Deep Learning-Based Dental Radiography Classification Using CNN and EfficientNet

Raissa Maringka; Wilsen Grivin Mokodaser; George Morris William  Tangka

doi:10.31154/cogito.v11i1.1003.218-228

Authors

Raissa Maringka Universitas Klabat
Wilsen Grivin Mokodaser Universitas Klabat
George Morris William Tangka Universitas Klabat

DOI:

https://doi.org/10.31154/cogito.v11i1.1003.218-228

Keywords:

Dental, Deep Learning, CNN, EfficientNet, Radiograph

Abstract

Dental radiographs play a vital role in detecting various oral conditions such as cavities, impacted teeth, restorations, and dental implants. However, manual interpretation of these images can be subjective, time-consuming, and prone to diagnostic inconsistencies. To overcome these limitations, this study proposes an automated classification framework for dental radiographs using deep learning techniques. Two models were developed: a custom Convolutional Neural Network (CNN) and a transfer learning–based EfficientNetB1. The dataset used was sourced from Kaggle’s Dental Radiography collection, consisting of 29,597 X-ray images distributed across five diagnostic categories—Cavity, Fillings, Impacted Tooth, Implant, and Normal. Preprocessing steps included image resizing to 64×64 pixels, normalization, augmentation, and class balancing to address data imbalance. Experimental findings indicate that the EfficientNetB1 model outperformed the CNN baseline, achieving an accuracy of 93.21%, with a precision of 92.80%, recall of 92.40%, and an F1-score of 92.60%, compared to the CNN’s 88.45% accuracy. The superior results of EfficientNetB1 are attributed to its compound scaling strategy and pre-trained ImageNet weights, which enhance feature extraction and generalization capabilities. Overall, this research demonstrates that transfer learning can significantly improve diagnostic accuracy in dental imaging and provides a strong foundation for developing intelligent, automated diagnostic systems in dentistry

References

T. P. Noronha and J. B. F. de Noronha, Global Public Health and Fluoride as a Vaccine for Tooth Decay: The 3rd Most Prevalent Disease in the World and Its" Vaccine". Editora Appris, 2025.

J. A. Phelan, “Dental lesions: diagnosis and treatment,” Oral Dis, vol. 3, no. S1, pp. S235–S237, 1997.

N. Shah, N. Bansal, and A. Logani, “Recent advances in imaging technologies in dentistry,” World J Radiol, vol. 6, no. 10, p. 794, 2014.

F. Chairunisa et al., “Oral health status and oral healthcare system in Indonesia: A narrative review,” J Int Soc Prev Community Dent, vol. 14, no. 5, pp. 352–361, 2024.

S. Waite, J. Scott, B. Gale, T. Fuchs, S. Kolla, and D. Reede, “Interpretive error in radiology,” American Journal of Roentgenology, vol. 208, no. 4, pp. 739–749, 2017.

L. Pinto-Coelho, “How artificial intelligence is shaping medical imaging technology: a survey of innovations and applications,” Bioengineering, vol. 10, no. 12, p. 1435, 2023.

S. S. Kshatri and D. Singh, “Convolutional neural network in medical image analysis: a review,” Archives of Computational Methods in Engineering, vol. 30, no. 4, pp. 2793–2810, 2023.

K. Sampath, S. Rajagopal, and A. Chintanpalli, “A comparative analysis of CNN-based deep learning architectures for early diagnosis of bone cancer using CT images,” Sci Rep, vol. 14, no. 1, p. 2144, 2024.

R. Lamba, “Advances in AI for Medical Imaging: A Review of Machine and Deep Learning in Disease Detection,” Procedia Comput Sci, vol. 260, pp. 262–273, 2025.

I. Nogues, J. Yao, D. Mollura, and R. M. Summers, “Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning,” 2016, IEEE.

M. T. Islam, M. A. Rahman, M. T. R. Mazumder, and S. H. Shourov, “Comparative Analysis of Neural Network Architectures for Medical Image Classification: Evaluating Performance Across Diverse Models,” American Journal of Advanced Technology and Engineering Solutions, vol. 4, no. 01, pp. 1–42, 2024.

C. Lin, P. Yang, Q. Wang, Z. Qiu, W. Lv, and Z. Wang, “Efficient and accurate compound scaling for convolutional neural networks,” Neural Networks, vol. 167, pp. 787–797, 2023.

S. A. Prajapati, R. Nagaraj, and S. Mitra, “Classification of dental diseases using CNN and transfer learning,” in 2017 5th International symposium on computational and business intelligence (ISCBI), IEEE, 2017, pp. 70–74.

S.-L. Chen et al., “Detection of various dental conditions on dental panoramic radiography using Faster R-CNN,” IEEE Access, vol. 11, pp. 127388–127401, 2023.

K.-C. Li et al., “Detection of tooth position by YOLOv4 and various dental problems based on CNN with bitewing radiograph,” IEEE Access, vol. 12, pp. 11822–11835, 2024.

J. Lian, L. Freeman, Y. Hong, and X. Deng, “Robustness with respect to class imbalance in artificial intelligence classification algorithms,” Journal of Quality Technology, vol. 53, no. 5, pp. 505–525, 2021.

G. Naidu, T. Zuva, and E. M. Sibanda, “A review of evaluation metrics in machine learning algorithms,” in Computer science on-line conference, Springer, 2023, pp. 15–25.

J. H. Cabot and E. G. Ross, “Evaluating prediction model performance,” Surgery, vol. 174, no. 3, pp. 723–726, 2023.

J. Krois et al., “Generalizability of deep learning models for dental image analysis,” Sci Rep, vol. 11, no. 1, p. 6102, 2021.

R. Zannah, M. Bashar, R. Bin Mushfiq, A. Chakrabarty, S. Hossain, and Y. J. Jung, “Semantic segmentation on panoramic dental x-ray images using u-net architectures,” IEEE Access, vol. 12, pp. 44598–44612, 2024.

J. Krois et al., “Generalizability of deep learning models for dental image analysis,” Sci Rep, vol. 11, no. 1, p. 6102, 2021.

D. V. Ashoka, “EffiViT: Hybrid CNN-Transformer for Retinal Imaging,” Computers in Biology and Medicine, vol. 191, p. 110164, 2025.

A. Seifossadat, "Dental Classification," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/code/abbasseifossadat/dental-classification/notebook. [Accessed: January, 2025].