Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Sep 7;21(1):65.
doi: 10.1186/s12938-022-01036-0.

Classification of facial paralysis based on machine learning techniques

Amira Gaber  1 , Mona F Taher  2 , Manal Abdel Wahed  2 , Nevin Mohieldin Shalaby  3 , Sarah Gaber  4
Affiliations

Classification of facial paralysis based on machine learning techniques

Amira Gaber et al. Biomed Eng Online. .

Abstract

Facial paralysis (FP) is an inability to move facial muscles voluntarily, affecting daily activities. There is a need for quantitative assessment and severity level classification of FP to evaluate the condition. None of the available tools are widely accepted. A comprehensive FP evaluation system has been developed by the authors. The system extracts real-time facial animation units (FAUs) using the Kinect V2 sensor and includes both FP assessment and classification. This paper describes the development and testing of the FP classification phase. A dataset of 375 records from 13 unilateral FP patients and 1650 records from 50 control subjects was compiled. Artificial Intelligence and Machine Learning methods are used to classify seven FP categories: the normal case and three severity levels: mild, moderate, and severe for the left and right sides. For better prediction results (Accuracy = 96.8%, Sensitivity = 88.9% and Specificity = 99%), an ensemble learning classifier was developed rather than one weak classifier. The ensemble approach based on SVMs was proposed for the high-dimensional data to gather the advantages of stacking and bagging. To address the problem of an imbalanced dataset, a hybrid strategy combining three separate techniques was used. Model robustness and stability was evaluated using fivefold cross-validation. The results showed that the classifier is robust, stable and performs well for different train and test samples. The study demonstrates that FAUs acquired by the Kinect sensor can be used in classifying FP. The developed FP assessment and classification system provides a detailed quantitative report and has significant advantages over existing grading scales.

Keywords: Ensemble classification; Facial animation units; Facial paralysis; Grading; Kinect; Machine learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Fig. 1
Fig. 1
Variation of K-NN accuracies with changing the number of nearest neighbors parameter (from 1 to 9) in the five classifiers: a smiling, b closing eyes, c raising eyebrows, d blowing cheeks, and e whistling
Fig. 2
Fig. 2
Block diagram of Facial Paralysis Evaluation system
Fig. 3
Fig. 3
Detailed analysis of features in each stage of FP evaluation
Fig. 4
Fig. 4
Framework of the classifiers and the corresponding features from the grading and symmetry modules
Fig. 5
Fig. 5
Framework of Facial Paralysis Classification approach
Fig. 6
Fig. 6
Flowchart of the rule-based classifier procedure
See this image and copyright information in PMC

References

    1. Song A, Wu Z, Ding X, Hu Q, Di X. Neurologist standard classification of facial nerve paralysis with deep neural networks. Future Internet. 2018;10(11):111.
    1. Walker W. Facial Paralysis—Physiopedia. [Online]. Available: https://www.physio-pedia.com/Facial_Palsy. [Accessed 11 November 2021].
    1. Finsterer J. Management of peripheral facial nerve palsy. Eur Arch Otorhinolaryngol. 2008;265(7):743–752. - PMC - PubMed
    1. Mavrikakis I. Facial nerve palsy: anatomy, etiology, evaluation, and management. Orbit. 2008;27:466–474. - PubMed
    1. Sajid M, Shafique T, Baig MJ, Riaz I, Amin S, Manzoor S. Automatic grading of palsy using asymmetrical facial features: a study complemented by new solutions. Symmetry. 2018;10(7):242.

LinkOut - more resources