Difficulty analysis of mandibular third molars using deep-learning model | |
| Author | Raknatee Chokluechai |
| Call Number | AIT Thesis no.DSAI-24-10 |
| Subject(s) | Molar, Third--surgery--Analysis Teeth Diseases--Diagnosis--Data processing Deep learning (Machine learning) |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Data Science and Artificial Intelligence |
| Publisher | Asian Institute of Technology |
| Abstract | This study investigates the usage of convolutional neural networks (CNNs) to automate the classification o fmandibular third molar impaction difficulty, traditionally assessed using Pell and Gregory’s and Winter’s classifications.The research aims to improve efficiency in dental dianostics by leveraging deep learning to analyze panoramic radio-graphs for surgical planning.A private dataset was created,and various CNN architectures, including AlexNet,ResNet18,ResNet50, and VGG16,were evaluated for their effectiveness in this task. Data augmentation tecniques such as brightness adjustment and Gaussian blur were found to enhance model performance significantly. the findings suggest that while VGG16 outperformed other models, the application of deep learning in this domain is not yet ready for widespread clinical use but shows promising potential for future developments. The study highlights the importance of considering additional anatomical features likethe inferior alveolar nerve in conjunction with traditional classifications to enhance prediction accuracy.Future research directions include exploring more advanced deep learning architectures and improving dataset size and balance to achieve more robust results. |
| Year | 2024 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Data Science and Artificial Intelligence (DSAI) |
| Chairperson(s) | Chaklam Silpasuwanchai |
| Examination Committee(s) | Attaphongse Taparugssanagorn;Chantri Polprasert |
| Scholarship Donor(s) | AIT Scholarship |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2024 |