Related Experiment Video
Updated: Sep 16, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.9K
Automatic Segmentation of the Infraorbital Canal in CBCT Images: Anatomical Structure Recognition Using Artificial
Ismail Gumussoy1, Emre Haylaz1, Suayip Burak Duman2,3
1Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Sakarya University, Sakarya 54050, Turkey.
Diagnostics (Basel, Switzerland)
|July 12, 2025
Summary
This study introduces an AI model for automatically segmenting the infraorbital canal (IOC) in cone-beam computed tomography (CBCT) images. The AI model accurately identifies the IOC, crucial for preventing nerve damage in maxillofacial and dental surgeries.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Medicine
- Anatomical Segmentation
Background:
- The infraorbital canal (IOC) is vital for neurovascular structures in the maxilla.
- Accurate IOC localization is critical for maxillofacial, dental implant, and orbital surgeries to prevent nerve damage and ensure surgical success.
Purpose of the Study:
- To develop and evaluate an artificial intelligence (AI)-based model for automatic segmentation of the infraorbital canal (IOC) in cone-beam computed tomography (CBCT) images.
Main Methods:
- A dataset of 220 CBCT images was utilized, with 110 patients' IOCs labeled using 3D Slicer.
- The nnU-Net v2 architecture was employed for training and testing the AI model.
- Performance was assessed using Dice Coefficient (DC), Intersection over the Union (IoU), F1-score, and 95% Hausdorff distance (95% HD).
Main Results:
- The AI model achieved a Dice Coefficient of 0.7792, IoU of 0.6402, F1-score of 0.787, and 95% HD of 0.7661.
- The area under the receiver operating characteristic curve (AUC) was calculated to be 0.91, indicating high model performance.
- The model demonstrated high precision and accuracy in detecting the infraorbital canal.
Conclusions:
- AI-based automatic segmentation of the IOC in CBCT images is a precise and accurate method.
- This AI approach holds significant potential for reducing surgical risks and improving the safety of critical anatomical structures.
- Accurate IOC identification is paramount for preserving patient function and sensory integrity during surgical procedures.
