AI-Assisted Facial Surgical Planning

NCT04319055 | Completed

• 1 other identifier: 201908066RIND
• Study Type: observational
• Target: 17,932
• Locations: 1 country
• Sites: 1

Brief Summary

Computer vision using deep learning architecture is broadly used in auto-recognition. In the research, the deep learning model which is trained by categorized single-eye images is applied to achieve the good performance of the model in blepharoptosis auto-diagnosis.

Conditions

Facial Plastic and Reconstructive Surgery; Periocular Diseases; Orbital Diseases; Artificial Intelligence

Keywords

Facial Plastic and Reconstructive Surgery; Periocular Diseases; Orbital Diseases; Artificial Intelligence

Outcome Measures

Primary Outcomes (4)

• The model performance is evaluated by accuracy

  An Artificial Intelligence Approach

  Through study completion, an average of 1 year

• AUC (Area Under the Curve)

  An Artificial Intelligence Approach

  Through study completion, an average of 1 year

• ROC (Receiver Operating Characteristics) curve.

  An Artificial Intelligence Approach

  Through study completion, an average of 1 year

• An Artificial Intelligence Approach to Identifying Facial, Periocular, and Orbital Diseases

  The model interpretability is accessed by Grad-CAM (Class Activation Maps).

  Through study completion, an average of 1 year

Eligibility Criteria

• Age: 20 Years - 65 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

All data was collected at ophthalmic outpatient clinics of National Taiwan University Hospital.

You may qualify if:

• The participants who were 20-year-old or above,
• Surgical informed consent was endorsed by the participants themselves,
• Participants who have surgical indications of the oculofacial surgeries, and
• The participants who agreed on photograph taking after explanation by the surgeon at outpatient clinics.

You may not qualify if:

• The participants who were 19-year-old or under,
• The participants who don't have surgical indications of the oculofacial surgeries,
• The participants who were designed for minimal invasive treatments, such as Botox or any kind of fillers injection,
• The participants who refused photograph taking for any reason, and
• The participants who are not available for standard quality of photograph taking, such as bedridden patients.

Sponsors & Collaborators

• National Taiwan University Hospital: lead
• Stanford University: collaborator

Study Sites (1)

National Taiwan University Hospital

Taipei, Taiwan

Location

MeSH Terms

Conditions

Orbital Diseases

Condition Hierarchy (Ancestors)

Eye Diseases

Study Officials

• Shu-Lang Liao, MD,MPH, EMBA

  National Taiwan University Hospital

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: March 3, 2020
• First Posted: March 24, 2020
• Study Start: January 1, 2009
• Primary Completion: December 31, 2018
• Study Completion: July 30, 2019
• Last Updated: February 18, 2021

Record last verified: 2021-02

Data Sharing

• IPD Sharing: Will not share

Locations

TW (1)