3D-reconstruction, Patient Privacy, Deep Learning, Digital Medicine
Conditions
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.
Interventions
DIAGNOSTIC_TESTDM
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
Sponsors
Sun Yat-sen University
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Healthy volunteers
Yes
Inclusion criteria
* The quality of facial images should be clinically acceptable.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| 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. |
Countries
China
Contacts
Primary ContactHaotian Lin
Outcome results
None listed