@bachelorthesis{nokey,

title = {Aligning MRI and CBCT for advanced TMJ diagnostics: Case series using AI-powered registration in dentistry and orthodontics},

author = {Eduardo Duarte Caleme and Lucia Cevidanes and Claudia Trindade Mattos and Felicia Miranda and Marcela Gurgel and Selene Barone and Alban Gaydamour and Enzo Tulissi and Jeanne Claret and Gaelle Leroux and Alexandre Moro and João Gonçalves and Antônio Ruellas and Marina Morettin Zuperlari and Paulo Zupelari Gonçalves and Nina Hsu and Larry Wolford and Juan Prieto and Jonas Bianchi},

url = {https://www.sciencedirect.com/science/article/pii/S1073874625000611},

doi = {https://doi.org/10.1053/j.sodo.2025.07.001},

issn = {1073-8746},

year  = {2025},

date = {2025-07-11},

journal = {Seminars in Orthodontics},

abstract = {This study demonstrates the functionality and clinical value of magnetic resonance imaging (MRI) to cone-beam computed tomography (CBCT) registration using a new open-source artificial intelligence (AI) model called MR2CBCT. We present five clinical cases in which the AI-based method was used to register CBCT and MRI images. For comparison, manual registration was also performed. Qualitative inspection revealed that manual alignment often showed errors that could compromise diagnostic accuracy. In contrast, the AI-based approach consistently corrected these discrepancies, producing more anatomically coherent fused images to better support clinical decision-making. Our findings highlight MR2CBCT as a reliable and accessible tool for multimodal integration in temporomandibular joint (TMJ) assessment in orthodontics and general dentistry.},

keywords = {CBCT, diagnosis, MRI, orthodontics, TMJ complex visualization},

pubstate = {published},

tppubtype = {bachelorthesis}

}