IRO Journals
Journal of Innovative Image Processing

An Efficient Dual Branch Multi-Scale CNN With Reconstruction Learning and Explainable AI for Dental Caries Classification

Open Access
Published: 16 July, 2026
Pages: 1022-1045
  • Shashikala K.S. , Shashikala K.S.
    Research Scholar, Department of Computer Science and Engineering, New Horizon College of Engineering, Bengaluru, Visvesvaraya Technological University, Belagavi, Karnataka, India
    Research Scholar, Department of Computer Science and Engineering, New Horizon College of Engineering, Bengaluru, Visvesvaraya Technological University, Belagavi, Karnataka, India
  • Umamaheswaran S. Umamaheswaran S.
    Research Supervisor, Department of Computer Science and Engineering, New Horizon College of Engineering, Bengaluru, Visvesvaraya Technological University, Belagavi, Karnataka, India
    Research Supervisor, Department of Computer Science and Engineering, New Horizon College of Engineering, Bengaluru, Visvesvaraya Technological University, Belagavi, Karnataka, India
view PDF
view PDF

How to Cite

K.S., Shashikala, and Umamaheswaran S. 2026. “An Efficient Dual Branch Multi-Scale CNN With Reconstruction Learning and Explainable AI for Dental Caries Classification”. Journal of Innovative Image Processing 8 (3): 1022-45. https://doi.org/10.36548/jiip.2026.3.014.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Dental Disease Diagnosis
Reconstruction Learning
Sharpness Aware Minimization
Multi Scale Learning

Abstract

Preventive oral healthcare depends on the early detection of dental caries. Delicate visual differences between healthy tooth and early-stage lesions make automated disease diagnosis difficult. This work introduces a comparative analysis between a Single-Branch Convolutional Neural Network (SBCNN) and a proposed Dual-Branch Multi-Scale Convolutional Neural Network (DBMSCNN) for multiple class dental caries classification. It integrates Sharpness-Aware Minimization (SAM), multi-scale feature extraction, and self-supervised reconstruction learning to enhance feature robustness and generalization. We utilized a three-class dental caries dataset consisting of No Enamel Caries, Advanced Caries and Early Stage Caries. A total of 447 samples were used for testing in each fold. The proposed DBMSCNN framework achieved a mean classification accuracy of 92.43% across five-fold stratified cross-validation. The model demonstrated strong discriminative capability and a low false-positive rate, with a mean specificity of 96.14% and a mean precision of 92.59%. Reconstruction-based self-supervised pretraining improved anatomical feature learning, resulting in mean Dice and IoU scores of 0.8530 and 0.7577 respectively. Feature-level analysis using t-SNE is done for qualitative visualization of latent feature distributions for the proposed model, while Grad-CAM and saliency maps show meaningful and moderate localization of carious regions. The comparative results validate the effectiveness of multi-scale learning, reconstruction-based regularization, and SAM optimization in improving diagnostic reliability for dental caries classification.

