Panoramic Radiograph
Panoramic radiographs (orthopantomograms) are 2D X-ray images of the entire mouth, crucial for dental diagnosis and treatment planning. Current research focuses on leveraging deep learning, particularly convolutional neural networks (like U-Net, ResUNet++, and Vision Transformers) and detection transformers (DETR), to automate tasks such as teeth detection, segmentation, numbering, and disease identification. These advancements aim to improve diagnostic accuracy, efficiency, and accessibility in dental practice, with studies demonstrating performance comparable to junior specialists in certain tasks. Furthermore, research is exploring 3D reconstruction techniques from these 2D images using neural implicit functions and other innovative approaches to provide more comprehensive spatial information.