CLASSIFICATION OF SKELETAL MALOCCLUSION USING CONVENTIONAL NEURAL NETWORK (CNN) WITH VISION ATTENTION
Abstract
Skeletal malocclusion, a common orthodontic condition, affects jaw function and dental health. It is often caused by genetic factors, abnormal growth, bad habits, or trauma. Conventional diagnostic models often fail to generalize across diverse datasets, leading to overfitting and poor test performance. This study aimed to improve diagnostic accuracy by incorporating Vision Attention mechanisms into a custom Convolutional Neural Network (CNN), enabling the model to focus on critical regions in X-ray images. A total of 491 radiographic images depicting facial skeletal structures with various malocclusion types (Classes 1, 2, and 3) were used in this study. A custom CNN was developed and evaluated both with and without attention mechanisms—specifically, Scaled Dot Product Attention and Multihead Attention—to assess their impact on classification performance. The baseline CNN without attention achieved an accuracy of 0.68. With Scaled Dot Product Attention, accuracy improved to 0.72, while Multihead Attention achieved the highest accuracy of 0.76. Evaluation using weighted average precision, recall, and F1-score showed that attention mechanisms significantly enhanced the model’s ability to differentiate between malocclusion classes. Notably, the Multihead Attention model yielded the best performance, reducing misclassification errors and improving generalization. Confusion matrix analysis revealed that it had the lowest classification errors, especially in distinguishing between Class 0 and Class 1. These results suggest that incorporating attention mechanisms, particularly Multihead Attention, enhances CNN performance by improving feature extraction and classification accuracy. Future research should explore more diverse datasets and implement advanced augmentation techniques to improve clinical reliability.
Downloads
References
S. I. Stomatologic, “WORLDWIDE PREVALENCE OF MALOCCLUSION IN THE DIFFERENT STAGES OF DENTITION: A SYSTEMATIC REVIEW AND META-ANALYSIS,” Eur J Paediatr Dent, vol. 21, p. 115, 2020. doi: 10.23804/ejpd.2020.21.02.05.
W. Farani and A. MI, “PREVALENSI MALOKLUSI ANAK USIA 9-11 TAHUN DI SD IT INSAN UTAMA YOGYAKARTA,” Insisiva Dental Journal: Majalah Kedokteran Gigi Insisiva, vol. 10, no. 1, pp. 26–31, 2021. doi: https://doi.org/10.18196/di.v10i1.7534.
M. F. Harun et al., “INCISOR MALOCCLUSION USING CUT-OUT METHOD AND CONVOLUTIONAL NEURAL NETWORK,” Progress in Microbes and Molecular Biology, 2022. doi: https://doi.org/10.36877/pmmb.a0000279.
M.-H. Guo et al., “ATTENTION MECHANISMS IN COMPUTER VISION: A SURVEY,” Comput Vis Media (Beijing), vol. 8, no. 3, pp. 331–368, 2022. doi: https://doi.org/10.1007/s41095-022-0271-y.
L. Cai, J. Gao, and D. Zhao, “A REVIEW OF THE APPLICATION OF DEEP LEARNING IN MEDICAL IMAGE CLASSIFICATION AND SEGMENTATION,” Ann Transl Med, vol. 8, no. 11, 2020. doi: https://doi.org/10.21037/atm.2020.02.44.
I. R. Ward, H. Laga, and M. Bennamoun, “RGB-D IMAGE-BASED OBJECT DETECTION: FROM TRADITIONAL METHODS TO DEEP LEARNING TECHNIQUES RGB-D IMAGE ANALYSIS AND PROCESSING,” 2019. doi: https://doi.org/10.1007/978-3-030-28603-3_8
A. Vaswani et al., “ATTENTION IS ALL YOU NEED,” 2023. doi: 10.48550/arXiv.1706.03762.
S. H. Jeong, J. P. Yun, H.-G. Yeom, H. K. Kim, and B. C. Kim, “DEEP-LEARNING-BASED DETECTION OF CRANIO-SPINAL DIFFERENCES BETWEEN SKELETAL CLASSIFICATION USING CEPHALOMETRIC RADIOGRAPHY,” Diagnostics, vol. 11, no. 4, p. 591, 2021. doi: https://doi.org/10.3390/diagnostics11040591.
W. Shin et al., “DEEP LEARNING BASED PREDICTION OF NECESSITY FOR ORTHOGNATHIC SURGERY OF SKELETAL MALOCCLUSION USING CEPHALOGRAM IN KOREAN INDIVIDUALS,” BMC Oral Health, vol. 21, pp. 1–7, 2021. doi: https://doi.org/10.1186/s12903-021-01513-3.
