Scientists have created a “digital mask” that will allow facial images to be stored in medical records while preventing the extraction of personal biometric information.
In a paper published Thursday in Nature Medicine, a team led by scientists from the University of Cambridge and Sun Yat-sen University, China, revealed they use three-dimensional (3D) reconstruction algorithms to erase identifiable features facial images while maintaining the relevant features necessary for diagnoses.
Facial images can be useful in identifying signs of disease, but also other biometric information about the patient, including race, gender, age, or mood.
With the increasing digitization of medical records comes the risk of data breaches and facial data is more difficult to anonymize while retaining critical information. Common methods, including blurring and cropping of identifiable areas, can lose important disease information, but cannot even completely escape facial recognition systems.
For privacy reasons, people are often reluctant to share their medical data for public medical research or electronic health records, which hampers the development of digital medical care.
Compared to the traditional method used to “anonymize” patients, i.e. cropping the image, the risk of being identified was significantly lower in digitally masked patients.
The researchers tested this by showing 12 eye doctors digitally masked or cropped images and asking them to identify the original from five other images. They correctly identified the original from the digitally masked image in just over a quarter (27%) of cases; for cropped images, they were able to do so in the vast majority of cases (91%).
The team interviewed randomly selected patients attending clinics to gauge their attitude towards digital masks. Over 80% of patients believed the digital mask would alleviate their privacy concerns and would be more likely to share their personal information if such a measure were implemented.
The research team also confirmed that digital masks can evade AI-based facial recognition algorithms.