Advanced Statistical Analysis of 3D Kinect Data: Mimetic Muscle Rehabilitation Following Head and Neck Surgeries Causing Facial Paresis

Abstract

An advanced statistical analysis of patients’ faces after specific surgical procedures that temporarily negatively affect the patient’s mimetic muscles is presented. For effective planning of rehabilitation, which typically lasts several months, it is crucial to correctly evaluate the improvement of the mimetic muscle function. The current way of describing the development of rehabilitation depends on the subjective opinion and expertise of the clinician and is not very precise concerning when the most common classification (House–Brackmann scale) is used. Our system is based on a stereovision Kinect camera and an advanced mathematical approach that objectively quantifies the mimetic muscle function independently of the clinician’s opinion. To effectively deal with the complexity of the 3D camera input data and uncertainty of the evaluation process, we designed a three-stage data-analytic procedure combining the calculation of indicators determined by clinicians with advanced statistical methods including functional data analysis and ordinal (multiple) logistic regression. We worked with a dataset of 93 distinct patients and 122 sets of measurements. In comparison to the classification with the House–Brackmann scale the developed system is able to automatically monitor reinnervation of mimetic muscles giving us opportunity to discriminate even small improvements during the course of rehabilitation.

Advanced Statistical Analysis of 3D Kinect Data: A Comparison of the Classification Methods

“…This work builds on previous publications and the work of several research groups dealing with similar topics [13].…”

“…The whole process of data preprocessing is thoroughly described in a recent paper [13]. To make this paper self-contained, let us briefly review this process here.…”

“…The warping functions w i are computed by a landmark registration technique, where the beginnings and end of each repetition are identified and a piecewise cubic interpolation is used for the warping function. A more detailed description of the used registration technique can be found in [13].…”

“…The resulting indicator curves measure symmetry (movements in the left-half versus movements in the right-half of the face), intensity (the range of motion during the exercise), and speed (how fast the selected exercise is performed, measured by the warping function). The exact definition of all computed indicators is described in [13].…”

“…Detailed description of the parametric statistical model for HB classification can be found in [13]. Let us recall that within this approach, the curves of the indicators are analysed by two parametric statistical models in two steps:…”