Show abstract - PDF - Reviews

Automated dental diagnosis requires accurate segmentation of tooth from cone-beam computed tomography (CBCT) images. However, existing segmentation methods often neglect incorporating prior information and symptoms of tooth, which can cause unsatisfactory segmentation performance on tooth with symptoms. To this respect, we propose Tooth Symptom Network (TSNet), consisting of Dental Prior Guiding Data Augmentation (DPGDA) and Dental Symptom Shape Loss (DSSL), to improve segmentation performance for tooth with different clinical symptoms. Experiments show that TSNet outperforms all state-of-the-art methods across datasets with all kinds of symptoms with an average increase of 1.13\% in Dice and 2.00\% in IoU.
Hide abstract