A Residual Cross-Attention Fusion Network with Adaptive Focal-Margin Loss for Robust Dental Caries Detection from Intraoral Radiographs

International Journal of Electronics and Communication Engineering

© 2025 by SSRG - IJECE Journal

Volume 12 Issue 9

Year of Publication : 2025

Authors : Sheetal Kulkarni, N. Rama Rao

10.14445/23488549/IJECE-V12I9P117

How to Cite?

Sheetal Kulkarni, N. Rama Rao, "A Residual Cross-Attention Fusion Network with Adaptive Focal-Margin Loss for Robust Dental Caries Detection from Intraoral Radiographs," SSRG International Journal of Electronics and Communication Engineering, vol. 12,  no. 9, pp. 194-202, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I9P117

Abstract:

In recent years, Automated dental caries detection using intraoral radiographs has attained increasing potential to assist dentists in early diagnosis and treatment planning. Traditional research primarily relies on general-purpose Convolutional Neural Networks (CNNs) such as VGG16 or ResNet, which have demonstrated reasonable performance in medical imaging tasks. The major challenge remains in accurately identifying carious lesions in the occurrence of anatomical noise, restorations and poor image contrast, which often leads to high false positive rates. This research proposes a novel hybrid architecture called ResXformer to address these limitations. Initially, the data is collected from diverse clinical sources and pre-processed to enhance the poor contrast. A depth-wise separable CNN backbone extracts fine-grained features with reduced computational cost. Later, a residual cross-attention fusion mechanism allows bidirectional information flow between the CNN and Transformer branches, enhancing spatial and contextual learning. Further, an adaptive focal-margin loss is introduced that penalizes ambiguous predictions based on per-sample logit variance, reducing false positives near restorations. Together, these steps create a robust, lightweight model tailored for accurate and interpretable dental caries detection in clinical practice.

Keywords:

Adaptive Focal-Margin Loss, Convolutional Neural Networks, Dental Caries Detection, Intraoral Radiographs, Residual Cross-Attention Fusion Network.

References:

