Facial images can be used to identify signs of disease in diagnosis (诊断). For example, abnormal changes in eye movement can indicate poor visual function and visual developmental problems. However, facial images also record other information about the patients, including their race, sex, age and mood. Due to privacy concerns, people often hesitate to share their facial images for public medical research or electronic health records, blocking the development of digital medical care.
The researchers now develop a digital mask, which inputs an original video of a patient’s face and outputs a video based on the use of a deep learning algorithm (算法)and 3D reconstruction. At the same time, the digital mask can remove as much of the patient’s personal biometric (生物统计的)information as possible.
Next, the researchers tested how useful the masks were in clinical practice and found that diagnosis through the digital masks agrees with that carried out through the original videos. This suggested that the technology was accurate enough in clinical practice. The team also confirmed that the digital masks can also avoid artificial intelligence-powered facial recognition.
The team surveyed randomly (随机地)selected patients attending clinics to test their attitudes towards digital masks. Over 80% of patients believed the digital masks would ease their privacy concerns and they expressed an increased willingness to share their personal information if such a measure was carried out.
Professor Patrick from the University of Cambridge said, “Digital masks offer a practical approach to protecting information from facial images, while still allowing the information to be useful to clinicians.” This could make telemedicine-phone and video consultations, much more practicable, making healthcare delivery more efficient especially during the COVID-19 pandemic. If tele-medicine is to be widely adopted, then we need to overcome the barriers and concerns related to privacy protection. The digital mask is an important step in this direction.
【小题1】What is the problem with the facial images in diagnosis?| A．Its result may be inaccurate. |
| B．Its process is too complicated. |
| C．It may reveal patients’ privacy. |
| D．It fails to observe eye movement. |
| A．It preserves biometric information of patients. |
| B．It can prevent the individual being identified. |
| C．It has high requirements for the original videos. |
| D．It helps doctors diagnose disease more accurately. |
| A．Objective. |
| B．Cautious. |
| C．Critical. |
| D．Supportive. |
| A．The significance of the digital mask. |
| B．The future development of telemedicine. |
| C．The barriers to protecting patients’ privacy. |
| D．The practical ways to protect patients’ privacy. |
