Reconstruction Technology to Auxiliary Diagnosis and Guarantee Patient Privacy
Study Details
Study Description
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.
Condition or Disease | Intervention/Treatment | Phase |
---|---|---|
|
Study Design
Arms and Interventions
Arm | Intervention/Treatment |
---|---|
facial videos dataset facial videos collected from Zhongshan Ophthalmic Center of Sun Yat-sen University. |
Diagnostic Test: DM
A new technology based on 3D reconstruction and deep learning algorithm to irreversibly erase the biometric attributes whilst retaining the clinical attributes needed for diagnosis and management
|
Outcome Measures
Primary Outcome Measures
- 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.
Eligibility Criteria
Criteria
Inclusion Criteria:
- The quality of facial images should be clinically acceptable.
Contacts and Locations
Locations
Site | City | State | Country | Postal Code | |
---|---|---|---|---|---|
1 | Zhongshan Ophthalmic Center | Guangzhou | Guangdong | China | 510000 |
Sponsors and Collaborators
- Sun Yat-sen University
Investigators
None specified.Study Documents (Full-Text)
None provided.More Information
Publications
None provided.- 2021KYPJ77