Objective measurement of hemifacial spasms severity via facial recognition: Unveiling correlations with quality of life
Ahmed Al Menabbawy (Greifswald; Cairo / EG), Lennart Ruhser (Greifswald), Ehab EL Refaee (Greifswald; Kairo / EG), Martin Weidemeier (Greifswald), Marc Matthes (Greifswald), Henry W. S. Schroeder (Greifswald)
Severity of hemifacial spasm impairs the quality of life of affected individuals. Although many classification and grading systems have been developed, they are almost always subjective without accurate quantification of the spasms. In this study we lever the usage of facial recognition and facial tracking technology in order to accurately quantify the spasms severity and be able to classify patients according to severity and distribution of the spasms.
Preoperative video recordings of the facial spasms with durations of at least 15 sec including the whole face were included. Videos were analyzed using Apple AR kit for facial tracking where after recognition of the face a mesh is allocated to specific biometric facial points. videos were then evaluated using Blender open-source software for measuring the amplitude and frequency of the spasms. Classification of the patients into groups was done using both divisive k-means and agglomerative hierarchical clustering. Correlation-Analysis with preoperative quality of Life (Qol) using SF-36 questionnaire scores was then performed.
79 preoperative videos could be accurately analyzed. Both up-bottom and bottom-up clustering approaches clustered the patients into 3 different groups/clusters according to the 4 variables (eye closure, mouth distance change, rate, and repetition of the spasms). Correlation of the groups with the Qol was done only for 45/79 patients (57%). Group 1 (Mainly tonic affection of the mouth and sparing the eye). Group 2 (highest frequency and repitition (clonic group). Group 3 (severe tonic affection of both the eye and mouth). Group 2 (clonic group) showed better total average and emotional Qol score in comparison to the other two groups.
Using facial recognition and tracking technologies can accurately classify and quantify the facial spasms and their severity over time as well as pre with postintervention. Hemifacial spasms can be classified into three groups according to frequency and amplitude of the spasms. Group 2 (clonic group) has the best quality of life among the three groups.
We use cookies on our website. Cookies are small (text) files that are created and stored on your device (e.g., smartphone, notebook, tablet, PC). Some of these cookies are technically necessary to operate the website, other cookies are used to extend the functionality of the website or for marketing purposes. Apart from the technically necessary cookies, you are free to allow or not allow cookies when visiting our website.