[1] Bree Jones et al., “Dental Caries Detection in Children using Intraoral Scans and Deep Learning,” Journal of Dentistry, vol. 160, pp. 1-12, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Viktor Szabó et al., “Validation of Artificial Intelligence Application for Dental Caries Diagnosis on Intraoral Bitewing and Periapical Radiographs,” Journal of Dentistry, vol. 147, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Javier Pérez De Frutos et al., “AI-Dentify: Deep Learning for Proximal Caries Detection on Bitewing X-Ray - Hunt4 Oral Health Study,” BMC Oral Health, vol. 24, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Betül Ayhan, Enes Ayan, and Saadet Atsü, “Detection of Dental Caries Under Fixed Dental Prostheses by Analyzing Digital Panoramic Radiographs with Artificial Intelligence Algorithms based on Deep Learning Methods,” BMC Oral Health, vol. 25, pp. 1-10, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[5] S. Siji Rani et al., “Deep Learning-based Cavity Detection in Diverse Intraoral Images: A Web-based Tool for Accessible Dental Care,” Procedia Computer Science, vol. 233, pp. 882-891, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Yutong Liang et al., “AI-Driven Dental Caries Management Strategies: From Clinical Practice to Professional Education and Public Self Care,” International Dental Journal, vol. 75, no. 4, pp. 1-11, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Mashail Alsolamy et al., “Automated Detection and Labeling of Posterior Teeth in Dental Bitewing X-Rays Using Deep Learning,” Computers in Biology and Medicine, vol. 183, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Leena Rohan Mehta et al., “Identifying Suitable Deep Learning Approaches for Dental Caries Detection Using Smartphone Imaging,” International Journal of Computational Methods and Experimental Measurements, vol. 12, no. 3, pp. 251-267, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Xiaoyan Zhang, “Integrating U-Net and Multi-Model Approaches for Accurate Dental Occlusal Surface and Caries Detection,” 2024 3rd International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC), Mianyang, China, pp. 33-40, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Lubaina T. Arsiwala-Scheppach et al., “Impact of Artificial Intelligence on Dentists’ Gaze during Caries Detection: A Randomized Controlled Trial,” Journal of Dentistry, vol. 140, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Gelareh Haghi Ashtiani et al., “Diagnostic Accuracy of Tele-Dentistry in Screening Children for Dental Caries by Community Health Workers in a Lower-Middle-Income Country,” International Journal of Paediatric Dentistry, vol. 34, no. 5, pp. 567-575, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Bipin Kumar Rai et al., “Leveraging 3D Faster R-CNN for 3D Dental X-ray Restoration and Treatment Identification,” Proceedings of Computing and Machine Learning, Sikkim, India, pp. 241-260, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Kathrin Becker et al., “Eligibility of a Novel BW + Technology and Comparison of Sensitivity and Specificity of Different Imaging Methods for Radiological Caries Detection,” Oral Radiology, vol. 40, pp. 424-435, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Reinhilde Jacobs et al., “Radiographic Diagnosis of Periodontal Diseases – Current Evidence Versus Innovations,” Periodontology 2000, vol. 95, no. 1, pp. 51-69, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Kyubaek Yoon et al., “AI-Based Dental Caries and Tooth Number Detection in Intraoral Photos: Model Development and Performance Evaluation,” Journal of Dentistry, vol. 141, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Jing-Wen Zhang et al., “Diagnostic Accuracy of Artificial Intelligence-Assisted Caries Detection: A Clinical Evaluation,” BMC Oral Health, vol. 24, pp. 1-7, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Luya Lian et al., “Deep Learning for Caries Detection and Classification,” Diagnostics, vol. 11, no. 9, pp. 1-11, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Sohee Kang et al., “Diagnostic Accuracy of Dental Caries Detection using Ensemble Techniques in Deep Learning with Intraoral Camera Images,” Plos One, vol. 19, no. 9, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Haihua Zhu et al., “CariesNet: A Deep Learning Approach for Segmentation of Multi-Stage Caries Lesion from Oral Panoramic X-ray Image,” Neural Computing and Applications, vol. 35, pp. 16051-16059, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Abu Tareq et al., “Visual Diagnostics of Dental Caries through Deep Learning of Non-Standardised Photographs Using a Hybrid YOLO Ensemble and Transfer Learning Model,” International Journal of Environmental Research and Public Health, vol. 20, no. 7, pp. 1-13, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Yi Liu et al., “Oral Screening of Dental Calculus, Gingivitis and Dental Caries through Segmentation on Intraoral Photographic Images Using Deep Learning,” BMC Oral Health, vol. 24, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Geetha Chandrashekar et al., “Collaborative Deep Learning Model for Tooth Segmentation and Identification using Panoramic Radiographs,” Computers in Biology and Medicine, vol. 148, pp. 1-21, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Mehmet Boztuna et al., “Segmentation of Periapical Lesions with Automatic Deep Learning on Panoramic Radiographs: An Artificial Intelligence Study,” BMC Oral Health, vol. 24, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Walaa Magdy Ahmed et al., “Artificial Intelligence in the Detection and Classification of Dental Caries,” The Journal of Prosthetic Dentistry, vol. 133, no. 5, pp.1326-1332, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Ronilo Ragodos et al., “Dental Anomaly Detection using Intraoral Photos via Deep Learning,” Scientific Reports, vol. 12, pp. 1-8, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Taseef Hasan Farook MScDent et al., “A Virtual Analysis of the Precision and Accuracy of 3-Dimensional Ear Casts Generated from Smartphone Camera Images,” The Journal of Prosthetic Dentistry, vol. 128, no. 4, pp. 830-836, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Esra Asci et al., “A Deep Learning Approach to Automatic Tooth Caries Segmentation in Panoramic Radiographs of Children in Primary Dentition, Mixed Dentition, and Permanent Dentition,” Children, vol. 11, no. 6, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Md Arid Hasan, and Krishno Dey, “Depthwise Separable Convolutions with Deep Residual Convolutions,” arXiv Preprint, pp. 1-9, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Omid Nejati Manzari et al., “BEFUnet: A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentation,” arXiv preprint, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Jiaxuan Li et al., “CFFormer: Cross CNN-Transformer Channel Attention and Spatial Feature Fusion for Improved Segmentation of Heterogeneous Medical Images,” Expert Systems with Applications, vol. 295, 2026.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Md Rakibul Islam et al., “Enhancing Semantic Segmentation with Adaptive Focal Loss: A Novel Approach,” arXiv preprint, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]