References

  1. Li, Jiaxing. "DA-Net: A Classification-Guided Network for Dental Anomaly Detection from Dental and Maxillofacial Images." Journal of King Saud University-Computer and Information Sciences 36, no. 9 (2024): 102229.
  2. Featherstone, John DB. "Dental Caries: A Dynamic Disease Process." Australian dental journal 53, no. 3 (2008): 286-291.
  3. Jones, Bree, Mathias Lambach, Tong Chen, Stavroula Michou, Nicky Kilpatrick, Nigel Curtis, David P. Burgner, Christoph Vannahme, and Mihiri Silva. "Dental Caries Detection in Children Using Intraoral Scans and Deep Learning." Journal of Dentistry 160 (2025): 105906.
  4. PR, Bipin, and Anoop BK. "Automated Biomedical Image Classification Using Multi-Scale Dense Dilated Semi-Supervised U-Net with Cnn Architecture." Multimedia Tools and Applications 83, no. 10 (2024): 30641-30673.
  5. Barragan-Montero, Ana, Adrien Bibal, Margerie Huet Dastarac, Camille Draguet, Gilmer Valdes, Dan Nguyen, Siri Willems et al. "Towards a Safe and Efficient Clinical Implementation of Machine Learning in Radiation Oncology by Exploring Model Interpretability, Explainability and Data-Model Dependency." Physics in Medicine & Biology 67, no. 11 (2022): 11TR01.
  6. Lin, Jianwu, Xin Zhang, Yongbin Qin, Shengxian Yang, Xingtian Wen, Tomislav Cernava, Quirico Migheli, and Xiaoyulong Chen. "Local and Global Feature-Aware Dual-Branch Networks for Plant Disease Recognition." Plant Phenomics 6 (2024): 0208.
  7. Rupesh Devidas Sushir “Exploring Novel Self-Supervised Learning Techniques for Image Reconstruction Tasks”. International Journal of Advanced Research in Science, Communication and Technology, (2024). 48–55.
  8. Huang, Peizhou, Chaoyi Zhang, Xiaoliang Zhang, Xiaojuan Li, Liang Dong, and Leslie Ying. "Self-Supervised Deep Unrolled Reconstruction Using Regularization by Denoising." IEEE transactions on medical imaging 43, no. 3 (2023): 1203-1213.
  9. Rani, Veenu, Syed Tufael Nabi, Munish Kumar, Ajay Mittal, and Krishan Kumar. "Self-Supervised Learning: A Succinct Review." Archives of Computational Methods in Engineering 30, no. 4 (2023): 2761-2775.
  10. Ohri, Kriti, and Mukesh Kumar. "Review on Self-Supervised Image Recognition Using Deep Neural Networks." Knowledge-Based Systems 224 (2021): 107090.
  11. Gidaris, Spyros, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, and Matthieu Cord. "Learning Representations by Predicting Bags of Visual Words." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6928-6938. 2020.
  12. T. Ratchatorn and M. Tanaka, "Improving Sharpness-Aware Minimization Using Label Smoothing and Adaptive Adversarial Cross-Entropy Loss," in IEEE Access, vol. 13, 2025, 100326-100337.
  13. Zhang, Zhiyuan, Ruixuan Luo, Qi Su, and Xu Sun. "GA-SAM: Gradient-Strength Based Adaptive Sharpness-Aware Minimization for Improved Generalization." In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, 3888-3903.
  14. Liu, Yong, Siqi Mai, Xiangning Chen, Cho-Jui Hsieh, and Yang You. "Towards Efficient and Scalable Sharpness-Aware Minimization." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, 12360-12370.
  15. Li, Tao, Pan Zhou, Zhengbao He, Xinwen Cheng, and Xiaolin Huang. "Friendly Sharpness-Aware Minimization." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024, 5631-5640.
  16. Yun, Vincent-Daniel. "Sharpness-Aware Minimization with Z-Score Gradient Filtering." In ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2026, 2961-2965.
  17. J., Priya, Kavya S., Gunavathie M.A., and Jacophine Susmi S. 2026. “A Novel Optimized Hybrid ResNextTransform for Dental Diseases Classification With Crested Porcupine Optimizer”. Journal of Innovative Image Processing 8 (1): 233-49. https://doi.org/10.36548/jiip.2026.1.013.
  18. Gruber, Nadja & Schwab, Johannes & Haltmeier, Markus & Biguri, Ander & Dlaska, Clemens & Hwang, Gyeongha. (2025). Noisier2Inverse: Self-Supervised Learning for Image Reconstruction with Correlated Noise. 10.48550/arXiv.2503.19468.
  19. Millard, Charles, and Mark Chiew. "A Theoretical Framework for Self-Supervised MR Image Reconstruction Using Sub-Sampling via Variable Density Noisier2Noise." IEEE transactions on computational imaging 9 (2023): 707-720.
  20. Yaman, Burhaneddin & Hosseini, Seyed Amir Hossein & Moeller, Steen & Ellermann, Jutta & Uğurbil, Kâmil & Akçakaya, Mehmet. (2020). Self‐Supervised Learning of Physics‐Guided Reconstruction Neural Networks Without Fully Sampled Reference Data. Magnetic Resonance in Medicine. 84. 10.1002/mrm.28378.
  21. Islam, Sheikh Rabiul, William Eberle, Sheikh Khaled Ghafoor, and Mohiuddin Ahmed. "Explainable Artificial Intelligence Approaches: A Survey." arXiv preprint arXiv:2101.09429 (2021).
  22. Srinivasu, Parvathaneni Naga, N. Sandhya, Rutvij H. Jhaveri, and Roshani Raut. "From Blackbox to Explainable AI in Healthcare: Existing Tools and Case Studies." Mobile Information Systems 2022, no. 1 (2022): 8167821.
  23. Kisten, Melvin, Absalom El-Shamir Ezugwu, and Micheal O. Olusanya. "Explainable Artificial Intelligence Model for Predictive Maintenance in Smart Agricultural Facilities." IEEE Access 12 (2024): 24348-24367.
  24. Himel, Galib Muhammad Shahriar; Islam, Md Masudul; Hannan, Ummae Hamida (2023), “Caries-Spectra: A dataset of Enamel Caries”, Mendeley Data, V2, doi: 10.17632/9jnf2jvghy.2
  25. Foret, Pierre, Ariel Kleiner, Hossein Mobahi, and Behnam Neyshabur. "Sharpness-Aware Minimization for Efficiently Improving Generalization." arXiv preprint arXiv:2010.01412 (2020).