the power of an integrated artificial intelligence model for enhancing reliable and efficient dental healthcare systems. Appl SystInnov 2025; 8(1): 7. DOI: https://doi.org/10.3390/asi8010007
Firincioglulari M, Boztuna M, Mirzaei O, Karanfiller T, Akkaya N, Orhan K. Segmentation of pulp and pulp stones with automatic deep learning in panoramic radiographs: An artificial intelligence study. Dent J 2025; 13(6): 274. DOI: https://doi.org/10.3390/dj13060274
Asghar S, Rashid J, Masood A. CariesXplainer: Enhancing dental caries detection using Gradient-weighted Class Activation Mapping and transfer learning. Multimed Tools Appl 2025. DOI: https://doi.org/10.1007/s11042-025-21001-y
Parkhi P, Harjal S, Sahu A, Agrawal P, Shingne H, Bobde Y, Padole A. A comprehensive deep learning framework for dental disease classification. J Eur Syst Automat 2025; 58(3): 511–521. DOI: https://doi.org/10.18280/jesa.580309
Mahizha SI, Annrose J, Mano ChristaineAngelo J, DomilinShyni I, vedaGiri GV. Deep convolutional neural networks for early detection of interproximal caries using bitewing radiographs: A systematic review. Evid Based Dent 2025; 26: 117. DOI: https://doi.org/10.1038/s41432-025-01134-7
Singh V, Singh K, Sehrawat R, Singh AP, Augustine J, Verma M. Deep learning techniques for dental caries detection and prosthodontics: A systematic review. In 2025 2nd international conference on computational intelligence, communication technology and networking (CICTN) (pp. 651–655). IEEE, 2025. DOI: https://doi.org/10.1109/CICTN64563.2025.10932642
Sneha Shetty R, Smitha, Saritha Pai S. Segmentation of dental X-ray images using U-net architecture, enhanced by CNN and GAN. In Recent trends in healthcare innovation (pp. 96–104). London: CRC Press, 2025. DOI: https://doi.org/10.1201/9781003501367-13
Yassar MKA, Fitria M, Oktiana M, Yufnanda MA, Saddami K, Muchtar K, Isma TRA. The role of u-net segmentation for enhancing deep learning-based dental caries classification. Indones J Electron Electromed Eng Med Inform 2025; 7(2): 253–269. DOI: https://doi.org/10.35882/ijeeemi.v7i2.75
Ma Y, Al-Aroomi MA, Zheng Y, Ren W, Liu P, Wu Q, ... Jiang C. Application of Mask R-CNN for automatic recognition of teeth and caries in cone-beam computerized tomography. BMC Oral Health 2025; 25(1). DOI: https://doi.org/10.1186/s12903-025-06293-8
Altan G, Al Samar A. Tooth segmentation on dental panoramic X-rays using Mask R-CNN. InMining biomedical text, images and visual features for information retrieval (pp.481–498). Elsevier, 2025. DOI: https://doi.org/10.1016/B978-0-443-15452-2.00022-4
Putra RH, Astuti ER, Wijaksana IK, E., Fariza A, Sitalaksmi RM, Yoda N. Automated periodontal bone loss detection on panoramic radiographs using you only look once v8 (yolov8): A retrospective AI approach. J Int Oral Health 2025; 17(3): 203–211. DOI: https://doi.org/10.4103/jioh.jioh_20_25
Hua Y, Chen R, Qin H. YOLO-DentSeg: A lightweight real-time model for accurate detection and segmentation of oral diseases in panoramic radiographs. Electronics 2025; 14(4): 805. DOI: https://doi.org/10.3390/electronics14040805
Bhargav A, Kumar SSP. Optimizing disease detection: Advancing gingivitis and calculus accuracy with RESNET V2 50 over RESNET 101. In 3rd international conference on engineering and science to achieve the sustainable development goals (art. no. 020062). AIP Publishing 2025. DOI: https://doi.org/10.1063/5.0278261
Justaniah E, Alhothali A. Classifying oral health issues from spectral imaging using convolutional neural network. In 2025 ai-driven smart healthcare for society 5.0 (pp. 143–148). IEEE, 2025. DOI: https://doi.org/10.1109/IEEECONF64992.2025.10963258
Ayhan B, Ayan E, Bayraktar Y. A novel deep learning-based perspective for tooth numbering and caries detection. Clin Oral Investig 2024; 28(3). DOI: https://doi.org/10.1007/s00784-024-05566-w
Kartbak SBA, Özel MB, Kocakaya DNC, Çakmak M, Sinanoğlu EA. Classification of intraoral photographs with deep learning algorithms trained according to cephalometric measurements. Diagnostics 2025; 15(9): 1059. DOI: https://doi.org/10.3390/diagnostics15091059
Amien FM, Kurniawan D, Junaidi A, Hermanto B. A comparative study of CNN architectures: Convnext, mobilenetv3, and efficientnet for oral disease diagnosis.J Pepadun 2025; 6(1): 81-91. DOI: https://doi.org/10.23960/pepadun.v6i1.267
Boy AF, Akhyar A, Arif TY, Syahrial S. Development of an artificial intelligence model based on MobileNetV3 for early detection of dental caries using smartphone images: A preliminary study.Adv Sci Technol Res J 2025; 19(4): 109–116. DOI: https://doi.org/10.12913/22998624/200308
Kaushik P, Kukreja V, Khurana S. Deep learning approaches for automated classification of dental conditions: A comparative study of inceptionv3 and resnet18. In 2024 international conference on augmented reality, intelligent systems, and industrial automation (ARIIA) (pp. 1–6). IEEE, 2024. DOI: https://doi.org/10.1109/ARIIA63345.2024.11051908
Inani H, Mehta V, Bhavsar D, Gupta RK, Jain A, Akhtar Z. AI-enabled dental caries detection using transfer learning and gradient-based class activation mapping. J Ambient Intell Humaniz Comput 2024. DOI: https://doi.org/10.1007/s12652-024-04795-x
Mohi A, Kareem L, Hassan AA. EfficientNet-B0 deep learning model for accurate classification of intrabony lesions in dental panoramic radiographs. PREPRINT (Version 1) available at Res Sq 2025. DOI: https://doi.org/10.21203/rs.3.rs-6207574/v1
Hasnain MA, Ali Z, Maqbool MS, Aziz M. X-ray image analysis for dental disease: A deep learning approach using efficientnets. VFAST Trans Softw Eng 2024; 12(3): 147–165. DOI: https://doi.org/10.21015/vtse.v12i3.1912
Machado LF. Mandible-focused osteoporosis risk assessment using dental panoramic radiography and artificial intelligence models [Doctoral dissertation, Universidade de Sã o Paulo], 2023.
