Related Experiment Video
Updated: May 9, 2026
Reliability of Artificial Intelligence-Based Cone Beam Computed Tomography Integration with Digital Dental Images
Published on: February 23, 2024
Comparative diagnostic yield of cone beam CT reconstruction using various software programs on the detection of
S L S Melo1, F Haiter-Neto, L R Correa
1Department of Oral Diagnosis, Piracicaba Dental School, University of Campinas, Piracicaba, São Paulo, Brazil.
Objectives:
To evaluate the effect on diagnostic yield in the detection of experimentally induced vertical root fractures on cone beam CT images using four dental software program.
Methods:
190 single-rooted extracted human teeth were divided into three groups according to the pulp canal status: unrestored (UR), filled with gutta-percha (GP) and restored with a metallic custom post (Post). One-half of the sample of each group was artificially fractured and the segments repositioned. All teeth were scanned on a cone beam CT device at 0.2 mm nominal voxel resolution (i-CAT Platinum; Imaging Sciences International, Hatfield, PA). The data were exported as digital imaging and communications in medicine files and imported into Dolphin Imaging & Management Solutions, v. 11.5 (Patterson Dental Supply Inc., St Paul, MN), InVivoDental, v. 5.0 (Anatomage Inc., San Jose, CA) and Kodak Dental Imaging Software 3D module, v. 2.1.11 (Carestream Health Inc., Rochester, NY) software. Cross-sectional images in the acquisition (using Xoran CAT™, v. 3.0.34 software; Xoran Technologies, Ann Arbor, MI) and additional software were presented to three calibrated oral radiologists who rated the presence or absence of root fracture on a five-point scale. Receiver operating characteristic analysis was performed, and treatment comparisons compared by analysis of variance and pairwise comparisons were performed using Tukey's test at an a priori value of α < 0.05%.
Results:
All dental software performed equally at detecting fractures. Fractures were significantly more difficult to detect when posts were present.
Conclusions:
The diagnosis of root fracture is software-independent. The presence of an intracanal metallic post significantly decreases the detection of artificially created root fractures.
