Geometric-Guided Few-Shot Dental Landmark Detection with Human-Centric Foundation Model

• URL: http://arxiv.org/abs/2507.04710v1
• Date: Mon, 07 Jul 2025 07:01:44 GMT
• Title: Geometric-Guided Few-Shot Dental Landmark Detection with Human-Centric Foundation Model
• Abstract summary: We introduce GeoSapiens, a novel few-shot learning framework designed for robust dental landmark detection using limited annotated CBCT of anterior teeth.<n>Experiments conducted on our collected dataset of teeth landmarks revealed that GeoSapiens surpassed existing landmark detection methods.
• Score: 6.016276428517095
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate detection of anatomic landmarks is essential for assessing alveolar bone and root conditions, thereby optimizing clinical outcomes in orthodontics, periodontics, and implant dentistry. Manual annotation of landmarks on cone-beam computed tomography (CBCT) by dentists is time-consuming, labor-intensive, and subject to inter-observer variability. Deep learning-based automated methods present a promising approach to streamline this process efficiently. However, the scarcity of training data and the high cost of expert annotations hinder the adoption of conventional deep learning techniques. To overcome these challenges, we introduce GeoSapiens, a novel few-shot learning framework designed for robust dental landmark detection using limited annotated CBCT of anterior teeth. Our GeoSapiens framework comprises two key components: (1) a robust baseline adapted from Sapiens, a foundational model that has achieved state-of-the-art performance in human-centric vision tasks, and (2) a novel geometric loss function that improves the model's capacity to capture critical geometric relationships among anatomical structures. Experiments conducted on our collected dataset of anterior teeth landmarks revealed that GeoSapiens surpassed existing landmark detection methods, outperforming the leading approach by an 8.18% higher success detection rate at a strict 0.5 mm threshold-a standard widely recognized in dental diagnostics. Code is available at: https://github.com/xmed-lab/GeoSapiens.

