Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
This observational study aims to develop and assess the accuracy, specificity, and sensitivity of a deep learning model for the classification of periodontitis using panoramic radiographs and clinical data inputs. A total of 341 panoramic images will be retrospectively collected and labeled by experienced periodontists to train and test the model. The model will be evaluated for its ability to determine the stage and grade of periodontitis based on the 2017 classification guidelines set by the American Academy of Periodontology. The results will be compared to those of clinical experts to validate the AI-assisted diagnostic system. This study is conducted at the Faculty of Dentistry, Ain Shams University, in fulfillment of a Master's degree in Periodontology.
a convolutional neural network (CNN)-based deep learning model will be trained using 341 panoramic radiographs and relevant clinical data to classify patients according to stage and grade of periodontitis. Images will be obtained from the Oral and Maxillofacial Radiology Department at Ain Shams University. The inclusion criteria includes radiographs of patients with periodontal bone loss and radiographs of patients with orthodontic brackets, mixed dentition, and artifacts will be excluded. Clinical data, including age, diabetes status, and smoking history, will be incorporated to calculate grading using the bone loss/age ratio of the testing set.
The collected dataset will be divided into 80% for training and 20% for testing. Six anatomical landmarks will be annotated per tooth to calculate the percentage of bone loss mesially and distally, which will be used to determine the stage of disease. Grading will be determined based on percentage bone loss relative to patient age and systemic modifiers. Expert-labeled datasets will serve as a reference standard for evaluating the performance of the AI model.
The primary objective is to evaluate the model's diagnostic accuracy for staging and grading compared to specialist assessments. The secondary objective is to measure the sensitivity and specificity of the model.
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Periodontitis Patients: Model's Testing Set | This cohort includes 47 patients diagnosed with different stages and grades of periodontitis. Each participant underwent clinical examination and panoramic radiography. Their images and clinical data were used to validate the performance of a deep learning model developed to classify periodontal staging and grading according to the 2017 classification by the American Academy of Periodontology. No intervention was administered; the study is observational and retrospective in design. |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Artificial Intelligence-Assisted Staging and Grading for Diagnosis of Periodontitis | Diagnostic Test | A deep learning diagnostic model (using DenseNet and VGG16 architectures) was applied to panoramic radiographs of 47 patients to classify the stage and grade of periodontitis. The model was trained on an external dataset and validated against expert-labeled outcomes. The purpose was to assess the accuracy of AI in replicating clinician-level diagnosis based on the 2017 classification system of periodontitis. |
| Measure | Description | Time Frame |
|---|---|---|
| Establishment of an AI model for calculating periodontal bone loss (%) and assigning stage and grade of periodontitis using 2017 classification | Development of a machine learning model using retrospectively collected panoramic radiographs to calculate the percentage of periodontal bone loss (PBL) for each tooth and assign a stage (I-IV) and grade (A-C) of periodontitis according to the 2017 World Workshop classification of Periodontal and Peri-implant Diseases. The outcome will be reported as the accuracy percentage in which the model successfully provides both a PBL calculation and a corresponding stage and grade classification without processing errors. | 10 months |
| Measure | Description | Time Frame |
|---|---|---|
| Diagnostic performance of the AI model compared to specialist diagnosis (accuracy, sensitivity, specificity) | Evaluation of the AI model's diagnostic performance in a testing set of 47 patients whose diagnoses (stage and grade of periodontitis) have been established by two experienced periodontists using combined clinical and radiographic data. The AI model's predictions will be compared with the specialists' consensus diagnosis, and accuracy, sensitivity, and specificity will be calculated as percentages. Results will be aggregated for the overall classification and reported as summary statistics. |
Not provided
Inclusion Criteria:
Exclusion Criteria:
x-ray images with
Not provided
Not provided
Not provided
A total of 47 adult patients diagnosed with periodontitis based on clinical and radiographic criteria were included. All participants were recruited from the outpatient clinics of the Periodontology Department at Ain Shams University. The population consisted of individuals with different stages and grades of periodontitis, providing a diverse testing sample for AI diagnostic validation.
Not provided
Not provided
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Ain Shams University | Cairo | Egypt |
Not provided
| ID | Term |
|---|---|
| D010518 | Periodontitis |
| ID | Term |
|---|---|
| D010510 | Periodontal Diseases |
| D009059 | Mouth Diseases |
| D009057 | Stomatognathic Diseases |
Not provided
Not provided
Not provided
Not provided
Not provided
|
| 3 months |