Abstract
Self-supervised segmentation of panoramic dental radiographs often lacks interpretability, leading clinicians to be hesitant in relying on these predictions. The practical application of such segmentation is limited, as the results must be comprehensible for effective diagnosis and treatment planning. To address this issue, we implement Explainable AI (XAI) techniques, such as Grad-CAM, which generate heat maps that highlight significant areas within the radiographs, thereby enhancing the model's transparency. This approach mitigates the black-box nature of self-supervised models and provides a reliable AI-driven solution. We propose a hybrid strategy that integrates attention-based segmentation with both supervised and self-supervised learning. Self-supervised learning is utilized to analyse unlabelled radiographs to extract features, which are subsequently fine-tuned through supervised learning to achieve accurate segmentation. This model aids in the detection of anomalies such as cavities, fractures, and periodontal diseases, thereby improving diagnostic precision. Additionally, it facilitates treatment planning and bridges the gap between clinical trust and AI automation, rendering AI-based dental imaging more practical and acceptable.
References
- Lu, Wei, Xueqian Yu, Yueyang Li, Yi Cao, Yanning Chen, and Fang Hua. "Artificial intelligence–related dental research: bibliometric and altmetric analysis." International Dental Journal 75, no. 1 (2025): 166-175.
- Loh, Hui Wen, Chui Ping Ooi, Silvia Seoni, Prabal Datta Barua, Filippo Molinari, and U. Rajendra Acharya. "Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011–2022)." Computer methods and programs in biomedicine 226 (2022): 107161.
- Hasnain, Muhammad Adnan, Hassaan Malik, Muhammad Mujtaba Asad, and Fahad Sherwani. "Deep learning architectures in dental diagnostics: a systematic comparison of techniques for accurate prediction of dental disease through x-ray imaging." International Journal of Intelligent Computing and Cybernetics 17, no. 1 (2024): 161-180.
- Walasai, Gordhan Das, Stefano Landini, Muhammad Nawaz Chandio, Abdul Azeem Kumbhar, Shoaib Ali Bhatti, and Sheeraz Ahmed. "Reducing carbon emissions and costs of electricity with solar PV systems in QUEST Nawabshah, Pakistan Administration Building." Journal of Computing & Biomedical Informatics 7, no. 02 (2024).
- Barzas, Konstantinos, Shereen Fouad, Gainer Jasa, and Gabriel Landini. "An explainable deep learning framework for mandibular canal segmentation from cone beam computed tomography volumes." In International Conference on Computational Advances in Bio and Medical Sciences, pp. 1-13. Cham: Springer Nature Switzerland, 2023.
- Yu, Young-Jun. "Machine learning for dental image analysis." arXiv preprint arXiv:1611.09958 (2016).
- Chen, Ting, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. "A simple framework for contrastive learning of visual representations." In International conference on machine learning, PmLR, 2020, 1597-1607.
- Bhattacharjee, Niharika. "Automated dental cavity detection system using deep learning and explainable AI." AMIA Summits on Translational Science Proceedings 2022 (2022): 140.
- Bonny, Talal, Wafaa Al Nassan, Khaled Obaideen, Tamer Rabie, Maryam Nooman AlMallahi, and Swati Gupta. "Primary Methods and Algorithms in Artificial-Intelligence-Based Dental Image Analysis: A Systematic Review." Algorithms 17, no. 12 (2024): 567.
- Ding, Hao, Jiamin Wu, Wuyuan Zhao, Jukka P. Matinlinna, Michael F. Burrow, and James KH Tsoi. "Artificial intelligence in dentistry—A review." Frontiers in Dental Medicine 4 (2023): 1085251.
- Arsiwala-Scheppach, Lubaina T., Akhilanand Chaurasia, Anne Mueller, Joachim Krois, and Falk Schwendicke. "Machine learning in dentistry: a scoping review." Journal of Clinical Medicine 12, no. 3 (2023): 937.
- Talpur, Sarena, Fahad Azim, Munaf Rashid, Sidra Abid Syed, Baby Alisha Talpur, and Saad Jawaid Khan. "Uses of different machine learning algorithms for diagnosis of dental caries." Journal of Healthcare Engineering 2022, no. 1 (2022): 5032435.
- Wang, Cheng, Rongjun Zhang, Xiaoling Wei, Le Wang, Wenqian Xu, and Qi Yao. "Machine learning-based automatic identification and diagnosis of dental caries and calculus using hyperspectral fluorescence imaging." Photodiagnosis and Photodynamic Therapy 41 (2023): 103217.
- Ren, Ruiyang, Haozhe Luo, Chongying Su, Yang Yao, and Wen Liao. "Machine learning in dental, oral and craniofacial imaging: a review of recent progress." PeerJ 9 (2021): e11451.
- Vandenberghe, Bart, Reinhilde Jacobs, and Hilde Bosmans. "Modern dental imaging: a review of the current technology and clinical applications in dental practice." European radiology 20 (2010): 2637-2655.
- Ketenci Çay, Fatmanur, Çağrı Yeşil, Oktay Çay, Büşra Gül Yılmaz, Fatma Hasene Özçini, and Dilhan İlgüy. "DeepLabv3+ method for detecting and segmenting apical lesions on panoramic radiography." Clinical Oral Investigations 29, no. 2 (2025): 101.
- Pauwels, Ruben. "A brief introduction to concepts and applications of artificial intelligence in dental imaging." Oral radiology 37, no. 1 (2021): 153-160.
- Zhou, Bolei, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. "Learning deep features for discriminative localization." In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, 2921-2929.
- Selvaraju, Ramprasaath R., Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. "Grad-CAM: visual explanations from deep networks via gradient-based localization." International journal of computer vision 128 (2020): 336-359.
- Long, Jonathan, Evan Shelhamer, and Trevor Darrell. "Fully convolutional networks for semantic segmentation." In Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, 3431-3440.
- Zhong, Wenjin, XiaoXiao Ren, and HanWen Zhang. "Automatic X-ray teeth segmentation with grouped attention." Scientific Reports 15, no. 1 (2025): 64.