H. Li, Y. Xu, Y. Lei, Q. Wang, and X. Gao, “AUTOMATIC CLASSIFICATION FOR SAGITTAL CRANIOFACIAL PATTERNS BASED ON DIFFERENT CONVOLUTIONAL NEURAL NETWORKS,” Diagnostics, vol. 12, no. 6, p. 1359, 2022. doi: https://doi.org/10.3390/diagnostics12061359.
J. N. Zhang et al., “DEEP LEARNING-BASED PREDICTION OF MANDIBULAR GROWTH TREND IN CHILDREN WITH ANTERIOR CROSSBITE USING CEPHALOMETRIC RADIOGRAPHS,” BMC Oral Health, vol. 23, no. 1, Dec. 2023, doi: https://doi.org/10.1186/s12903-023-02734-4.
P. Tiwari et al., “CNN BASED MULTICLASS BRAIN TUMOR DETECTION USING MEDICAL IMAGING,” Comput Intell Neurosci, vol. 2022, 2022. doi: https://doi.org/10.1155/2022/1830010.
N. Kumar, T. Lakshmi, D. Slavakkam, and R. Ch, “INTEGRATED PREDICTIVE ANALYSIS FOR PERIODONTAL DISEASE AND MALOCCLUSION DETECTION IN DENTISTRY USING DEEP LEARNING AND CNN-BASED DECISION MAKING,” 2023, doi: 10.21203/rs.3.rs-3177552/v1.
G. Celik, “DETECTION OF COVID-19 AND OTHER PNEUMONIA CASES FROM CT AND X-RAY CHEST IMAGES USING DEEP LEARNING BASED ON FEATURE REUSE RESIDUAL BLOCK AND DEPTHWISE DILATED CONVOLUTIONS NEURAL NETWORK,” Appl Soft Comput, vol. 133, p. 109906, 2023. doi: https://doi.org/10.1016/j.asoc.2022.109906.
S. Aksoy, B. Kiliç, and T. Süzek, “COMPARATIVE ANALYSIS OF THREE MACHINE LEARNING MODELS FOR EARLY PREDICTION OF SKELETAL CLASS-III MALOCCLUSION FROM PROFILE PHOTOS,” Mugla Journal of Science and Technology, vol. 8, no. 2, pp. 22–30, Dec. 2022, doi: https://doi.org/10.22531/muglajsci.1108397.
G. S. Demircan, B. Kılıç, and T. Önal-Süzek, “EARLY DIAGNOSIS AND PREDICTION OF SKELETAL CLASS III MALOCCLUSION FROM PROFILE PHOTOS USING ARTIFICIAL INTELLIGENCe,” in 8th European Medical and Biological Engineering Conference: Proceedings of the EMBEC 2020, November 29–December 3, 2020 Portorož, Slovenia, Springer, 2021, pp. 434–448. doi: https://doi.org/10.1007/978-3-030-64610-3_50.
L. Nan et al., “AUTOMATED SAGITTAL SKELETAL CLASSIFICATION OF CHILDREN BASED ON DEEP LEARNING,” Diagnostics, vol. 13, no. 10, p. 1719, 2023. doi: https://doi.org/10.3390/diagnostics13101719.
G. Li et al., “PRACTICES AND APPLICATIONS OF CONVOLUTIONAL NEURAL NETWORK-BASED COMPUTER VISION SYSTEMS IN ANIMAL FARMING: A REVIEW,” Sensors, vol. 21, no. 4, p. 1492, 2021. doi: https://doi.org/10.3390/s21041492.
S. Y. Chaganti, I. Nanda, K. R. Pandi, T. G. Prudhvith, and N. Kumar, “IMAGE CLASSIFICATION USING SVM AND CNN,” in 2020 International conference on computer science, engineering and applications (ICCSEA), IEEE, 2020, pp. 1–5. doi: https://doi.org/10.1109/ICCSEA49143.2020.9132851.
O. O. Oladimeji and A. O. J. Ibitoye, “BRAIN TUMOR CLASSIFICATION USING RESNET50-CONVOLUTIONAL BLOCK ATTENTION MODULE,” Applied Computing and Informatics, no. ahead-of-print, 2023. doi: https://doi.org/10.1108/ACI-09-2023-0022.
Copyright (c) 2025 I Putu Ronny Eka Wicaksana, Antoni Wibowo, Rojali Rojali, Azurah A Samah, Aspalilah Alias
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this Journal agree to the following terms:
- Author retain copyright and grant the journal right of first publication with the work simultaneously licensed under a creative commons attribution license that allow others to share the work within an acknowledgement of the work’s authorship and initial publication of this journal.
- Authors are able to enter into separate, additional contractual arrangement for the non-exclusive distribution of the journal’s published version of the work (e.g. acknowledgement of its initial publication in this journal).
- Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their websites) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published works.
1.gif)
