Reconstruction Technology to Auxiliary Diagnosis and Guarantee Patient Privacy

• Conditions: 3D-reconstruction; Patient Privacy; Deep Learning; Digital Medicine
• Interventions: Diagnostic Test: DM

• Registration Number: NCT05058599
• Lead Sponsor: Sun Yat-sen University

Brief Summary

Medical data that contain facial images are particularly sensitive as they retain important personal biometric identity, privacy protection. We developed a novel technology called "Digital Mask" (DM), based on real-time three-dimensional (3D) reconstruction and deep learning algorithm, to extract disease-relevant features but remove patient identifiable features from facial images of patients.

Detailed Description

Not available

Study Timeline

• Study Start: 2020-05-10
• Status Verified: 2021-09
• Study First Submitted: 2021-09-16
• Study First Submitted QC: 2021-09-16
• Last Update Submitted: 2021-09-16
• Primary Completion: 2021-09-20
• Study First Posted: 2021-09-28
• Last Update Posted: 2021-09-28
• Study Completion: 2022-01-30

Recruitment & Eligibility

• Status: UNKNOWN
• Sex: All
• Target Recruitment: 400

Inclusion Criteria

• The quality of facial images should be clinically acceptable.

Exclusion Criteria

Not provided

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
facial videos dataset	DM	facial videos collected from Zhongshan Ophthalmic Center of Sun Yat-sen University.

Primary Outcome Measures

Name	Time	Method
Diagnostic consistency	baseline	For each eye, both the diagnosis from the original videos and the diagnosis from the DM-reconstructed videos were recorded and compared. If the two diagnoses were consistent, it suggests that the reconstruction would be precise enough in clinical practice.

Trial Locations

Locations (1)

Zhongshan Ophthalmic Center; 🇨🇳 Guangzhou, Guangdong, China