To evaluate and compare the performance of AI algorithms in detecting dental pathologies and anomalies across different types of dental radiographs (including panoramic, bitewing, periapical, and CBCT) as well as dental photographs
Conditions
Interventions
This results in a total of 6,000 radiographs and 6,000 photographs across all studied conditions. The types of radiographs used in the study include bitewing, periapical, panoramic, or CBCT, selected
Diagnostic
Sponsors
Chulalongkorn University
Eligibility
Sex/Gender
All
Inclusion criteria
Inclusion criteria: 1. Images acquired according to standard institutional protocols, covering a wide range of dental pathologies and anomalies: 1) dental caries, 2) impacted teeth, 3) alveolar bone loss/periodontal diseases, 4) missing/extra teeth, 5) dental tumors/cysts/cancer, and 6) dental age calculation. Factors affecting image visibility will be either included or controlled. For example, radiographs from different manufacturers, models, and machines, with varying patient positioning, exposure factors, and image enhancement filters, will be enlisted and standardized. This variability is intended to improve the model's robustness in handling imaging equipment differences commonly encountered in clinical practice. 2. Intraoral radiographs will focus strictly on structures within the oral cavity, minimizing any extraoral details to ensure clarity, relevance, and the anonymity of patients in the region of interest. 3. Clear intraoral photographs, taken from three perspectives: a frontal view at maximum intercuspal position and two occlusal views.
Exclusion criteria
Exclusion criteria: 1. Non-diagnostic quality radiographs and sub-standard photographs, such as overexposed, underexposed, distorted, or blurred images. 2. Images with conditions that obscure the region of interest, such as existing pathology or a history of surgery or physical treatment in the area. 3. Since AI models can be developed as sub-models and then merged to fulfill all research objectives, images and radiographs used in this study may be collected from different patients. This independent data collection method offers the advantage of reducing unnecessary radiation exposure for patients who lack a clinical indication for radiographic imaging.
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| Radiographs at 12 months after end of the intervention Oral Panoramic X-ray Imaging Assisted Diagnosis Software | — |
Secondary
| Measure | Time frame |
|---|---|
| N/A N/A N/A | — |
Countries
Thailand
Contacts
Public ContactThantrira Porntaveetus
Faculty of Dentistry, Chulalongkorn University
Outcome results
None listed