Digital mask to safeguard sensitive info in patient facial images

A patient’s facial image data – while extremely useful when it comes to identifying and diagnosing disease – is susceptible to data breaches and is not easily anonymised for medical recordkeeping. A joint team of researchers from the University of Cambridge, UK, and Sun Yat-sen University in Guangzhou, China, have introduced a “digital mask” that enables secure storage of facial images, at the same time preventing potentially sensitive personal biometric information that can be derived from these images from being leaked out.

Facial images are important markers of identifying signs of disease: for example, features such as deep forehead wrinkles and wrinkles around the eyes are significantly associated with coronary heart disease, while abnormal changes in eye movement can indicate poor visual function and visual cognitive developmental problems.

However, facial images also inevitably record other biometric information about the patient, including their race, sex, age and mood – details which are to be kept private. This, combined with the risk of data breaches, has led to widespread reluctance to share medical data for public medical research or electronic health records, hindering the development of digital medical care.

The team successfully used three-dimensional (3D) reconstruction and deep learning algorithms to create a digital mask that would erase identifiable features from facial images while retaining disease-relevant features needed for diagnosis. The digital mask would reconstruct a face, complete with eyelids and eyeballs, in a new output video.

Converting the output videos of 3D faces back to the original videos is extremely difficult because most of the necessary personal information is no longer retained in the mask – in simple terms, it is not possible to identify the individual from the digital mask video.

In tests, the researchers noted how useful the masks were in clinical practice and found that diagnosis using the digital masks was consistent with that carried out using the original videos. This suggests that the reconstruction was precise enough for use in clinical practice.

Professor Haotian Lin from Sun Yat-sen University, had earlier raised a concern, “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.”

“Digital masking offers a pragmatic approach to safeguarding patient privacy while still allowing the information to be useful to clinicians. At the moment, the only options available are crude, but our digital mask is a much more sophisticated tool for anonymising facial images,” answered Professor Patrick Yu-Wai-Man from the University of Cambridge.

“This could make telemedicine [phone and video consultations] much more feasible, making healthcare delivery more efficient. If telemedicine is to be widely adopted, then we need to overcome the barriers and concerns related to privacy protection. Our digital mask is an important step in this direction.”

Category: Uncategorized