Related Experiment Video
Updated: Dec 25, 2025
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
1.3K
Deep Learning Method for Mandibular Canal Segmentation in Dental Cone Beam Computed Tomography Volumes
Joel Jaskari1, Jaakko Sahlsten1, Jorma Järnstedt2
1Aalto University School of Science, 00076, Aalto, Finland.
Scientific Reports
|April 5, 2020
Summary
A new deep learning system accurately locates mandibular canals in 3D CT scans for dental implantology. This automated approach significantly reduces manual effort in identifying the mandibular nerve canal, improving safety and efficiency.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oral and Maxillofacial Surgery
Background:
- Accurate localization of mandibular canals is crucial in dental implantology to prevent damage to the mandibular nerve.
- Current manual identification of mandibular canals from 3D CT images is labor-intensive and requires expert interpretation.
Purpose of the Study:
- To develop and evaluate a deep learning system for automatic mandibular canal localization.
- To assess the accuracy of the deep learning model in identifying mandibular canals on cone beam CT (CBCT) volumes.
Main Methods:
- A fully convolutional neural network segmentation model was applied to a diverse dataset of 637 CBCT volumes.
- The model was trained on coarsely annotated mandibular canals and evaluated on a dataset of 15 volumes with precise voxel-level annotations.
Main Results:
- The deep learning model achieved high accuracy in localizing mandibular canals, with a mean curve distance of 0.56 mm and an average symmetric surface distance of 0.45 mm.
- The model demonstrated excellent performance on the voxel-level annotated dataset, validating its effectiveness.
Conclusions:
- Deep learning offers a highly accurate and automated solution for mandibular canal localization in dental implantology.
- Integration of this technology can significantly reduce manual annotation workload and enhance the safety and efficiency of dental implant procedures.
