X2Teeth: 3D Teeth Reconstruction from a Single Panoramic Radiograph

TL;DR

X2Teeth is a novel deep learning approach that reconstructs detailed 3D dental cavity structures from a single panoramic radiograph, addressing a previously unexplored challenge in dental imaging.

Contribution

The paper introduces X2Teeth, a ConvNet that decomposes 3D teeth reconstruction into localization and shape estimation, with a patch-based training strategy for end-to-end learning.

Findings

Achieves a 3D reconstruction IoU of 0.681.

Outperforms encoder-decoder and retrieval-based methods by over 1.5 times.

Successfully reconstructs detailed 3D structures of entire dental cavities.

Abstract

3D teeth reconstruction from X-ray is important for dental diagnosis and many clinical operations. However, no existing work has explored the reconstruction of teeth for a whole cavity from a single panoramic radiograph. Different from single object reconstruction from photos, this task has the unique challenge of constructing multiple objects at high resolutions. To conquer this task, we develop a novel ConvNet X2Teeth that decomposes the task into teeth localization and single-shape estimation. We also introduce a patch-based training strategy, such that X2Teeth can be end-to-end trained for optimal performance. Extensive experiments show that our method can successfully estimate the 3D structure of the cavity and reflect the details for each tooth. Moreover, X2Teeth achieves a reconstruction IoU of 0.681, which significantly outperforms the encoder-decoder method by $1.71X and the retrieval-based method by $1.52X. Our method can also be promising for other multi-anatomy 3D reconstruction tasks.