Artificial Intelligence for Root Canal Orifice Identification Using Dental Operating Microscope Images: A Preliminary...

Area of Science:

• Dentistry
• Artificial Intelligence
• Medical Imaging

Background:

• Accurate identification of root canal orifices is crucial for successful endodontic treatment.
• Traditional methods rely on visual inspection, which can be challenging and time-consuming.
• Advancements in artificial intelligence offer potential for automated and enhanced diagnostic capabilities.

Purpose of the Study:

• To evaluate the diagnostic performance of artificial intelligence (AI) in detecting root canal orifices.
• To assess the accuracy of a YOLO-based convolutional neural network (CNN) using images from a dental operating microscope (DOM).

Main Methods:

• Eighty human maxillary first and second molars were used.
• Root canal orifices were identified under a dental operating microscope (DOM).
• Video recordings were analyzed, with 1527 frames randomly selected and manually labeled for AI training and testing.

Main Results:

• The AI system achieved 91% accuracy in detecting root canal orifices.
• The system correctly identified 502 out of 526 root canal orifices.
• The YOLO-based CNN demonstrated high accuracy and sensitivity.

Conclusions:

• AI, specifically a YOLO-based CNN, shows significant potential for accurate root canal orifice detection from DOM images.
• This technology could enhance diagnostic efficiency and precision in endodontic procedures.
• Further research may validate AI's role in improving endodontic treatment outcomes.