# Coarse-to-fine volumetric segmentation of teeth in Cone-Beam CT

arXiv: https://arxiv.org/abs/1810.10293 · HTML: https://mlsanity.com/paper/1810.10293/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2018.

## Built on by (most cited first, 4 of 4)

- [Towards automated brain aneurysm detection in TOF-MRA: open data, weak labels, and anatomical knowledge](https://mlsanity.com/paper/2103.06168/) (2021)
- [Convolutional Neural Networks in Orthodontics: a review](https://mlsanity.com/paper/2104.08886/) (2021)
- [Weakly Supervised Learning with Automated Labels from Radiology Reports for Glioma Change Detection](https://mlsanity.com/paper/2210.09698/) (2022)
- [Topology of a Smile: Persistent Homology in Dental Imaging](https://mlsanity.com/paper/2608.21422/) (2026)

## Abstract (arXiv)

We consider the problem of localizing and segmenting individual teeth inside 3D Cone-Beam Computed Tomography (CBCT) images. To handle large image sizes we approach this task with a coarse-to-fine framework, where the whole volume is first analyzed as a 33-class semantic segmentation (adults have up to 32 teeth) in coarse resolution, followed by binary semantic segmentation of the cropped region of interest in original resolution. To improve the performance of the challenging 33-class segmentation, we first train the Coarse step model on a large weakly labeled dataset, then fine-tune it on a smaller precisely labeled dataset. The Fine step model is trained with precise labels only. Experiments using our in-house dataset show significant improvement for both weakly-supervised pretraining and for the addition of the Fine step. Empirically, this framework yields precise teeth masks with low localization errors sufficient for many real-world applications.