🤖 AI Summary
Clinical gait videos for movement disorder diagnosis face dual challenges: privacy leakage and kinematic analysis distortion. Manual de-identification is inefficient and inconsistent, while pre-processing blur degrades pose estimation accuracy. This paper proposes the first end-to-end framework jointly optimizing privacy preservation and motion analysis fidelity. It integrates a lightweight OpenPose-based pose estimator, DeepSORT-based multi-object tracking, adaptive face detection, and dynamic region-specific blurring—fully deployed in real time on iPad. Crucially, it overcomes pose distortion inherent in conventional “blur-then-analyze” pipelines by performing privacy masking *after* kinematic feature extraction. The system enables precise patient identification and personalized facial anonymization in outpatient settings. Evaluated on 116 cerebral palsy pediatric gait videos, it achieves >91.08% facial blurring accuracy, reduces processing time by 91.08% versus manual annotation, significantly lowers kinematic extraction error, and receives strong clinical usability endorsement from domain experts.
📝 Abstract
Movement disorders are typically diagnosed by consensus-based expert evaluation of clinically acquired patient videos. However, such broad sharing of patient videos poses risks to patient privacy. Face blurring can be used to de-identify videos, but this process is often manual and time-consuming. Available automated face blurring techniques are subject to either excessive, inconsistent, or insufficient facial blurring - all of which can be disastrous for video assessment and patient privacy. Furthermore, assessing movement disorders in these videos is often subjective. The extraction of quantifiable kinematic features can help inform movement disorder assessment in these videos, but existing methods to do this are prone to errors if using pre-blurred videos. We have developed an open-source software called SecurePose that can both achieve reliable face blurring and automated kinematic extraction in patient videos recorded in a clinic setting using an iPad. SecurePose, extracts kinematics using a pose estimation method (OpenPose), tracks and uniquely identifies all individuals in the video, identifies the patient, and performs face blurring. The software was validated on gait videos recorded in outpatient clinic visits of 116 children with cerebral palsy. The validation involved assessing intermediate steps of kinematics extraction and face blurring with manual blurring (ground truth). Moreover, when SecurePose was compared with six selected existing methods, it outperformed other methods in automated face detection and achieved ceiling accuracy in 91.08% less time than a robust manual face blurring method. Furthermore, ten experienced researchers found SecurePose easy to learn and use, as evidenced by the System Usability Scale. The results of this work validated the performance and usability of SecurePose on clinically recorded gait videos for face blurring and kinematics extraction.