Assessing the Precision of Convolutional Neural Networks... | NCT05901857

Studies
Assessing the Precision of Convolutional Neural Networks for Dental Age Estimation From Panoramic Radiographs

NCT05901857

Sponsor

Cairo University

Status

Unknown status

Last Update Posted

Jun 13, 2023Actual

Enrollment

22Estimated

Phase

Not provided

Conditions

Age Problem

Interventions

convolutional neural network

Countries

Egypt

Protocol Section

Identification Module Status Module Sponsor/Collaborators Module Oversight Module Description Module Conditions Module Design Module Arms/Interventions Module Outcomes Module Eligibility Module Contacts/Locations Module References Module IPD Sharing Statement Module

Results Section

Participant Flow Module Baseline Characteristics Module Outcome Measures Module Adverse Events Module More Info Module

Annotation Section

Annotation Module

Document Section

Large Document Module

Derived Section

Miscellaneous Info Module Condition Browse Module Intervention Browse Module

Protocol Section

Identification Module

NCT ID

Results Section

No data available

No data is available for this block.

Annotation Section

No data available

No data is available for this block.

Document Section

No data available

No data is available for this block.

Derived Section

Miscellaneous Info Module

Version Holder

Status Module

Record Verification Date

Jun 2023

Overall Recruitment Status or Expanded Access Status

Unknown status

Last Known Status

Recruiting

Delayed Posting

Not provided

Why Stopped

Not provided

Expanded Access Info

Start Date

Jun 30, 2023Estimated

Primary Completion Date

Jan 1, 2024Estimated

Completion Date

Dec 1, 2025Estimated

First Submitted Date

May 12, 2023

First Submission Date that Met QC Criteria

Jun 4, 2023

First Posted Date

Jun 13, 2023Actual

Results Waived

Not provided

Results First Submitted Date

Not provided

Results First Submitted that Met QC Criteria

Not provided

Results First Posted Date

Not provided

Certification/Extension (aka Delayed Results) First Submitted Date

Not provided

Certification/Extension First Submitted that Passed QC Review

Not provided

Certification/Extension First Posted Date

Not provided

Last Update Submitted Date

Jun 4, 2023

Last Update Posted Date

Jun 13, 2023Actual

Sponsor/Collaborators Module

Responsible Party, by Official Title

Rawan Abdel Wahhab Bahaa Eldin Elkassas, Principal Investigator, Cairo UniversityPrincipal Investigator

Lead Sponsor

Cairo UniversityOTHER

Collaborators

Not provided

Oversight Module

Has Data Monitoring Committee (DMC)

Not provided

Is FDA Regulated Drug

Is FDA Regulated Device

Is Unapproved Device

Not provided

Pediatric Postmarket Surveillance of a Device Product

Not provided

Product Exported from US

Not provided

FDAAA801 Violation

Not provided

Description Module

Brief Summary

The aim of this study is to assess the accuracy of a convolutional neural network in dental age estimation from digital panoramic radiographs. The reference standard will be the chronological age of the patient.

Detailed Description

Willems method is a dental age estimation technique modiﬁed from Demirjian method by creating new tables from which a maturity score is directly expressed in years.

Panoramic radiographs of all participants will be taken with their informed consent, then they will be numbered and coded. Chronological age for each participant will be calculated by subtracting date of birth from date of radiograph and the real age will be blinded from the researcher (The chronological age is the ground truth). All panoramic radiographs will be examined twice by the main author to determine the dental age according to Willems method.

The seven mandibular left teeth excluding the third molar will be scored as '0' for absence of calcification, and 'A' to 'H', depending on the stage of calcification. Each letter corresponds to a score which is the dental age fraction using tables for boys and girls. Summing the scores for the seven left mandibular teeth directly will result in the estimated dental age. The dental radiologist estimation accurancy will be compared to the ground truth (first index test).

The second index test which will also be compared to the ground truth is the CNN model. To prepare the dataset for the CNN model, a rigorous preprocessing procedure will be followed. This will involve resizing the images to the desired dimensions, segmenting the teeth parts to be included in the image, and applying data augmentation techniques to enhance the quality and quantity of the dataset. The dataset will then be split into training and testing sets using a 20:80 ratio, which will be carefully selected based on the expected number of samples. Also the accuracy of the model will be assessed compared to the ground truth (the chronological ages).

Design Module

Study Type

Observational

Number of References to an Expanded Access Study

Not provided

Expanded Access Types

Not provided

Patient Registry

Target Follow-Up Duration

Not provided

Phases

Not provided

Interventional Study Design

Allocation

Not provided

Intervention Model

Biospecimen

No data available

No data is available for this block.

Enrollment

22Estimated

Arms/Interventions Module

Arm Groups

Not provided

Interventions

Name	Type	Description	Arm Group Labels	Other Names
convolutional neural network	Diagnostic Test	A deep learning model for dental age classification from panoramic images

Outcomes Module

Primary Outcomes

Measure	Description	Time Frame
Accuracy of dental age estimation from digital panoramic radiographs using CNN models	Percentage	Through study completion, an average of 1 year

Secondary Outcomes

Not provided

Other Outcomes

Not provided

Eligibility Module

Eligibility Criteria

Inclusion Criteria:

Presence of all mandibular left permanent teeth (except third molars)
Clearly visible root development
No systemic disease
No history of root canal therapy or extraction
No related diseases affecting mandibular development such as cysts or tumors.

Exclusion Criteria:

Patients with premature birth
Facial asymmetry
Congenital anomalies
History of trauma or surgery in dentofacial region

Accepts Healthy Volunteers

Not provided

Sex

All

Sex/Gender Based

Not provided

Sex/Gender Description

Not provided

Minimum Age

6 Years

Maximum Age

16 Years

Standard Ages

Child

Study Population

Panoramic radiographs will be recruited from Faculty of Dentistry, Oral Radiology Department.

Sampling Method

Probability Sample

Contacts/Locations Module

Central Contacts

Name	Role	Phone	Extension	Email
Rawan Elkassas	Contact	+201011385738		rawanelkassas@gmail.com

Overall Officials

Name	Affiliation	Role
Mohab Eid	Nile University	Study Chair

Locations

Facility	Status	City	State	ZIP	Country	Contacts
Rawan Elkassas	Recruiting	Cairo			Egypt

References Module

Citations

PubMed Identifier	Type	Citation	Retractions
32239317	Background	Banar N, Bertels J, Laurent F, Boedi RM, De Tobel J, Thevissen P, Vandermeulen D. Towards fully automated third molar development staging in panoramic radiographs. Int J Legal Med. 2020 Sep;134(5):1831-1841. doi: 10.1007/s00414-020-02283-3. Epub 2020 Apr 1.
31160078	Background	Ekert T, Krois J, Meinhold L, Elhennawy K, Emara R, Golla T, Schwendicke F. Deep Learning for the Radiographic Detection of Apical Lesions. J Endod. 2019 Jul;45(7):917-922.e5. doi: 10.1016/j.joen.2019.03.016. Epub 2019 Jun 1.

ID	Term
D016571	Neural Networks, Computer
D055641	Mathematical Concepts