OpticalDR: A Deep Optical Imaging Model for Privacy-Protective Depression Recognition
This addresses privacy risks in automated depression diagnosis for patients by providing an incremental improvement in privacy protection while maintaining diagnostic accuracy.
The paper tackles privacy concerns in depression recognition by designing an optical imaging system that erases identity information from facial images while retaining disease-relevant features, achieving state-of-the-art privacy protection with an average AUC of 0.51 and competitive depression recognition results with MAE/RMSE of 7.53/8.48 on AVEC 2013 and 7.89/8.82 on AVEC 2014.
Depression Recognition (DR) poses a considerable challenge, especially in the context of the growing concerns surrounding privacy. Traditional automatic diagnosis of DR technology necessitates the use of facial images, undoubtedly expose the patient identity features and poses privacy risks. In order to mitigate the potential risks associated with the inappropriate disclosure of patient facial images, we design a new imaging system to erase the identity information of captured facial images while retain disease-relevant features. It is irreversible for identity information recovery while preserving essential disease-related characteristics necessary for accurate DR. More specifically, we try to record a de-identified facial image (erasing the identifiable features as much as possible) by a learnable lens, which is optimized in conjunction with the following DR task as well as a range of face analysis related auxiliary tasks in an end-to-end manner. These aforementioned strategies form our final Optical deep Depression Recognition network (OpticalDR). Experiments on CelebA, AVEC 2013, and AVEC 2014 datasets demonstrate that our OpticalDR has achieved state-of-the-art privacy protection performance with an average AUC of 0.51 on popular facial recognition models, and competitive results for DR with MAE/RMSE of 7.53/8.48 on AVEC 2013 and 7.89/8.82 on AVEC 2014, respectively.