Related papers

• Caries DETR: Tooth Structure-aware Prior and Lesion-aware Dynamic Loss Refinement for DETR Based Caries Detection [38.87257255907775]
  We propose Caries-DETR, a specialized Transformer framework for caries detection in intraoral images.<n>A Tooth Structure-aware Query Initialization (TSQI) is designed, leveraging large-scale intraoral photograph pre-training.<n>We also design a Lesion-aware Dynamic Loss Refinement (LDLR) to implement quality-driven hard mining.
  arXiv  Detail & Related papers  (2026-04-26T14:02:41Z)
• Adapting Foundation Model for Dental Caries Detection with Dual-View Co-Training [53.77904429789069]
  We present Attention-TNet, a novel Dual-View Co-Training network for accurate dental caries detection.<n>OurTNet starts with employing automated tooth detection to establish two complementary views: a global view from panoramic X-ray images and a local view from cropped tooth images.<n>To effectively integrate information from both views, we introduce a Gated Cross-View module.
  arXiv  Detail & Related papers  (2025-08-28T14:13:26Z)
• GEPAR3D: Geometry Prior-Assisted Learning for 3D Tooth Segmentation [0.15487122608774898]
  Tooth segmentation in Cone-Beam Computed Tomography (CBCT) remains challenging.<n>We introduce GEPAR3D, a novel approach that unifies instance detection and multi-class segmentation into a single step to improve root segmentation.<n>We leverage a deep watershed method, modeling each tooth as a continuous 3D energy basin encoding voxel distances to boundaries.
  arXiv  Detail & Related papers  (2025-07-31T20:46:58Z)
• Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography: The AortaSeg24 Challenge [55.252714550918824]
  AortaSeg24 MICCAI Challenge introduced the first dataset of 100 CTA volumes annotated for 23 clinically relevant aortic branches and zones.<n>This paper presents the challenge design, dataset details, evaluation metrics, and an in-depth analysis of the top-performing algorithms.
  arXiv  Detail & Related papers  (2025-02-07T21:09:05Z)
• Benchmarking Pretrained Attention-based Models for Real-Time Recognition in Robot-Assisted Esophagectomy [2.847280871973632]
  Esophageal cancer is among the most common types of cancer worldwide.<n>In recent years, robot-assisted minimally invasive esophagectomy has emerged as a promising alternative.<n>Computer-aided anatomy recognition holds promise for improving surgical navigation.
  arXiv  Detail & Related papers  (2024-12-04T15:32:37Z)
• Transformer-Based Tooth Alignment Prediction With Occlusion And Collision Constraints [3.5034434329837563]
  We propose a lightweight tooth alignment neural network based on Swin-transformer. We first re-organized 3D point clouds based on virtual arch lines and converted them into order-sorted multi-channel textures. We then designed two new occlusal loss functions that quantitatively evaluate the occlusal relationship between the upper and lower jaws.
  arXiv  Detail & Related papers  (2024-10-28T07:54:07Z)
• OralBBNet: Spatially Guided Dental Segmentation of Panoramic X-Rays with Bounding Box Priors [34.82692226532414]
  OralBBNet is designed to improve the accuracy and robustness of tooth classification and segmentation on panoramic X-rays.<n>Our approach achieved a 1-3% improvement in mean average precision (mAP) for tooth detection compared to existing techniques.<n>Results of this study establish a foundation for the wider implementation of object detection models in dental diagnostics.
  arXiv  Detail & Related papers  (2024-06-06T04:57:29Z)
• A Deep Learning Approach to Teeth Segmentation and Orientation from Panoramic X-rays [1.7366868394060984]
  We present a comprehensive approach to teeth segmentation and orientation from panoramic X-ray images, leveraging deep learning techniques. We build our model based on FUSegNet, a popular model originally developed for wound segmentation. We introduce oriented bounding box (OBB) generation through principal component analysis (PCA) for precise tooth orientation estimation.
  arXiv  Detail & Related papers  (2023-10-26T06:01:25Z)
• Revisiting Computer-Aided Tuberculosis Diagnosis [56.80999479735375]
  Tuberculosis (TB) is a major global health threat, causing millions of deaths annually. Computer-aided tuberculosis diagnosis (CTD) using deep learning has shown promise, but progress is hindered by limited training data. We establish a large-scale dataset, namely the Tuberculosis X-ray (TBX11K) dataset, which contains 11,200 chest X-ray (CXR) images with corresponding bounding box annotations for TB areas. This dataset enables the training of sophisticated detectors for high-quality CTD.
  arXiv  Detail & Related papers  (2023-07-06T08:27:48Z)
• Orientation-Shared Convolution Representation for CT Metal Artifact Learning [63.67718355820655]
  During X-ray computed tomography (CT) scanning, metallic implants carrying with patients often lead to adverse artifacts. Existing deep-learning-based methods have gained promising reconstruction performance. We propose an orientation-shared convolution representation strategy to adapt the physical prior structures of artifacts.
  arXiv  Detail & Related papers  (2022-12-26T13:56:12Z)
• Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network [51.44506007844284]
  We propose a shape-aware relation network for accurate and real-time landmark detection in endoscopic submucosal dissection surgery. We first devise an algorithm to automatically generate relation keypoint heatmaps, which intuitively represent the prior knowledge of spatial relations among landmarks. We then develop two complementary regularization schemes to progressively incorporate the prior knowledge into the training process.
  arXiv  Detail & Related papers  (2021-11-08T07:57:30Z)
• Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans [56.55092443401416]
  emphiMeshSegNet in the first stage of TS-MDL reached an averaged Dice similarity coefficient (DSC) at 0.953pm0.076$, significantly outperforming the original MeshSegNet. PointNet-Reg achieved a mean absolute error (MAE) of $0.623pm0.718, mm$ in distances between the prediction and ground truth for $44$ landmarks, which is superior compared with other networks for landmark detection.
  arXiv  Detail & Related papers  (2021-09-24T13:00:26Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.