Tundra Space

Tundra Space

Clinical Research Directory

Browse clinical research sites, groups, and studies.

Back to Studies
NOT YET RECRUITING
NCT06450938
NA

No Code Artificial Intelligence to Detect Radiographic Features Associated With Unsatisfactory Endodontic Treatment

Sponsor: University of Copenhagen

View on ClinicalTrials.gov

Summary

Developing neural network-based models for image analysis can be time-consuming, requiring dataset design and model training. No-code AI platforms allow users to annotate object features without coding. Corrective annotation, a "human-in-the-loop" approach, refines AI segmentations iteratively. Dentistry has seen success with no-code AI for segmenting dental restorations. This study aims to assess radiographic features related to root canal treatment quality using a "human-in-the-loop" approach.

Official title: Implementing a Corrective Annotation No Code Artificial Intelligence-based Software to Detect Several Radiographic Features Associated With Unsatisfactory Endodontic Treatment: A Randomized Controlled Trial

Key Details

Gender

All

Age Range

20 Years - 40 Years

Study Type

INTERVENTIONAL

Enrollment

80

Start Date

2024-07-30

Completion Date

2024-12-13

Last Updated

2024-06-25

Healthy Volunteers

Yes

Interventions

DEVICE

AI guidance for finding radiographic features

A secured website was made for the trial in which each student could log in using the assigned number. All the image datasets were uploaded to this website. The students will be randomly assigned to the experiment and control group. Both students were asked to segment the features associated with the quality of root canal treatment and predict the prognosis of treatment while the experiment group had access to AI guidance and the control group didn't.