Related Experiment Video
Updated: Jul 16, 2026
06:45
Automated Joint Space Detection Improves Bone Segmentation Accuracy
Published on: November 28, 2025
Automatic segmentation of jaw tissues in CT using active appearance models and semi-automatic landmarking
Sylvia Rueda1, José Antonio Gil, Raphaël Pichery
1Medical Image Computing Laboratory, Universidad Politécnica de Valencia, UPV/ETSIA, Camino de Vera s/n, 46022 Valencia, Spain. silruelo@degi.upv.es
Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|March 16, 2007
Summary
This study introduces an automated system using Active Appearance Models (AAMs) for segmenting jaw tissues in CT scans, crucial for precise oral implant surgery and avoiding nerve damage.
Area of Science:
- Medical Imaging
- Computer-Aided Surgery
- Biomedical Engineering
Background:
- Preoperative planning is vital for oral implant surgery to assess bone quality and avoid critical structures.
- Current methods often require manual initialization and lack full automation for jaw tissue segmentation.
Purpose of the Study:
- To develop a fully automated system for segmenting jaw tissues, including cortical bone, trabecular core, and the mandibular canal with the dental nerve, on CT images.
- To improve the precision and efficiency of preoperative planning for dental implant placement.
Main Methods:
- An automated segmentation system utilizing Active Appearance Models (AAMs) was developed.
- A semi-automatic landmarking process was employed for AAM model creation.
- The AAM was trained on 215 images and validated using a leave-4-out cross-validation scheme.
Main Results:
- The automated system achieved an initialization error of 3.25%.
- Mean segmentation errors were 1.63mm (cortical bone), 2.90mm (trabecular core), 4.76mm (mandibular canal), and 3.40mm (dental nerve).
Conclusions:
- The proposed AAM-based system offers a significant advancement in automated jaw tissue segmentation for preoperative planning.
- This technology can enhance surgical accuracy and patient safety by precisely identifying critical anatomical structures like the dental nerve.
