Related Experiment Video
Updated: May 11, 2026
Reliability of Artificial Intelligence-Based Cone Beam Computed Tomography Integration with Digital Dental Images
Published on: February 23, 2024
Prospective evaluation of reliability of cone-beam computed tomography in detecting different position of vibroplasty
C Güldner1, J Heinrichs, R Weiß
1Department of Otorhinolaryngology, Head and Neck Surgery, UKGM, University of Marburg, Marburg, Germany. gueldner@staff.uni-marburg.de
Objectives:
This study had the following objectives: (i) to determine the accuracy of determination of Vibrant Soundbridge position in the spectrum of typically implanted sites in the middle ear, (ii) to assess interobserver agreement between three observers with different levels of radiology experience and (iii) to determine the suitability of cone-beam computed tomography (CT) to be used as the baseline radiological assessment post implantation, confirm ferromagnetic transducer (FMT) position.
Design:
Prospective research study. Using four fresh human cadaveric heads, different types of vibroplasty were performed. After each step, cone-beam CT was performed for each of the four cadaveric heads.
Setting:
University hospital (ENT and Neuroradiology).
Participants:
Four fresh cadaveric heads of human donors were operated and analysed by radiological imaging.
Main Outcome Measures:
There are different ways of coupling an ferromagnetic transducer to the anatomical structures of the middle and inner ear. Possibilities of differentiation between these coupling variants should be presented.
Results:
The individual reconstruction view was significantly different from a standardised view for each observer (observer 1: P = 0.003; observer 2: P = 0.001; observer 3: P = 0.002) for all coupling variants combined as well as for each individual coupling variant (overall correct diagnosis: 100% versus 60%). Regarding the frequency of correct diagnosis, no significant differences were found between the three observers (P > 0.500) for each individual coupling variant as well as for all coupling variants combined. The worst rates of correct diagnosis were found in the standardised view for incus (42%), stapes (0%) and TORP (17%) vibroplasty.
Conclusion:
Cone-beam CT as a radiological control for Vibrant Soundbridge is safe and adequately sensitive and reliable and is therefore suitable for clinical investigation. The position of the ferromagnetic transducer in the middle ear and the presence or absence of an additional coupler could be determined in this study. Therefore, cone-beam-CT is useful for the assessment of device failure when there has been gross displacement of the ferromagnetic transducer (or smaller displacements in case of a baseline postoperative cone-beam CT). Regarding the quality of imaging, cone-beam CT produced accurate results with different observers with widely varying radiological experience.
