Technology UK CU – As the digital world expands, privacy’s concerns are becoming more and more of a huge concern for the public. Privacy for medical information is even more of a concern for most of a people, however researchers have developed a novel technique that could possibly address some of the concerns surrounding privacy.
Scientist from Cambridge and China have developed a 3D reconstruction and deep learning algorithms to efface characteristics that can reveal identity of facial images while retaining disease-relevant characteristics required for diagnosis.
Facial images usually display signs of disease. These include deep forehead wrinkles and wrinkles around the eyes which are closely linked to coronary heart disease, whereas unusual changes in eye movement can point to poor visual functions and visual cognitive developmental problems, yet facial images also can record other biometric details of patients, such as race, sex, age and mood.
The rapid digital transformation of medical records also risks data leaks. Patient data can usually be anonymized, however anonymizing facial data while keeping essential information is more complex.
Privacy concerns, are a huge obstacle for most people in sharing medical data linked to public medical research for electronic health records, which has seen a push back for digital medical care.
Professor Haotian Lin, Sun Yat-sen of the University, Guangzhou, China said “During the COVID-19 pandemic, we had to turn to consultations over the phone or by video link rather than in person. Remote healthcare for eye diseases requires patients to share a large amount of digital facial information. Patients want to know that their potentially sensitive information is secure and that their privacy is protected.”
Professor Lin and the team produced a ‘digital mask’, where an original video of a person’s face and outputs a video eliminating much of the persons biometric information as possible preventing identification.
The researchers hope to use the technology to make telemedicine, phone and video consultations more effective.
