Self-Supervised Learning with Masked Image Modeling for Teeth Numbering, Detection of Dental Restorations, and Instance Segmentation in Dental Panoramic Radiographs
This work addresses the challenge of automating dental radiographic interpretation for dental care, but it is incremental as it applies existing self-supervised methods to a new domain.
This study tackled the problem of limited training data for deep learning in dental panoramic radiographs by applying self-supervised learning methods like SimMIM and UM-MAE to a Swin Transformer, achieving performance improvements such as 90.4% and 88.9% on detection and segmentation tasks, with average precision increases of 13.4 and 12.8 over a baseline.
The computer-assisted radiologic informative report is currently emerging in dental practice to facilitate dental care and reduce time consumption in manual panoramic radiographic interpretation. However, the amount of dental radiographs for training is very limited, particularly from the point of view of deep learning. This study aims to utilize recent self-supervised learning methods like SimMIM and UM-MAE to increase the model efficiency and understanding of the limited number of dental radiographs. We use the Swin Transformer for teeth numbering, detection of dental restorations, and instance segmentation tasks. To the best of our knowledge, this is the first study that applied self-supervised learning methods to Swin Transformer on dental panoramic radiographs. Our results show that the SimMIM method obtained the highest performance of 90.4% and 88.9% on detecting teeth and dental restorations and instance segmentation, respectively, increasing the average precision by 13.4 and 12.8 over the random initialization baseline. Moreover, we augment and correct the existing dataset of panoramic radiographs. The code and the dataset are available at https://github.com/AmaniHAlmalki/DentalMIM.