Detection of Periapical Lesions on Dental Panoramic Radiographs Based on Artificial Intelligence

Periapical Diseases Clinical Trial

— OPTITOMO  

Official title:

Detection of Periapical Lesions on Dental Panoramic Images Based on Artificial Intelligence Using Cone Beam Computed Tomography

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT05888935
• Other study ID #: 2023-04Obs-CHRMT
• Status: Recruiting
• Start date: October 1, 2022
• Est. completion date: December 1, 2024

Study information

• Verified date: May 2023
• Source: Centre Hospitalier Régional Metz-Thionville
• Contact: Arpiné EL NAR, PhD
• Phone: 0033387557766
• Email: a.elnar[@]chr-metz-thionville.fr
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

Dental periapical damages can have various reasons and is reflected by a radiolucent lesion on complementary imaging: angulated retro-alveolar (RA) radiographs, dental panoramic radiographs, and three-dimensional imaging such as computed tomography (CT) or cone-beam computed tomography (CBCT).

For the radiographic detection of these deep periodontal lesions, the dental panoramic represents a first approach commonly performed with relatively low radiation. The investigation can be followed by retroalveolar radiology imaging that are more localized and more precise. However, using these techniques, the detection rates of these lesions are low (20% and 36% respectively), it is necessary to use three-dimensional tomographic investigation to be more discriminating (69%). The gold standard imaging for detection of these lesions is CBCT followed by retroalveolar radiography (~2x less sensitive than CBCT) and panoramic radiography (~2x less sensitive than RA). Although not a full-thickness radiograph, the dental panoramic has the advantage of being more commonly performed while being less radiating than CBCT and giving a global view of the dental arches on a single image.

The detection of periapical lesions is done after a clinical assessment and a visual appreciation of the complementary examinations.

The aim of this project is to improve the detection of periapical lesions, by developing an algorithm able to identify them on a panoramic dental radiograph. This algorithm is based on a deep learning system trained with reference data including panoramic dental imaging and CBCT with an acquisition interval of less than 3 months. The model is based on a previous work, will improve the quality of the initial data (using CBCT), using innovative artificial intelligence algorithms (transfer learning).

Description:

The final objective of the research is to improve the early diagnosis of periapical lesions, which would allow a better and faster care of these lesions namely at early stages. This represents a major public health interest since these lesions can be responsible for multiple local and regional pathologies (osteomyelitis, cervico-facial cellulitis, thrombophlebitis, cerebral abscesses...) or even more serious general pathologies (cardiac pathologies, cardiovascular diseases, diabetes, renal diseases, tendinopathies...). For certain target groups such as the military and high-level athletes, this research would make it possible to improve the assessment carried out before medical aptitude or club transfer.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 2000
• Est. completion date: December 1, 2024
• Est. primary completion date: December 1, 2024
• Gender: All
• Age group: 18 Years and older

Eligibility

Inclusion Criteria:

• Patients who have had CBCT and panoramic dental imaging with less than 3 months between the two examinations

Exclusion Criteria:

• Patients who refused to participe in the study.

Related Conditions & MeSH terms

• Periapical Diseases

Locations

Country	Name	City	State
France	CHR Metz-Thionville/Hopital de Mercy	Metz

Sponsors (1)

Lead Sponsor	Collaborator
Centre Hospitalier Régional Metz-Thionville

Country where clinical trial is conducted

France, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Artificial Intelligence software performance	measurement of the F1 score. The F1 score is calculated as the harmonic mean of the precision and recall scores.; It ranges from 0-100%, and a higher F1 score denotes a better quality classifier.	2 years
Secondary	Artificial Intelligence software specificity	measurement of the true positives, true negatives, false positives, false negatives	2 years