Machado LF, Watanabe PCA, Rodrigues GA, Murta Jr LO. Deep learning for automatic mandible segmentation on dental panoramic X-Ray images. Biomed Phys Eng Express 2023; 9: 035015. DOI: https://doi.org/10.1088/2057-1976/acb7f6
Karuppan Perumal MK, Rajan Renuka R, Kumar Subbiah S, Manickam Natarajan P. Artificial intelligence-driven clinical decision support systems for early detection and precision therapy in oral cancer: A mini review. Front Oral Health 2025; 6. DOI: https://doi.org/10.3389/froh.2025.1592428
Veseli E, Mehrabanian M, Ammar N. The potential of artificial intelligence in the early detection of systemic diseases during routine dental care: The potential of artificial intelligence in the early detection of systemic diseases during routine dental care. Br Dent J 2025; 239(3): 168-174. DOI: https://doi.org/10.1038/s41415-025-8666-7
Subramanian RR, Sudharsan RR, Vairamuthu B, Dewi DA. Neural network models for diagnosing recurrent aphthous ulcerations from clinical oral images. Sci Rep 2025; 15(1). DOI: https://doi.org/10.1038/s41598-025-06951-5
Kim D, Kim J, Choi SG. CNN-based remote dental diagnosis model for caries detection with grad-CAM. Sci Rep 2025; 15(1). DOI: https://doi.org/10.1038/s41598-025-11447-3
Huang Y-Y, Mao Y-C, Chen T-Y, Chen C-A, Chen S-L, Huang Y-J, ... Abu PAR. Application of convolutional neural networks in an automatic judgment system for tooth impaction based on dental panoramic radiography. Diagnostics 2025; 15(11): 1363. DOI: https://doi.org/10.3390/diagnostics15111363
Noor Uddin A, Ali SA, Lal A, Adnan N, Ahmed SMF, Umer F. Applications of AI-based deep learning models for detecting dental caries on intraoral images – a systematic review. Evid Based Dent 2024; 26: 71-72. DOI: https://doi.org/10.1038/s41432-024-01089-1
Kayadibi İ, Köse U, Güraksın GE, Çetin B. An AI-assisted explainable mTMCNN architecture for detection of mandibular third molar presence from panoramic radiography. Int J Med Inform 2025; 105724. DOI: https://doi.org/10.1016/j.ijmedinf.2024.105724
Saldivia-Siracusa C, de Souza ESC, da Silva AVB, Araújo ALD, Pedroso CM, da Silva TA, ... Santos-Silva AR. Automated classification of oral potentially malignant disorders and oral squamous cell carcinoma using a convolutional neural network framework: a cross-sectional study. Lancet Reg Health Am 2025; 47. https://www.thelancet.com/journals/lanam/article/PIIS2667-193X(25)00148-6/fulltext DOI: https://doi.org/10.1016/j.lana.2025.101138
Marie HS, Elbaz M, Soliman RS, Elkhatib AA. DentoMorph-LDMs: Diffusion models based on novel adaptive 8-connected gum tissue and deciduous teeth loss for dental image augmentation. Sci Rep 2025; 15(1). DOI: https://doi.org/10.1038/s41598-025-11955-2
Chai Y, Chai X, Zhang L, Ye G, Sheykhahmad FR. Oral cancer detection via Vanilla CNN optimized by improved artificial protozoa optimizer. Sci Rep 2025; 15(1). DOI: https://doi.org/10.1038/s41598-025-11861-7
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Policy for Journals/Articles with Open Access
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
Policy for Journals / Manuscript with Paid Access
Authors who publish with this journal agree to the following terms:
- Publisher retain copyright .
- Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work .
