Artificial intelligence-based incisive canal visualization for preventing and detecting post-implant injury, using...

Area of Science:

• Dentistry
• Medical Imaging
• Artificial Intelligence

Background:

• Iatrogenic nerve injuries are a risk during dental implant surgery.
• Accurate visualization of the mandibular incisive canal (MIC) is crucial for prevention.

Purpose of the Study:

• To clinically validate an AI tool for automatic MIC segmentation on CBCT.
• To assess the tool's impact on nerve injury prevention and detection.

Main Methods:

• AI-based segmentation of MIC on CBCT scans.
• Comparison of AI-segmented canals with CBCT images by radiologists.
• Observer assessment of canal identification and injury detection with confidence levels.

Main Results:

• AI tool enabled clear visualization of bilateral MIC on pre- and postoperative CBCT.
• Significantly improved incisive canal detection (25%) and observer confidence (8%) for preoperative assessment.
• AI tool demonstrated clinical utility in visualizing MIC and improving expert confidence.

Conclusions:

• The AI-based tool is clinically useful for bilateral MIC visualization on CBCT.
• AI-driven segmentation and 3D modeling enhance preoperative canal detection and expert confidence.
• This technology aids in preventing iatrogenic implant-related nerve injuries.