# Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans arXiv: https://arxiv.org/abs/2109.11941 · HTML: https://mlsanity.com/paper/2109.11941/ ## Key facts - Cited by 24 papers in the map (data through 14 Oct 2026). - Builds on 10 of its 41 references that are in the map. - First posted on arXiv 24 Sep 2021. ## Builds on (most cited first, 10 of 10) - [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017) - [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016) - [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018) - [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019) - [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018) - [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017) - [Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning](https://mlsanity.com/paper/1807.03146/) (2018) - [Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization](https://mlsanity.com/paper/1908.00748/) (2019) - [Flowing ConvNets for Human Pose Estimation in Videos](https://mlsanity.com/paper/1506.02897/) (2015) - [Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets](https://mlsanity.com/paper/2003.07619/) (2020) ## Built on by (most cited first, 24 of 24) - [3DTeethSeg'22: 3D Teeth Scan Segmentation and Labeling Challenge](https://mlsanity.com/paper/2305.18277/) (2023) - [DentVLM: A Multimodal Vision-Language Model for Comprehensive Dental Diagnosis and Enhanced Clinical Practice](https://mlsanity.com/paper/2509.23344/) (2025) - [3D Dental Model Segmentation with Geometrical Boundary Preserving](https://mlsanity.com/paper/2503.23702/) (2025) - [Is in-domain data beneficial in transfer learning for landmarks detection in x-ray images?](https://mlsanity.com/paper/2403.01470/) (2024) - [Fully automated landmarking and facial segmentation on 3D photographs](https://mlsanity.com/paper/2309.10472/) (2023) - [nnLandmark: A Self-Configuring Method for 3D Medical Landmark Detection](https://mlsanity.com/paper/2504.06742/) (2025) - [3D-U-SAM Network For Few-shot Tooth Segmentation in CBCT Images](https://mlsanity.com/paper/2309.11015/) (2023) - [AI-Enhanced Virtual Reality in Medicine: A Comprehensive Survey](https://mlsanity.com/paper/2402.03093/) (2024) - [Leveraging Point Transformers for Detecting Anatomical Landmarks in Digital Dentistry](https://mlsanity.com/paper/2504.11418/) (2025) - [ArchMap: Arch-Flattening and Knowledge-Guided Vision Language Model for Tooth Counting and Structured Dental Understanding](https://mlsanity.com/paper/2511.14336/) (2025) - [Sparse Anatomical Prompt Semi-Supervised Learning with Masked Image Modeling for CBCT Tooth Segmentation](https://mlsanity.com/paper/2402.04587/) (2024) - [CHaRM: Conditioned Heatmap Regression Methodology for Accurate and Fast Dental Landmark Localization](https://mlsanity.com/paper/2501.13073/) (2025) - [3DTeethSAM: Taming SAM2 for 3D Teeth Segmentation](https://mlsanity.com/paper/2512.11557/) (2025) - [Aortic root landmark localization with optimal transport loss for heatmap regression](https://mlsanity.com/paper/2407.04921/) (2024) - [Transformer-Based Tooth Alignment Prediction With Occlusion And Collision Constraints](https://mlsanity.com/paper/2410.20806/) (2024) - [Evaluating the Suitability of Different Intraoral Scan Resolutions for Deep Learning-Based Tooth Segmentation](https://mlsanity.com/paper/2502.19515/) (2025) - [Detecting Dental Landmarks from Intraoral 3D Scans: the 3DTeethLand challenge](https://mlsanity.com/paper/2512.08323/) (2025) - [SOFTooth: Semantics-Enhanced Order-Aware Fusion for Tooth Instance Segmentation](https://mlsanity.com/paper/2512.23411/) (2025) - [OrthoAI v2: From Single-Agent Segmentation to Dual-Agent Treatment Planning for Clear Aligners](https://mlsanity.com/paper/2603.15663/) (2026) - [TCATSeg: A Tooth Center-Wise Attention Network for 3D Dental Model Semantic Segmentation](https://mlsanity.com/paper/2603.16620/) (2026) - [Text-Conditioned Multi-Expert Regression Framework for Fully Automated Multi-Abutment Design](https://mlsanity.com/paper/2604.09047/) (2026) - [3D Geometric Tooth Alignment Planning via Deep Reinforcement Learning](https://mlsanity.com/paper/2607.14544/) (2026) - [B-Spline Embedded Structure Learning for 3D Tooth Segmentation](https://mlsanity.com/paper/2608.17291/) (2026) - [Anatomy-preserving unpaired cone-beam CT refinement for image-guided radiotherapy using pseudo-label guided diffusion](https://mlsanity.com/paper/2610.06094/) (2026) ## Abstract (arXiv) Accurately segmenting teeth and identifying the corresponding anatomical landmarks on dental mesh models are essential in computer-aided orthodontic treatment. Manually performing these two tasks is time-consuming, tedious, and, more importantly, highly dependent on orthodontists' experiences due to the abnormality and large-scale variance of patients' teeth. Some machine learning-based methods have been designed and applied in the orthodontic field to automatically segment dental meshes (e.g., intraoral scans). In contrast, the number of studies on tooth landmark localization is still limited. This paper proposes a two-stage framework based on mesh deep learning (called TS-MDL) for joint tooth labeling and landmark identification on raw intraoral scans. Our TS-MDL first adopts an end-to-end iMeshSegNet method (i.e., a variant of the existing MeshSegNet with both improved accuracy and efficiency) to label each tooth on the downsampled scan. Guided by the segmentation outputs, our TS-MDL further selects each tooth's region of interest (ROI) on the original mesh to construct a light-weight variant of the pioneering PointNet (i.e., PointNet-Reg) for regressing the corresponding landmark heatmaps. Our TS-MDL was evaluated on a real-clinical dataset, showing promising segmentation and localization performance. Specifically, iMeshSegNet in the first stage of TS-MDL reached an averaged Dice similarity coefficient (DSC) at textcolor[rgb]0,0,00.964±0.054, significantly outperforming the original MeshSegNet. In the second stage, PointNet-Reg achieved a mean absolute error (MAE) of 0.597±0.761 , mm in distances between the prediction and ground truth for 66 landmarks, which is superior compared with other networks for landmark detection. All these results suggest the potential usage of our TS-MDL in orthodontics.