Related Experiment Video
Updated: Apr 12, 2026
05:54
Real-Time Dynamic Navigation System for the Precise Quad-Zygomatic Implant Placement in a Patient with a Severely Atrophic Maxilla
Published on: October 18, 2021
2.4K
Developing an Artificial Intelligence Solution to Autosegment the Edentulous Maxillary Bone for Implant Planning.
Mohammad-Adel Moufti1,2, Tharwat Alhalabieh1, Kawthar Mohammad1
1College of Dental Medicine, University of Sharjah, Sharjah, United Arab Emirates.
European Journal of Dentistry
|April 10, 2026
Summary
Artificial intelligence (AI) can automate dental implant planning by segmenting edentulous maxillary ridges. A deep learning model achieved moderate-to-high accuracy, showing potential to improve efficiency and outcomes in digital implant workflows.
Area of Science:
- Dentistry
- Medical Imaging
- Artificial Intelligence
Background:
- Digital dental implant planning using cone beam computed tomography (CBCT) is time-consuming and error-prone.
- Artificial intelligence (AI) offers automation potential for image analysis in dentistry.
- Automating segmentation of edentulous maxillary ridges can support implant planning.
Purpose of the Study:
- To develop a deep learning system for segmenting edentulous maxillary ridges.
- To support automated digital dental implant planning.
- To evaluate the accuracy of the AI model in segmenting maxillary edentulous spaces.
Main Methods:
- A convolutional neural network (CNN) based on the U-Net architecture was developed using the Medical Open Network for AI (MONAI) framework.
- Seventy-seven CBCT scans were used, with manual segmentation performed using 3D Slicer software.
- The dataset was split into training (90%) and testing (10%) sets, and model performance was evaluated using the Dice Similarity Coefficient (DSC).
Main Results:
- The AI model achieved a mean Dice Similarity Coefficient (DSC) of 76.57% in segmenting maxillary edentulous spaces.
- Discrepancies were noted due to manual annotation choices regarding narrow bone regions and irregular sinus floors.
- The AI model demonstrated greater anatomical precision in several instances compared to manual segmentation.
Conclusions:
- The developed AI model shows moderate-to-high accuracy for segmenting maxillary edentulous spaces.
- Refined datasets and labelling protocols can further enhance this AI approach.
- This AI-driven segmentation has strong potential to streamline digital implant planning and improve clinical outcomes.
