Aligning MRI and CBCT for Advanced TMJ Diagnostics: Case Series Using AI-Powered Registration in Dentistry and...

Area of Science:

• Medical Imaging
• Artificial Intelligence in Medicine
• Dental Diagnostics

Background:

• Accurate image registration is crucial for multimodal imaging in dentistry.
• Manual registration methods can introduce diagnostic errors.
• Open-source AI solutions offer potential for improved clinical workflows.

Purpose of the Study:

• To evaluate the functionality and clinical value of the MR2CBCT AI model for MRI-to-CBCT registration.
• To compare AI-based registration with manual registration in clinical cases.
• To assess the impact of AI registration on diagnostic accuracy and clinical decision-making.

Main Methods:

• Development and application of the open-source MR2CBCT AI model.
• Registration of MRI and CBCT images in five clinical temporomandibular joint (TMJ) cases.
• Comparative analysis of AI-based registration versus manual registration.

Main Results:

• The MR2CBCT AI model demonstrated effective registration of MRI and CBCT images.
• AI-based registration corrected discrepancies often found in manual alignments.
• Fused images generated by the AI approach were more anatomically coherent.

Conclusions:

• MR2CBCT is a reliable and accessible tool for multimodal image integration.
• AI-based registration enhances diagnostic accuracy in TMJ assessment.
• This technology supports improved clinical decision-making in orthodontics and general dentistry.